Trust in Institutions
Alex Flores
2025-07-07
Prep
Libraries & Data
library(tidyverse)
library(sandwich)
library(gtsummary)
library(flextable)
library(tables)
library(psych)
library(ggplot2)
library(openxlsx)
library(lmerTest)
library(lme4)
library(knitr)
library(hrbrthemes)
library(interactions)
d <- read.csv("/Users/af13/Documents/Research/24_ElectionStudy/data + analyses/2024ElectionStudy_combined_cleancases.csv", na.strings = c("","NA"), header = T, fileEncoding="latin1")mcSummary() function
Variable Construction
Single-measures
# numeracy
d <- d %>%
group_by(pid) %>%
fill(numeracy, .direction = "downup") %>%
ungroup()
addmargins(table(d$numeracy,d$wave, exclude = F))
# trustGovt
d[d$wave == 1 | d$wave == 2,] <- d[d$wave == 1 | d$wave == 2,] %>%
group_by(pid) %>%
fill(trustGovt1, .direction = "downup") %>%
ungroup()
addmargins(table(d$trustGovt1,d$wave, exclude = F))
d[d$wave == 1 | d$wave == 2,] <- d[d$wave == 1 | d$wave == 2,] %>%
group_by(pid) %>%
fill(trustGovt2, .direction = "downup") %>%
ungroup()
addmargins(table(d$trustGovt2,d$wave, exclude = F))
d$trustGovt <- rowMeans(d[,c("trustGovt1","trustGovt2")], na.rm = T)
d$trustGovt.c <- d$trustGovt - mean(d$trustGovt, na.rm = T)
# trustSci
psych::alpha(d[ ,c("trustSci_1","trustSci_2","trustSci_3","trustSci_4")])
d <- d %>%
group_by(pid) %>%
fill(trustSci_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$trustSci_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(trustSci_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$trustSci_2,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(trustSci_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$trustSci_3,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(trustSci_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$trustSci_4,d$wave, exclude = F))
d$trustSci <- rowMeans(d[, c("trustSci_1", "trustSci_2", "trustSci_3", "trustSci_4")], na.rm = T)
table(d$trustSci, d$wave)
# affProj_Trump
d[d$wave == 2 | d$wave == 3,] <- d[d$wave == 2 | d$wave == 3,] %>%
group_by(pid) %>%
fill(affProj_Trump_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$affProj_Trump_1,d$wave, exclude = F))
d[d$wave == 2 | d$wave == 3,] <- d[d$wave == 2 | d$wave == 3,] %>%
group_by(pid) %>%
fill(affProj_Trump_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$affProj_Trump_2,d$wave, exclude = F))
d[d$wave == 2 | d$wave == 3,] <- d[d$wave == 2 | d$wave == 3,] %>%
group_by(pid) %>%
fill(affProj_Trump_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$affProj_Trump_3,d$wave, exclude = F))
d[d$wave == 2 | d$wave == 3,] <- d[d$wave == 2 | d$wave == 3,] %>%
group_by(pid) %>%
fill(affProj_Trump_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$affProj_Trump_4,d$wave, exclude = F))
# punitive policies
d <- d %>%
group_by(pid) %>%
fill(deathpenalty, .direction = "downup") %>%
ungroup()
addmargins(table(d$deathpenalty,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(abortionban, .direction = "downup") %>%
ungroup()
addmargins(table(d$abortionban,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(ICEraids, .direction = "downup") %>%
ungroup()
addmargins(table(d$ICEraids,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(gunctrl, .direction = "downup") %>%
ungroup()
addmargins(table(d$gunctrl,d$wave, exclude = F))
addmargins(table(d$gunctrl,d$wave))
d <- d %>%
group_by(pid) %>%
fill(vaxxpass, .direction = "downup") %>%
ungroup()
addmargins(table(d$vaxxpass,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(hatespeech, .direction = "downup") %>%
ungroup()
addmargins(table(d$hatespeech,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(jailCEOs, .direction = "downup") %>%
ungroup()
addmargins(table(d$jailCEOs,d$wave, exclude = F))
# ideological position based on punitive policies
## deathpenalty, abortionban, ICEraids, gunctrl => negative = more liberal, positive = more conservative
## vaxxpass, hatespeech, jailCEOs => positive = more liberal, negative = more conservative
d$vaxxpass.r <- d$vaxxpass * -1
d$hatespeech.r <- d$hatespeech * -1
d$jailCEOs.r <- d$jailCEOs * -1
describe(d[,c('deathpenalty', 'abortionban', 'ICEraids', 'gunctrl','vaxxpass.r', 'hatespeech.r', 'jailCEOs.r')])
d$issue_ideology <- rowMeans(d[,c('deathpenalty', 'abortionban', 'ICEraids', 'gunctrl','vaxxpass.r', 'hatespeech.r', 'jailCEOs.r')], na.rm = T)
psych::alpha(d[,c('deathpenalty', 'abortionban', 'ICEraids', 'gunctrl','vaxxpass.r', 'hatespeech.r', 'jailCEOs.r')]) # a bit low!
# hist(d$issue_ideology)
psych::describe(d$issue_ideology) # that is a normal distribution
d <- d %>%
group_by(pid) %>%
fill(issue_ideology, .direction = "downup") %>%
ungroup()
addmargins(table(d$issue_ideology,d$wave, exclude = F))
# climate change belief
d$climbel_1 <- d$climatechange_belief_1
d$climbel_2 <- d$climatechange_belief_2
d$climbel_3 <- d$climatechange_belief_3
d$climbel_4 <- d$climatechange_belief_4
d <- d %>%
group_by(pid) %>%
fill(climatechange_belief_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$climatechange_belief_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(climatechange_belief_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$climatechange_belief_2,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(climatechange_belief_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$climatechange_belief_3,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(climatechange_belief_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$climatechange_belief_4,d$wave, exclude = F))
# GCB
d <- d %>%
group_by(pid) %>%
fill(GCB_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$GCB_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(GCB_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$GCB_2,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(GCB_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$GCB_3,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(GCB_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$GCB_4,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(GCB_5, .direction = "downup") %>%
ungroup()
addmargins(table(d$GCB_5,d$wave, exclude = F))
# AI risk
d <- d %>%
group_by(pid) %>%
fill(AIrisk_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$AIrisk_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(AIrisk_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$AIrisk_2,d$wave, exclude = F))
# Group FT
d <- d %>%
group_by(pid) %>%
fill(FT_groups_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$FT_groups_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(FT_groups_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$FT_groups_2,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(FT_groups_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$FT_groups_3,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(FT_groups_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$FT_groups_4,d$wave, exclude = F))
# Religion
d <- d %>%
group_by(pid) %>%
fill(religion, .direction = "downup") %>%
ungroup()
addmargins(table(d$religion,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(Evangelical, .direction = "downup") %>%
ungroup()
addmargins(table(d$Evangelical,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(rel_importance, .direction = "downup") %>%
ungroup()
addmargins(table(d$rel_importance,d$wave, exclude = F))
# ZIP code
d <- d %>%
group_by(pid) %>%
fill(ZIPcode, .direction = "downup") %>%
ungroup()
addmargins(table(d$ZIPcode,d$wave, exclude = F))
# vote_MC
d <- d %>%
group_by(pid) %>%
fill(vote_MC_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$vote_MC_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(vote_MC_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$vote_MC_2,d$wave, exclude = F))
# Israel
table(d$israel)
d <- d %>%
group_by(pid) %>%
fill(israel, .direction = "downup") %>%
ungroup()
addmargins(table(d$israel,d$wave, exclude = F))
table(d$israel_usRole)
d <- d %>%
group_by(pid) %>%
fill(israel_usRole, .direction = "downup") %>%
ungroup()
addmargins(table(d$israel_usRole,d$wave, exclude = F))
d$israel_usRole <- as.numeric(as.character(d$israel_usRole))
# border
table(d$border_Harris)
d <- d %>%
group_by(pid) %>%
fill(border_Harris, .direction = "downup") %>%
ungroup()
addmargins(table(d$border_Harris,d$wave, exclude = F))
table(d$border_Trump)
d <- d %>%
group_by(pid) %>%
fill(border_Trump, .direction = "downup") %>%
ungroup()
addmargins(table(d$border_Trump,d$wave, exclude = F))
# polling
d <- d %>%
group_by(pid) %>%
fill(pollFreq, .direction = "downup") %>%
ungroup()
addmargins(table(d$pollFreq,d$wave, exclude = F))
d$pollFreq <- dplyr::recode(d$pollFreq,
`1` = 7,
`2` = 6,
`3` = 5,
`4` = 4,
`5` = 3,
`6` = 2,
`7` = 1)
d[d$wave == 1 | d$wave ==2,] <- d[d$wave == 1 | d$wave ==2,] %>%
group_by(pid) %>%
fill(pollAcc, .direction = "downup") %>%
ungroup()
d[d$wave == 3 | d$wave == 4,] <- d[d$wave == 3 | d$wave == 4,] %>%
group_by(pid) %>%
fill(pollAcc, .direction = "downup") %>%
ungroup()
addmargins(table(d$pollAcc,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(pollPred, .direction = "downup") %>%
ungroup()
addmargins(table(d$pollPred,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(pollsource, .direction = "downup") %>%
ungroup()
addmargins(table(d$pollsource,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(pollsource_7_TEXT, .direction = "downup") %>%
ungroup()
addmargins(table(d$pollsource_7_TEXT,d$wave, exclude = F))
# NFC
d <- d %>%
group_by(pid) %>%
fill(NFC6_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$NFC6_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(NFC6_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$NFC6_2,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(NFC6_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$NFC6_3,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(NFC6_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$NFC6_4,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(NFC6_5, .direction = "downup") %>%
ungroup()
addmargins(table(d$NFC6_5,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(NFC6_6, .direction = "downup") %>%
ungroup()
addmargins(table(d$NFC6_6,d$wave, exclude = F))
d$NFC <- rowMeans(d[,c("NFC6_1", "NFC6_2", "NFC6_3", "NFC6_4", "NFC6_5", "NFC6_6")], na.rm = T)
# Executive order measures
d <- d %>%
group_by(pid) %>%
fill(EO_impact_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_impact_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(EO_impact_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_impact_2,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(EO_impact_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_impact_3,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(EO_impact_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_impact_4,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(EO_valence_1, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_valence_1,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(EO_valence_2, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_valence_2,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(EO_valence_3, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_valence_3,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(EO_valence_4, .direction = "downup") %>%
ungroup()
addmargins(table(d$EO_valence_4,d$wave, exclude = F))
# gov't process measures
d <- d %>%
group_by(pid) %>%
fill(govt_process, .direction = "downup") %>%
ungroup()
addmargins(table(d$govt_process,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(representation_Dem, .direction = "downup") %>%
ungroup()
addmargins(table(d$representation_Dem,d$wave, exclude = F))
d <- d %>%
group_by(pid) %>%
fill(representation_Rep, .direction = "downup") %>%
ungroup()
addmargins(table(d$representation_Rep,d$wave, exclude = F))
# ideology
d <- d %>%
group_by(pid) %>%
fill(ideology, .direction = "downup") %>%
ungroup()
addmargins(table(d$ideology,d$wave, exclude = F))repeated measures
# emotions
d$Neg_Emo <- rowMeans(d[,c("Emotions_1", "Emotions_2", "Emotions_5")], na.rm = T)
psych::alpha(d[,c("Emotions_1", "Emotions_2", "Emotions_5")])
d$Neg_Emo.c <- d$Neg_Emo - mean(d$Neg_Emo, na.rm = T)
d$Pos_Emo <- rowMeans(d[,c("Emotions_3", "Emotions_4")], na.rm = T)
cor.test(d$Emotions_3, d$Emotions_4)
d$Pos_Emo.c <- d$Pos_Emo - mean(d$Pos_Emo, na.rm = T)
# vote confidence
d$voteconfidence <- rowMeans(d[,c('voteconf_natl','voteconf_self')], na.rm = T)
# party ID
## Creating continuous measure of party from branching ANES question
d$partyCont <- NA
d$partyCont[d$demStrength == 1] <- -3
d$partyCont[d$demStrength == 2] <- -2
d$partyCont[d$partyClose == 1] <- -1
d$partyCont[d$partyClose == 3] <- 0
d$partyCont[d$partyClose == 2] <- 1
d$partyCont[d$repStrength == 2] <- 2
d$partyCont[d$repStrength == 1] <- 3
## Creating factor measure of party from continuous measure
d$party_factor <- NA
d$party_factor[d$partyCont == -3 | d$partyCont == -2 | d$partyCont == -1] <- "Democrat"
d$party_factor[d$partyCont == 3 | d$partyCont == 2 | d$partyCont == 1] <- "Republican"
d$party_factor[d$partyCont == 0] <- "Independent"
table(d$party_factor)
# affective polarization
## Parties
d$FT_Outgroup <- ifelse(d$party_factor == "Democrat", d$FT_parties_2,
ifelse(d$party_factor == "Republican", d$FT_parties_1, NA))
d$FT_diff <- NA
d$FT_diff <- d$FT_parties_1 - d$FT_parties_2
## Politicians
d$FT_Outcandidate <- ifelse(d$party_factor == "Democrat", d$FT_pols_2,
ifelse(d$party_factor == "Republican", d$FT_pols_1, NA))
d$FT_CandDiff <- NA
d$FT_CandDiff <- d$FT_pols_1 - d$FT_pols_2
describeBy(d$FT_CandDiff, d$party_factor)
# connectedness
d$connectedness_6 <- as.numeric(d$connectedness_6)
d$connectedness <- rowMeans(d[,c("connectedness_1","connectedness_2","connectedness_3","connectedness_4","connectedness_5","connectedness_6","connectedness_7","connectedness_8")], na.rm = T)
psych::alpha(d[ , c("connectedness_1","connectedness_2","connectedness_3","connectedness_4","connectedness_5","connectedness_6","connectedness_7","connectedness_8")])
# demNorms
d$antidemNorms <- rowMeans(d[,c("demNorms_Reps_1", "demNorms_Reps_2", "demNorms_Reps_3", "demNorms_Reps_4", "demNorms_Dems_1", "demNorms_Dems_2", "demNorms_Dems_3", "demNorms_Dems_4")], na.rm = T)
psych::alpha(d[,c("demNorms_Reps_1", "demNorms_Reps_2", "demNorms_Reps_3", "demNorms_Reps_4")])
psych::alpha(d[,c("demNorms_Dems_1", "demNorms_Dems_2", "demNorms_Dems_3", "demNorms_Dems_4")])
d$demNorms <- (d$antidemNorms*-1)
psych::describe(d$demNorms)
psych::describe(d$antidemNorms)
# anti-Asian animus
d$AAA <- rowMeans(d[c("AAA_1", "AAA_2", "AAA_3")], na.rm = T)
psych::alpha(d[,c("demNorms_Dems_1", "demNorms_Dems_2", "demNorms_Dems_3", "demNorms_Dems_4")])
# gov't trust
cor.test(d$trustGovt1, d$trustGovt2) # yeah
d$trustGovt <- rowMeans(d[c("trustGovt1", "trustGovt2")], na.rm = T)
# science trust
d$trustSci <- rowMeans(d[c("trustSci_1", "trustSci_2","trustSci_3","trustSci_4")], na.rm = T)
psych::alpha(d[c("trustSci_1", "trustSci_2","trustSci_3","trustSci_4")])
# Vote Choice
table(d$voteChoice_final, d$wave)
d$voteID <- NA
d$voteID[d$voteChoice_final == 1] <- "Trump"
d$voteID[d$voteChoice_final == 2] <- "Harris"
d$voteID[d$VoteChoice == 1] <- "Trump"
d$voteID[d$VoteChoice == 2] <- "Harris"
d$voteID[d$VoteLean == 1] <- "Trump"
d$voteID[d$VoteLean == 2] <- "Harris"
d$voteID[d$VoteLean == 3] <- "Other"
d$voteID[d$voteChoice_final == 4] <- "Did Not Vote"
d$voteID[d$voteChoice_final == 3] <- "Other" # Hmmm
table(d$voteID, exclude = F)
# counter-proj
## ID
d$proj_ID <- NA
d$proj_ID[d$voteID == "Harris"] <- "Left"
d$proj_ID[d$voteID == "Trump"] <- "Right"
d$proj_ID[d$voteID == "Other" & d$party_factor == "Democrat"] <- "Left"
d$proj_ID[d$voteID == "Other" & d$party_factor == "Republican"] <- "Right"
## affective polarization
d$affPol_proj_Harris <- d$FT_proj_Harris_2 - d$FT_proj_Harris_1
d$affPol_proj_Trump <- d$FT_proj_Trump_1 - d$FT_proj_Trump_2
d$affPol_proj_Dem <- d$FT_proj_Dem_2 - d$FT_proj_Dem_1
d$affPol_proj_Rep <- d$FT_proj_Rep_1 - d$FT_proj_Rep_2
## dem norms
d$demNorms_proj_harris <- rowMeans(d[,c("demNorms_proj_harris_1", "demNorms_proj_harris_2", "demNorms_proj_harris_3", "demNorms_proj_harris_4")], na.rm = T)
d$demNorms_proj_Trump <- rowMeans(d[,c("demNorms_proj_Trump_1", "demNorms_proj_Trump_2", "demNorms_proj_Trump_3", "demNorms_proj_Trump_4")], na.rm = T)
d$demNorms_proj_Dem <- rowMeans(d[,c("demNorms_proj_Dem_1", "demNorms_proj_Dem_2", "demNorms_proj_Dem_3", "demNorms_proj_Dem_4")], na.rm = T)
d$demNorms_proj_Rep <- rowMeans(d[,c("demNorms_proj_Rep_1", "demNorms_proj_Rep_2", "demNorms_proj_Rep_3", "demNorms_proj_Rep_4")], na.rm = T)
# Affective Polarization
#d$affPol_proj <- ifelse(d$voteID == "Harris", d$affPol_proj_Harris,
# ifelse(d$voteID == "Trump", d$affPol_proj_Trump,
# ifelse(d$voteID == "Other" & d$party_factor == "Democrat", #d$affPol_proj_Dem,
# ifelse(d$voteID == "Other" & d$party_factor == "Republican", #d$affPol_proj_Rep, NA))))
d$affPol_proj <- rowMeans(d[,c("affPol_proj_Harris","affPol_proj_Trump","affPol_proj_Dem","affPol_proj_Rep")], na.rm = T)
describeBy(d$affPol_proj, list(d$proj_ID, d$wave))
## Negative Polarization
d$negPol_proj <- ifelse(d$voteID == "Harris", d$FT_proj_Harris_1,
ifelse(d$voteID == "Trump", d$FT_proj_Trump_2,
ifelse(d$voteID == "Other" & d$party_factor == "Democrat", d$FT_proj_Dem_1,
ifelse(d$voteID == "Other" & d$party_factor == "Republican", d$FT_proj_Rep_2, NA))))
## Democratic Norms
d$demNorms_proj <- ifelse(d$voteID == "Harris", d$demNorms_proj_harris,
ifelse(d$voteID == "Trump", d$demNorms_proj_Trump,
ifelse(d$voteID == "Other" & d$party_factor == "Democrat", d$demNorms_proj_Dem,
ifelse(d$voteID == "Other" & d$party_factor == "Republican", d$demNorms_proj_Rep, NA))))
# climate attitudes
d$climBel_proj <- ifelse(d$voteID == "Harris", d$climBel_proj_Harris,
ifelse(d$voteID == "Trump", d$climbel_proj_Trump,
ifelse(d$voteID == "Other" & d$party_factor == "Democrat", d$climBel_proj_Dem,
ifelse(d$voteID == "Other" & d$party_factor == "Republican", d$climBel_proj_Rep, NA))))
# ID centrality variables
## ID formation 1
d$IDform_1 <- rowMeans(d[, c("IDform_Dem_1", "IDform_Rep_1", "IDform_ind_1", "IDform_lib_1", "IDform_leftist_1", "IDform_prog_1", "IDform_con_1", "IDform_right_1", "IDform_mod_1", "IDform_socialist_1", "IDform_natlist_1", "IDform_libertarian_1", "IDform_feminist_1", "IDform_prolife_1", "IDform_prochoice_1", "IDform_MAGA_1", "IDform_enviro_1", "IDform_antiTrump_1", "IDform_pop_1", "IDform_other_1")], na.rm = T)
## ID formation 2
d$IDform_2 <- rowMeans(d[, c("IDform_Dem_2", "IDform_Rep_2", "IDform_ind_2", "IDform_lib_2", "IDform_leftist_2", "IDform_prog_2", "IDform_con_2", "IDform_right_2", "IDform_mod_2", "IDform_socialist_2", "IDform_natlist_2", "IDform_libertarian_2", "IDform_feminist_2", "IDform_prolife_2", "IDform_prochoice_2", "IDform_MAGA_2", "IDform_enviro_2", "IDform_antiTrump_2", "IDform_pop_2", "IDform_other_2")], na.rm = T)
## ID formation 3
d$IDform_3 <- rowMeans(d[, c("IDform_Dem_3", "IDform_Rep_3", "IDform_ind_3", "IDform_lib_3", "IDform_leftist_3", "IDform_prog_3", "IDform_con_3", "IDform_right_3", "IDform_mod_3", "IDform_socialist_3", "IDform_natlist_3", "IDform_libertarian_3", "IDform_feminist_3", "IDform_prolife_3", "IDform_prochoice_3", "IDform_MAGA_3", "IDform_enviro_3", "IDform_antiTrump_3", "IDform_pop_3", "IDform_other_3")], na.rm = T)
## ID formation 4
d$IDform_4 <- rowMeans(d[, c("IDform_Dem_4", "IDform_Rep_4", "IDform_ind_4", "IDform_lib_4", "IDform_leftist_4", "IDform_prog_4", "IDform_con_4", "IDform_right_4", "IDform_mod_4", "IDform_socialist_4", "IDform_natlist_4", "IDform_libertarian_4", "IDform_feminist_4", "IDform_prolife_4", "IDform_prochoice_4", "IDform_MAGA_4", "IDform_enviro_4", "IDform_antiTrump_4", "IDform_pop_4", "IDform_other_4")], na.rm = T)
## ID formation 5
d$IDform_5 <- rowMeans(d[, c("IDform_Dem_5", "IDform_Rep_5", "IDform_ind_5", "IDform_lib_5", "IDform_leftist_5", "IDform_prog_5", "IDform_con_5", "IDform_right_5", "IDform_mod_5", "IDform_socialist_5", "IDform_natlist_5", "IDform_libertarian_5", "IDform_feminist_5", "IDform_prolife_5", "IDform_prochoice_5", "IDform_MAGA_5", "IDform_enviro_5", "IDform_antiTrump_5", "IDform_pop_5", "IDform_other_5")], na.rm = T)
## ID formation 6
d$IDform_6 <- rowMeans(d[, c("IDform_Dem_6", "IDform_Rep_6", "IDform_ind_6", "IDform_lib_6", "IDform_leftist_6", "IDform_prog_6", "IDform_con_6", "IDform_right_6", "IDform_mod_6", "IDform_socialist_6", "IDform_natlist_6", "IDform_libertarian_6", "IDform_feminist_6", "IDform_prolife_6", "IDform_prochoice_6", "IDform_MAGA_6", "IDform_enviro_6", "IDform_antiTrump_6", "IDform_pop_6", "IDform_other_6")], na.rm = T)
## composite identity centrality
d$IDform <- rowMeans(d[,c("IDform_1", "IDform_2", "IDform_3", "IDform_4", "IDform_5", "IDform_6")], na.rm = T)
psych::alpha(d[,c("IDform_1", "IDform_2", "IDform_3", "IDform_4", "IDform_5", "IDform_6")])
# Identity Variables
d$numID_selected <- NA
d$numID_selected <- rowSums(d[,c("polID_Liberal_select", "polID_Leftist_select", "polID_Progressive_select", "polID_Conservative_select", "polID_RightWing_select", "polID_Moderate_select", "polID_Socialist_select", "polID_Nationalist_select", "polID_Libertarian_select", "polID_Feminist_select", "polID_Prolife_select", "polID_Prochoice_select", "polID_MAGA_select", "polID_AntiTrump_select", "polID_Environmentalist_select", "polID_Populist_select", "polID_Other_select")],na.rm = T)
table(d$numID_selected, d$wave)
## Calculate & join ID sds for each participant
ID_sds <- d %>%
dplyr::group_by(pid) %>%
dplyr::summarize(sdID_selected = sd(numID_selected, na.rm = TRUE))
d <- d %>%
left_join(ID_sds, by = "pid")Analyses
Analytic codes
### partisan identity vars
# Contrast Codes
## dems vs. reps
d$pDem_Rep <- NA
d$pDem_Rep[d$party_factor == "Democrat"] <- -1/2
d$pDem_Rep[d$party_factor == "Independent"] <- 0
d$pDem_Rep[d$party_factor == "Republican"] <- 1/2
## partisans vs. inds
d$pParty_Ind <- NA
d$pParty_Ind[d$party_factor == "Democrat"] <- -1/3
d$pParty_Ind[d$party_factor == "Independent"] <- 2/3
d$pParty_Ind[d$party_factor == "Republican"] <- -1/3
# Dummy Codes
## Democrats
### dems vs. R
d$pDem_R <- NA
d$pDem_R[d$party_factor == "Democrat"] <- 0
d$pDem_R[d$party_factor == "Independent"] <- 0
d$pDem_R[d$party_factor == "Republican"] <- 1
### dems vs. I
d$pDem_I <- NA
d$pDem_I[d$party_factor == "Democrat"] <- 0
d$pDem_I[d$party_factor == "Independent"] <- 1
d$pDem_I[d$party_factor == "Republican"] <- 0
## Republicans
### reps vs. D
d$pRep_D <- NA
d$pRep_D[d$party_factor == "Democrat"] <- 1
d$pRep_D[d$party_factor == "Independent"] <- 0
d$pRep_D[d$party_factor == "Republican"] <- 0
### reps vs. I
d$pRep_I <- NA
d$pRep_I[d$party_factor == "Democrat"] <- 0
d$pRep_I[d$party_factor == "Independent"] <- 1
d$pRep_I[d$party_factor == "Republican"] <- 0
## Independents
### inds vs. D
d$pInd_D <- NA
d$pInd_D[d$party_factor == "Democrat"] <- 1
d$pInd_D[d$party_factor == "Independent"] <- 0
d$pInd_D[d$party_factor == "Republican"] <- 0
### inds vs. R
d$pInd_R <- NA
d$pInd_R[d$party_factor == "Democrat"] <- 0
d$pInd_R[d$party_factor == "Independent"] <- 0
d$pInd_R[d$party_factor == "Republican"] <- 1
# party switch
d$party_switch.d <- ifelse(d$party_switch == "TRUE", 1, 0)
### political ID variables - Selected
d$Liberal <- ifelse(d$polID_Liberal_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Leftist <- ifelse(d$polID_Leftist_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Progressive <- ifelse(d$polID_Progressive_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Conservative <- ifelse(d$polID_Conservative_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$RightWing <- ifelse(d$polID_RightWing_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Moderate <- ifelse(d$polID_Moderate_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Socialist <- ifelse(d$polID_Socialist_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Nationalist <- ifelse(d$polID_Nationalist_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Libertarian <- ifelse(d$polID_Libertarian_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Feminist <- ifelse(d$polID_Feminist_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Prolife <- ifelse(d$polID_Prolife_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Prochoice <- ifelse(d$polID_Prochoice_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$MAGA <- ifelse(d$polID_MAGA_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$AntiTrump <- ifelse(d$polID_AntiTrump_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Populist <- ifelse(d$polID_Populist_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
d$Environmentalist <- ifelse(d$polID_Environmentalist_select == 1, 1, ifelse(d$polID_Other_select == 1, -1, 0))
### political ID variables - NOT Selected
d$nLiberal <- ifelse(d$polID_Liberal_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nLeftist <- ifelse(d$polID_Leftist_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nProgressive <- ifelse(d$polID_Progressive_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nConservative <- ifelse(d$polID_Conservative_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nRightWing <- ifelse(d$polID_RightWing_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nModerate <- ifelse(d$polID_Moderate_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nSocialist <- ifelse(d$polID_Socialist_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nNationalist <- ifelse(d$polID_Nationalist_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nLibertarian <- ifelse(d$polID_Libertarian_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nFeminist <- ifelse(d$polID_Feminist_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nProlife <- ifelse(d$polID_Prolife_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nProchoice <- ifelse(d$polID_Prochoice_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nMAGA <- ifelse(d$polID_MAGA_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nAntiTrump <- ifelse(d$polID_AntiTrump_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nPopulist <- ifelse(d$polID_Populist_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
d$nEnvironmentalist <- ifelse(d$polID_Environmentalist_not_select == 1, 1, ifelse(d$polID_Other_not_select == 1, -1, 0))
### wave
d$wave <- as.factor(d$wave)
# contrast codes
d$wave.lin <- NA
d$wave.lin[d$wave == 1] <- -1/2
d$wave.lin[d$wave == 2] <- -1/4
d$wave.lin[d$wave == 3] <- 1/4
d$wave.lin[d$wave == 4] <- 1/2
d$wave.quad <- NA
d$wave.quad[d$wave == 1] <- -1/4
d$wave.quad[d$wave == 2] <- 1/4
d$wave.quad[d$wave == 3] <- 1/4
d$wave.quad[d$wave == 4] <- -1/4
d$wave.cub <- NA
d$wave.cub[d$wave == 1] <- 1/4
d$wave.cub[d$wave == 2] <- -1/2
d$wave.cub[d$wave == 3] <- 1/2
d$wave.cub[d$wave == 4] <- -1/4
# dummy codes
## wave 1
d$wave1_2 <- NA
d$wave1_2[d$wave == 1] <- 0
d$wave1_2[d$wave == 2] <- 1
d$wave1_2[d$wave == 3] <- 0
d$wave1_2[d$wave == 4] <- 0
d$wave1_3 <- NA
d$wave1_3[d$wave == 1] <- 0
d$wave1_3[d$wave == 2] <- 0
d$wave1_3[d$wave == 3] <- 1
d$wave1_3[d$wave == 4] <- 0
d$wave1_4 <- NA
d$wave1_4[d$wave == 1] <- 0
d$wave1_4[d$wave == 2] <- 0
d$wave1_4[d$wave == 3] <- 0
d$wave1_4[d$wave == 4] <- 1
## wave 4
d$wave4_1 <- NA
d$wave4_1[d$wave == 1] <- 1
d$wave4_1[d$wave == 2] <- 0
d$wave4_1[d$wave == 3] <- 0
d$wave4_1[d$wave == 4] <- 0
d$wave4_2 <- NA
d$wave4_2[d$wave == 1] <- 0
d$wave4_2[d$wave == 2] <- 1
d$wave4_2[d$wave == 3] <- 0
d$wave4_2[d$wave == 4] <- 0
d$wave4_3 <- NA
d$wave4_3[d$wave == 1] <- 0
d$wave4_3[d$wave == 2] <- 0
d$wave4_3[d$wave == 3] <- 1
d$wave4_3[d$wave == 4] <- 0DV: Perceived Election Legitimacy (PEL)
Perceived election legitimacy was measured with two questions:
How confident are you that your own vote was counted as you intended? (
voteconf_self)How confident are you that votes nationwide were counted as voters intended? (
voteconf_natl)
These are highly correlated, but there are still interesting differences in patterns of own vs. national vote confidence.
##
## Pearson's product-moment correlation
##
## data: d$voteconf_natl and d$voteconf_self
## t = 113.95, df = 7522, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.7872919 0.8038743
## sample estimates:
## cor
## 0.7957322ggplot(d, aes(x=voteconfidence)) +
geom_density(fill="#69b3a2", color="#e9ecef", alpha=0.9) +
theme_bw() +
labs(x = "Perceived Election Legitimacy")
wave_label <- c(`1` = "Wave 1", `2` = "Wave 2", `3` = "Wave 3", `4` = "Wave 4")
ggplot(d[!is.na(d$party_factor),], aes(x=voteconfidence, fill = party_factor)) +
geom_density(color="black", alpha=0.5, position = 'identity') +
theme_bw() +
facet_grid(wave~., labeller = as_labeller(wave_label)) +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
labs(x = "Perceived Election Legitimacy")
ggplot(d[!is.na(d$party_factor),],
aes(x = party_factor,
y = voteconfidence,
fill = party_factor,
color = party_factor)) +
geom_jitter(height = .3, width =.3, alpha=0.4, size = .5, show.legend = F ) +
stat_summary(geom = "errorbar", color = "black", width = .1, show.legend = F) +
stat_summary( geom = "point", fun = "mean", color = "black", size = 1 , show.legend = F) +
theme_bw() +
scale_fill_manual(values = c("#1696d2","grey","#db2b27")) +
scale_color_manual(values = c("#1696d2","grey","#db2b27")) +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy")
(creating long dataset)
1. PEL over time
ggplot(d.EL[!is.na(d.EL$party_factor),],
aes(x = wave,
y = voteconf,
color = Vote_Type,
group = Vote_Type)) +
stat_summary(geom = "path", fun = "mean", color = "black", linetype = "dashed") +
stat_summary(geom = "errorbar", color = "black", width = .1) +
stat_summary(geom = "point", fun = "mean") +
facet_wrap(~party_factor) +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy") +
scale_color_manual("Vote Type",
values = c("#00C9A8","#FF0000"),
labels = c("Own Vote", "National Votes")) +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1)) +
theme_bw()
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = voteconfidence,
color = wave,
group = 1)) +
stat_summary(geom = "path", fun = "mean", color = "black", linetype = "dashed", show.legend = F) +
stat_summary(geom = "errorbar", color = "black", width = .1, show.legend = F) +
stat_summary(geom = "point", fun = "mean", show.legend = F) +
facet_wrap(~party_factor) +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy") +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1)) +
scale_x_discrete(labels = c("Wave 1","Wave 2", "Wave 3", "Wave 4")) +
theme(legend.position = "none") +
theme_bw()
Mean (and SD) for PEL by party over time
# Average PEL
kable(round(tapply(d$voteconfidence, list(d$party_factor, d$wave), FUN = mean, na.rm = T),2))| 1 | 2 | 3 | 4 | |
|---|---|---|---|---|
| Democrat | 3.87 | 3.60 | 3.58 | 3.39 |
| Independent | 2.72 | 3.05 | 3.15 | 2.95 |
| Republican | 2.67 | 3.68 | 3.62 | 3.65 |
## 1 2 3 4
## Democrat 1.06 1.20 1.14 1.22
## Independent 1.28 1.28 1.23 1.32
## Republican 1.16 1.02 0.96 1.02Summary
Across all parties, confidence in own votes was higher than votes nationally (b = 0.31, p < .001).
Democrats begin with higher PEL (M = 3.87) than Republicans (M = 2.67; b = 0.12, p = .002) and Independents (b = 0.49, p < .001). This falls linearly over time (b = -0.43, p < .001) until, in wave 4, Democrats express lower PEL (M = 3.39) than Republicans (M = 3.65; b = -0.37, p < .001), though Democrats’ PEL is still higher than Independents’ (M = 2.95; b = 0.27, p = .001).
Republicans’ PEL increases over time (b = 0.77, p < .001), though this increase takes place primarily from Wave 1 to Wave 2 (pre- and post-election), after which Republicans’ PEL remains stable.
Models
PEL.m1.l <- lmer(voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d.EL)
summary(PEL.m1.l)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin +
## wave.quad + wave.cub) + (1 | pid)
## Data: d.EL
##
## REML criterion at convergence: 42297
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.3491 -0.5333 0.0402 0.5749 3.9156
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7973 0.8929
## Residual 0.6134 0.7832
## Number of obs: 15628, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.371e+00 2.119e-02 3.422e+03 159.118
## pDem_Rep -7.742e-02 3.535e-02 4.864e+03 -2.190
## pParty_Ind -3.715e-01 4.225e-02 1.123e+04 -8.793
## vOwn_Natl -2.678e-01 1.702e-02 1.313e+04 -15.734
## wave.lin 1.778e-01 2.298e-02 1.366e+04 7.734
## wave.quad 5.026e-01 3.457e-02 1.331e+04 14.536
## wave.cub -1.306e-01 2.129e-02 1.318e+04 -6.131
## pDem_Rep:vOwn_Natl 4.873e-03 2.788e-02 1.300e+04 0.175
## pParty_Ind:vOwn_Natl 1.257e-01 4.495e-02 1.316e+04 2.797
## pDem_Rep:wave.lin 1.217e+00 3.864e-02 1.356e+04 31.507
## pDem_Rep:wave.quad 1.087e+00 5.741e-02 1.328e+04 18.927
## pDem_Rep:wave.cub -6.531e-01 3.471e-02 1.315e+04 -18.817
## pParty_Ind:wave.lin 1.313e-02 6.090e-02 1.377e+04 0.216
## pParty_Ind:wave.quad 6.759e-02 9.235e-02 1.342e+04 0.732
## pParty_Ind:wave.cub 3.673e-02 5.705e-02 1.326e+04 0.644
## vOwn_Natl:wave.lin -8.388e-02 4.303e-02 1.302e+04 -1.949
## vOwn_Natl:wave.quad -9.243e-02 6.696e-02 1.300e+04 -1.380
## vOwn_Natl:wave.cub 1.148e-01 4.176e-02 1.299e+04 2.750
## pDem_Rep:vOwn_Natl:wave.lin 2.265e-01 7.240e-02 1.297e+04 3.128
## pDem_Rep:vOwn_Natl:wave.quad 3.312e-01 1.110e-01 1.296e+04 2.983
## pDem_Rep:vOwn_Natl:wave.cub -1.507e-01 6.799e-02 1.296e+04 -2.216
## pParty_Ind:vOwn_Natl:wave.lin -1.179e-01 1.129e-01 1.303e+04 -1.045
## pParty_Ind:vOwn_Natl:wave.quad -8.335e-02 1.764e-01 1.302e+04 -0.472
## pParty_Ind:vOwn_Natl:wave.cub 1.685e-01 1.106e-01 1.301e+04 1.523
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep 0.02858 *
## pParty_Ind < 2e-16 ***
## vOwn_Natl < 2e-16 ***
## wave.lin 1.11e-14 ***
## wave.quad < 2e-16 ***
## wave.cub 8.96e-10 ***
## pDem_Rep:vOwn_Natl 0.86123
## pParty_Ind:vOwn_Natl 0.00517 **
## pDem_Rep:wave.lin < 2e-16 ***
## pDem_Rep:wave.quad < 2e-16 ***
## pDem_Rep:wave.cub < 2e-16 ***
## pParty_Ind:wave.lin 0.82925
## pParty_Ind:wave.quad 0.46425
## pParty_Ind:wave.cub 0.51968
## vOwn_Natl:wave.lin 0.05129 .
## vOwn_Natl:wave.quad 0.16748
## vOwn_Natl:wave.cub 0.00597 **
## pDem_Rep:vOwn_Natl:wave.lin 0.00176 **
## pDem_Rep:vOwn_Natl:wave.quad 0.00286 **
## pDem_Rep:vOwn_Natl:wave.cub 0.02673 *
## pParty_Ind:vOwn_Natl:wave.lin 0.29608
## pParty_Ind:vOwn_Natl:wave.quad 0.63665
## pParty_Ind:vOwn_Natl:wave.cub 0.12786
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m1 <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(PEL.m1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad +
## wave.cub) + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22252.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6388 -0.5025 0.0716 0.5367 3.8673
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5456 0.7387
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.346e+00 2.172e-02 3.333e+03 154.049 < 2e-16 ***
## pDem_Rep -1.187e-01 3.761e-02 3.946e+03 -3.157 0.00161 **
## pParty_Ind -4.260e-01 4.732e-02 6.837e+03 -9.004 < 2e-16 ***
## wave.lin 1.731e-01 2.854e-02 5.967e+03 6.063 1.42e-09 ***
## wave.quad 4.668e-01 4.281e-02 5.730e+03 10.903 < 2e-16 ***
## wave.cub -1.028e-01 2.625e-02 5.641e+03 -3.916 9.10e-05 ***
## pDem_Rep:wave.lin 1.203e+00 5.036e-02 5.908e+03 23.884 < 2e-16 ***
## pDem_Rep:wave.quad 1.096e+00 7.497e-02 5.708e+03 14.616 < 2e-16 ***
## pDem_Rep:wave.cub -6.436e-01 4.528e-02 5.622e+03 -14.212 < 2e-16 ***
## pParty_Ind:wave.lin 5.468e-03 7.448e-02 6.042e+03 0.073 0.94148
## pParty_Ind:wave.quad 1.798e-02 1.124e-01 5.817e+03 0.160 0.87297
## pParty_Ind:wave.cub 9.580e-02 6.918e-02 5.715e+03 1.385 0.16618
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav.ln wav.qd wav.cb pDm_Rp:wv.l
## pDem_Rep 0.067
## pParty_Ind 0.470 -0.038
## wave.lin 0.181 -0.012 0.121
## wave.quad -0.009 -0.009 0.029 -0.216
## wave.cub -0.058 0.010 -0.043 -0.072 0.173
## pDm_Rp:wv.l 0.009 0.164 0.006 0.061 -0.006 -0.008
## pDm_Rp:wv.q -0.008 -0.046 0.001 -0.008 0.058 0.009 -0.213
## pDm_Rp:wv.c -0.002 -0.053 -0.007 -0.008 0.008 0.057 -0.113
## pPrty_Ind:wv.l 0.098 -0.013 0.193 0.565 -0.124 -0.021 -0.037
## pPrty_Ind:wv.q 0.016 0.005 0.010 -0.121 0.574 0.102 0.005
## pPrty_Ind:wv.c -0.030 0.004 -0.064 -0.020 0.103 0.588 0.005
## pDm_Rp:wv.q pDm_Rp:wv.c pPrty_Ind:wv.l pPrty_Ind:wv.q
## pDem_Rep
## pParty_Ind
## wave.lin
## wave.quad
## wave.cub
## pDm_Rp:wv.l
## pDm_Rp:wv.q
## pDm_Rp:wv.c 0.166
## pPrty_Ind:wv.l 0.002 0.006
## pPrty_Ind:wv.q -0.036 -0.004 -0.213
## pPrty_Ind:wv.c -0.003 -0.031 -0.063 0.173Simple-Effects Models
PEL.m1.d <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(PEL.m1.d)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave.lin + wave.quad +
## wave.cub) + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22252.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6388 -0.5025 0.0716 0.5367 3.8673
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5456 0.7387
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.54761 0.02599 3278.96323 136.506 < 2e-16 ***
## pDem_R -0.11875 0.03761 3945.76029 -3.157 0.00161 **
## pDem_I -0.48540 0.05026 6458.38963 -9.659 < 2e-16 ***
## wave.lin -0.43016 0.03362 5912.25574 -12.796 < 2e-16 ***
## wave.quad -0.08711 0.05016 5711.50355 -1.737 0.08249 .
## wave.cub 0.18705 0.03034 5615.94669 6.165 7.55e-10 ***
## pDem_R:wave.lin 1.20278 0.05036 5907.77340 23.884 < 2e-16 ***
## pDem_R:wave.quad 1.09584 0.07498 5708.04469 14.616 < 2e-16 ***
## pDem_R:wave.cub -0.64358 0.04528 5621.54064 -14.212 < 2e-16 ***
## pDem_I:wave.lin 0.60686 0.07775 6030.66239 7.805 6.94e-15 ***
## pDem_I:wave.quad 0.56590 0.11726 5806.94293 4.826 1.43e-06 ***
## pDem_I:wave.cub -0.22599 0.07212 5710.32856 -3.134 0.00174 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wav.ln wav.qd wav.cb pDm_R:wv.l pDm_R:wv.q
## pDem_R -0.645
## pDem_I -0.417 0.339
## wave.lin 0.178 -0.123 -0.087
## wave.quad -0.038 0.023 0.024 -0.226
## wave.cub -0.064 0.045 0.033 -0.108 0.170
## pDm_R:wv.ln -0.115 0.164 0.067 -0.670 0.150 0.073
## pDm_R:wv.qd 0.026 -0.046 -0.016 0.151 -0.671 -0.114 -0.213
## pDm_R:wv.cb 0.041 -0.053 -0.027 0.074 -0.114 -0.673 -0.113 0.166
## pDm_I:wv.ln -0.061 0.040 0.191 -0.438 0.099 0.047 0.289 -0.067
## pDm_I:wv.qd 0.012 -0.010 0.006 0.097 -0.436 -0.075 -0.063 0.286
## pDm_I:wv.cb 0.024 -0.013 -0.065 0.048 -0.073 -0.430 -0.031 0.049
## pDm_R:wv.c pDm_I:wv.l pDm_I:wv.q
## pDem_R
## pDem_I
## wave.lin
## wave.quad
## wave.cub
## pDm_R:wv.ln
## pDm_R:wv.qd
## pDm_R:wv.cb
## pDm_I:wv.ln -0.031
## pDm_I:wv.qd 0.049 -0.216
## pDm_I:wv.cb 0.284 -0.066 0.174PEL.m1.d.w4 <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave4_1 + wave4_2 + wave4_3) + (1 | pid),
data = d)
summary(PEL.m1.d.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave4_1 + wave4_2 + wave4_3) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 22255
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6388 -0.5025 0.0716 0.5367 3.8673
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5456 0.7387
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.30754 0.03916 7794.37948 84.463 < 2e-16 ***
## pDem_R 0.36958 0.05732 8040.70971 6.448 1.20e-10 ***
## pDem_I -0.26695 0.08268 7653.03724 -3.229 0.00125 **
## wave4_1 0.52368 0.03835 5918.61903 13.656 < 2e-16 ***
## wave4_2 0.23230 0.03876 5725.41975 5.994 2.17e-09 ***
## wave4_3 0.20427 0.03935 5663.54152 5.191 2.16e-07 ***
## pDem_R:wave4_1 -1.52457 0.05751 5910.07827 -26.512 < 2e-16 ***
## pDem_R:wave4_2 -0.19327 0.05767 5736.33181 -3.351 0.00081 ***
## pDem_R:wave4_3 -0.23546 0.05864 5671.36641 -4.015 6.01e-05 ***
## pDem_I:wave4_1 -0.71985 0.08783 6027.56666 -8.196 3.00e-16 ***
## pDem_I:wave4_2 -0.11570 0.09018 5812.06667 -1.283 0.19956
## pDem_I:wave4_3 -0.03826 0.09205 5719.23173 -0.416 0.67770
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wav4_1 wav4_2 wav4_3 pD_R:4_1 pD_R:4_2
## pDem_R -0.662
## pDem_I -0.430 0.314
## wave4_1 -0.695 0.477 0.331
## wave4_2 -0.658 0.449 0.316 0.674
## wave4_3 -0.635 0.434 0.307 0.649 0.642
## pDm_R:wv4_1 0.462 -0.692 -0.223 -0.670 -0.450 -0.434
## pDm_R:wv4_2 0.442 -0.667 -0.213 -0.454 -0.673 -0.432 0.670
## pDm_R:wv4_3 0.426 -0.641 -0.206 -0.437 -0.432 -0.673 0.644 0.641
## pDm_I:wv4_1 0.297 -0.199 -0.743 -0.444 -0.299 -0.288 0.292 0.199
## pDm_I:wv4_2 0.278 -0.188 -0.687 -0.293 -0.436 -0.280 0.192 0.289
## pDm_I:wv4_3 0.271 -0.181 -0.661 -0.283 -0.279 -0.436 0.185 0.184
## pD_R:4_3 pD_I:4_1 pD_I:4_2
## pDem_R
## pDem_I
## wave4_1
## wave4_2
## wave4_3
## pDm_R:wv4_1
## pDm_R:wv4_2
## pDm_R:wv4_3
## pDm_I:wv4_1 0.192
## pDm_I:wv4_2 0.185 0.667
## pDm_I:wv4_3 0.288 0.635 0.618PEL.m1.r <- lmer(voteconfidence ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(PEL.m1.r)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pRep_D + pRep_I) * (wave.lin + wave.quad +
## wave.cub) + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22252.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6388 -0.5025 0.0716 0.5367 3.8673
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5456 0.7387
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.42886 0.02879 3357.66307 119.086 < 2e-16 ***
## pRep_D 0.11875 0.03761 3945.76029 3.157 0.00161 **
## pRep_I -0.36665 0.05157 6387.73603 -7.110 1.28e-12 ***
## wave.lin 0.77262 0.03739 5892.03242 20.664 < 2e-16 ***
## wave.quad 1.00873 0.05558 5690.58870 18.149 < 2e-16 ***
## wave.cub -0.45653 0.03350 5607.98516 -13.628 < 2e-16 ***
## pRep_D:wave.lin -1.20278 0.05036 5907.77340 -23.884 < 2e-16 ***
## pRep_D:wave.quad -1.09584 0.07498 5708.04469 -14.616 < 2e-16 ***
## pRep_D:wave.cub 0.64358 0.04528 5621.54064 14.212 < 2e-16 ***
## pRep_I:wave.lin -0.59592 0.07949 6026.20443 -7.497 7.49e-14 ***
## pRep_I:wave.quad -0.52994 0.11979 5804.83277 -4.424 9.86e-06 ***
## pRep_I:wave.cub 0.41759 0.07346 5701.86096 5.685 1.38e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pRep_D pRep_I wav.ln wav.qd wav.cb pRp_D:wv.l pRp_D:wv.q
## pRep_D -0.724
## pRep_I -0.464 0.399
## wave.lin 0.149 -0.110 -0.069
## wave.quad -0.054 0.042 0.030 -0.205
## wave.cub -0.042 0.030 0.016 -0.115 0.164
## pRp_D:wv.ln -0.111 0.164 0.055 -0.745 0.152 0.086
## pRp_D:wv.qd 0.037 -0.046 -0.018 0.152 -0.743 -0.122 -0.213
## pRp_D:wv.cb 0.032 -0.053 -0.012 0.086 -0.121 -0.742 -0.113 0.166
## pRp_I:wv.ln -0.073 0.065 0.188 -0.477 0.095 0.056 0.351 -0.070
## pRp_I:wv.qd 0.021 -0.019 0.001 0.097 -0.473 -0.078 -0.072 0.346
## pRp_I:wv.cb 0.024 -0.020 -0.060 0.055 -0.075 -0.463 -0.040 0.054
## pRp_D:wv.c pRp_I:wv.l pRp_I:wv.q
## pRep_D
## pRep_I
## wave.lin
## wave.quad
## wave.cub
## pRp_D:wv.ln
## pRp_D:wv.qd
## pRp_D:wv.cb
## pRp_I:wv.ln -0.041
## pRp_I:wv.qd 0.056 -0.211
## pRp_I:wv.cb 0.338 -0.069 0.171PEL.m1.i <- lmer(voteconfidence ~ (pInd_R + pInd_D) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(PEL.m1.i)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pInd_R + pInd_D) * (wave.lin + wave.quad +
## wave.cub) + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22252.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6388 -0.5025 0.0716 0.5367 3.8673
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5456 0.7387
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.06220 0.04594 5982.29753 66.651 < 2e-16 ***
## pInd_R 0.36665 0.05157 6387.73603 7.110 1.28e-12 ***
## pInd_D 0.48540 0.05026 6458.38963 9.659 < 2e-16 ***
## wave.lin 0.17670 0.06988 6042.54678 2.529 0.01147 *
## wave.quad 0.47879 0.10552 5805.06195 4.538 5.80e-06 ***
## wave.cub -0.03894 0.06512 5706.40012 -0.598 0.54991
## pInd_R:wave.lin 0.59592 0.07949 6026.20443 7.497 7.49e-14 ***
## pInd_R:wave.quad 0.52994 0.11979 5804.83277 4.424 9.86e-06 ***
## pInd_R:wave.cub -0.41759 0.07346 5701.86095 -5.685 1.38e-08 ***
## pInd_D:wave.lin -0.60686 0.07775 6030.66239 -7.805 6.94e-15 ***
## pInd_D:wave.quad -0.56590 0.11726 5806.94293 -4.826 1.43e-06 ***
## pInd_D:wave.cub 0.22599 0.07212 5710.32856 3.134 0.00174 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pInd_R pInd_D wav.ln wav.qd wav.cb pInd_R:wv.l pInd_R:wv.q
## pInd_R -0.832
## pInd_D -0.858 0.727
## wave.lin 0.196 -0.176 -0.170
## wave.quad 0.017 -0.017 -0.018 -0.214
## wave.cub -0.064 0.060 0.057 -0.055 0.174
## pInd_R:wv.l -0.165 0.188 0.144 -0.882 0.189 0.050
## pInd_R:wv.q -0.014 0.001 0.016 0.188 -0.886 -0.153 -0.211
## pInd_R:wv.c 0.053 -0.060 -0.047 0.050 -0.155 -0.890 -0.069 0.171
## pInd_D:wv.l -0.174 0.157 0.191 -0.902 0.193 0.051 0.795 -0.169
## pInd_D:wv.q -0.013 0.013 0.006 0.193 -0.904 -0.158 -0.171 0.800
## pInd_D:wv.c 0.057 -0.054 -0.065 0.050 -0.158 -0.907 -0.045 0.139
## pInd_R:wv.c pInd_D:wv.l pInd_D:wv.q
## pInd_R
## pInd_D
## wave.lin
## wave.quad
## wave.cub
## pInd_R:wv.l
## pInd_R:wv.q
## pInd_R:wv.c
## pInd_D:wv.l -0.045
## pInd_D:wv.q 0.140 -0.216
## pInd_D:wv.c 0.807 -0.066 0.1742. Moderator: Gov’t trust
ggplot(d) +
geom_smooth(aes(x = trustGovt,
y = voteconfidence),
color = "#69b3a2",
method = "lm") +
facet_wrap(~wave, labeller = as_labeller(wave_label)) +
labs(x = "Trust in Government",
y = "Perceived Election Legitimacy") +
theme_bw() +
coord_cartesian(ylim = c(1,5))
ggplot(d[!is.na(d$party_factor),]) +
geom_smooth(aes(x = trustGovt,
y = voteconfidence,
fill = party_factor,
color = party_factor),
method = "lm") +
facet_wrap(~wave, labeller = as_labeller(wave_label)) +
labs(x = "Trust in Government",
y = "Perceived Election Legitimacy") +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
scale_color_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
theme_bw() +
coord_cartesian(ylim = c(1,5))
ggplot(d.EL[!is.na(d.EL$party_factor) & !is.na(d.EL$trustGovt_bins),],
aes(x = wave,
y = voteconf,
color = Vote_Type,
group = Vote_Type)) +
stat_summary(geom = "path", fun = "mean", color = "black", linetype = "dashed") +
stat_summary(geom = "errorbar", color = "black", width = .1) +
stat_summary(geom = "point", fun = "mean") +
facet_grid(trustGovt_bins~party_factor) +
geom_text(data = na.omit(n_bins_govtrust), aes(label = paste0("n = ", n)),
x = 1.3, y = 1.2,
size = 3,
inherit.aes = FALSE,
color = "black") +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy") +
scale_color_manual("Vote Type",
values = c("#00C9A8","#FF0000"),
labels = c("Own Vote", "National Votes")) +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1)) +
theme_bw()
#ggplot(d.EL[!is.na(d.EL$party_factor) & !is.na(d.EL$trustGovt_terciles),],
# aes(x = wave,
# y = voteconf,
# color = Vote_Type,
# group = Vote_Type)) +
# stat_summary(geom = "path", fun = "mean", color = "black", linetype = "dashed") +
# stat_summary(geom = "errorbar", color = "black", width = .1) +
# stat_summary(geom = "point", fun = "mean") +
# facet_grid(trustGovt_terciles~party_factor) +
# geom_text(data = na.omit(n_terc_govtrust), aes(label = paste0("n = ", n)),
# x = 1.4, y = 1.2,
# size = 3,
# inherit.aes = FALSE) +
# labs(x = "Participant Party ID",
# y = "Perceived Election Legitimacy") +
# scale_color_manual("Vote Type",
# values = c("#00C9A8","#FF0000"),
# labels = c("Own Vote", "National Votes")) +
# coord_cartesian(ylim = c(1,5)) +
# scale_y_continuous(breaks = seq(1,5,1)) +
# theme_bw()Summary
Again, some differences by vote type (visible in graph above)—most notable differences occur for those high in governmental trust.
Overall, relationship between gov’t trust and PEL is positive (b = 0.26, p < .001). The strength of this trend slightly flattens over time (b = -0.08, p = .009), though it is still significant and positive in wave 4 (b = 0.25, p < .001). (Wave 1 effect: b = 0.39, p < .001.)
The trust-PEL relationship is stronger for Republicans (b = 0.53, p < .001) than for Democrats (b = 0.24, p < .001) in wave 1 (comparison: b = 0.30, p < .001); by wave 4, this relationship has flipped, such that the trust-PEL slope is steeper for Democrats (b = 0.29, p < .001) than for Republicans (b = 0.15, p < .001), though the overall gov’t trust-PEL relationship is smaller in magnitude relative to Wave 1; b = -0.14, p < .001.
Models
PEL.m2.l <- lmer(voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin + wave.quad + wave.cub) * trustGovt + (1 | pid),
data = d.EL)
summary(PEL.m2.l)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin +
## wave.quad + wave.cub) * trustGovt + (1 | pid)
## Data: d.EL
##
## REML criterion at convergence: 41043.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5197 -0.5332 0.0420 0.5788 3.8958
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6888 0.8299
## Residual 0.5911 0.7688
## Number of obs: 15428, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.530e+00 2.292e-02 5.029e+03
## pDem_Rep -4.178e-02 3.606e-02 5.727e+03
## pParty_Ind -2.904e-01 5.116e-02 1.305e+04
## vOwn_Natl -2.004e-01 2.391e-02 1.294e+04
## wave.lin 2.552e-01 3.480e-02 1.399e+04
## wave.quad 2.260e-01 4.985e-02 1.331e+04
## wave.cub -6.028e-02 2.974e-02 1.317e+04
## trustGovt 2.333e-01 1.295e-02 1.496e+04
## pDem_Rep:vOwn_Natl 4.222e-03 3.384e-02 1.277e+04
## pParty_Ind:vOwn_Natl 1.001e-01 6.542e-02 1.296e+04
## pDem_Rep:wave.lin 5.901e-01 5.056e-02 1.421e+04
## pDem_Rep:wave.quad 9.950e-01 7.098e-02 1.323e+04
## pDem_Rep:wave.cub -4.658e-01 4.201e-02 1.307e+04
## pParty_Ind:wave.lin 1.921e-01 9.514e-02 1.397e+04
## pParty_Ind:wave.quad -7.139e-02 1.375e-01 1.338e+04
## pParty_Ind:wave.cub 3.115e-02 8.207e-02 1.324e+04
## vOwn_Natl:wave.lin -3.702e-02 6.227e-02 1.284e+04
## vOwn_Natl:wave.quad -2.032e-02 9.415e-02 1.280e+04
## vOwn_Natl:wave.cub 1.970e-01 5.711e-02 1.281e+04
## pDem_Rep:trustGovt 9.552e-03 2.099e-02 1.490e+04
## pParty_Ind:trustGovt 4.631e-02 3.266e-02 1.535e+04
## vOwn_Natl:trustGovt 8.163e-02 1.744e-02 1.288e+04
## wave.lin:trustGovt -6.373e-02 2.590e-02 1.452e+04
## wave.quad:trustGovt -2.882e-01 3.676e-02 1.333e+04
## wave.cub:trustGovt 9.490e-02 2.271e-02 1.321e+04
## pDem_Rep:vOwn_Natl:wave.lin -6.553e-03 8.934e-02 1.274e+04
## pDem_Rep:vOwn_Natl:wave.quad 5.189e-01 1.349e-01 1.273e+04
## pDem_Rep:vOwn_Natl:wave.cub -5.072e-02 8.109e-02 1.273e+04
## pParty_Ind:vOwn_Natl:wave.lin -2.518e-01 1.700e-01 1.286e+04
## pParty_Ind:vOwn_Natl:wave.quad 3.047e-01 2.572e-01 1.281e+04
## pParty_Ind:vOwn_Natl:wave.cub 3.720e-01 1.563e-01 1.283e+04
## pDem_Rep:vOwn_Natl:trustGovt 2.517e-02 2.677e-02 1.275e+04
## pParty_Ind:vOwn_Natl:trustGovt -3.037e-02 4.689e-02 1.291e+04
## pDem_Rep:wave.lin:trustGovt -3.437e-01 4.057e-02 1.438e+04
## pDem_Rep:wave.quad:trustGovt -2.666e-01 5.691e-02 1.330e+04
## pDem_Rep:wave.cub:trustGovt 2.087e-01 3.465e-02 1.317e+04
## pParty_Ind:wave.lin:trustGovt 1.433e-01 6.927e-02 1.449e+04
## pParty_Ind:wave.quad:trustGovt -1.638e-01 9.946e-02 1.340e+04
## pParty_Ind:wave.cub:trustGovt 3.230e-02 6.161e-02 1.327e+04
## vOwn_Natl:wave.lin:trustGovt 5.842e-02 4.433e-02 1.282e+04
## vOwn_Natl:wave.quad:trustGovt 7.838e-02 6.899e-02 1.278e+04
## vOwn_Natl:wave.cub:trustGovt 9.864e-02 4.325e-02 1.281e+04
## pDem_Rep:vOwn_Natl:wave.lin:trustGovt -2.054e-01 6.927e-02 1.273e+04
## pDem_Rep:vOwn_Natl:wave.quad:trustGovt 1.159e-01 1.068e-01 1.273e+04
## pDem_Rep:vOwn_Natl:wave.cub:trustGovt 7.212e-02 6.581e-02 1.273e+04
## pParty_Ind:vOwn_Natl:wave.lin:trustGovt -1.483e-01 1.187e-01 1.284e+04
## pParty_Ind:vOwn_Natl:wave.quad:trustGovt 3.240e-01 1.851e-01 1.279e+04
## pParty_Ind:vOwn_Natl:wave.cub:trustGovt 1.470e-01 1.166e-01 1.283e+04
## t value Pr(>|t|)
## (Intercept) 154.046 < 2e-16 ***
## pDem_Rep -1.159 0.246705
## pParty_Ind -5.676 1.41e-08 ***
## vOwn_Natl -8.383 < 2e-16 ***
## wave.lin 7.333 2.37e-13 ***
## wave.quad 4.535 5.82e-06 ***
## wave.cub -2.027 0.042658 *
## trustGovt 18.018 < 2e-16 ***
## pDem_Rep:vOwn_Natl 0.125 0.900724
## pParty_Ind:vOwn_Natl 1.530 0.126039
## pDem_Rep:wave.lin 11.672 < 2e-16 ***
## pDem_Rep:wave.quad 14.017 < 2e-16 ***
## pDem_Rep:wave.cub -11.086 < 2e-16 ***
## pParty_Ind:wave.lin 2.019 0.043491 *
## pParty_Ind:wave.quad -0.519 0.603666
## pParty_Ind:wave.cub 0.380 0.704260
## vOwn_Natl:wave.lin -0.594 0.552228
## vOwn_Natl:wave.quad -0.216 0.829079
## vOwn_Natl:wave.cub 3.449 0.000565 ***
## pDem_Rep:trustGovt 0.455 0.648969
## pParty_Ind:trustGovt 1.418 0.156251
## vOwn_Natl:trustGovt 4.680 2.89e-06 ***
## wave.lin:trustGovt -2.461 0.013872 *
## wave.quad:trustGovt -7.838 4.93e-15 ***
## wave.cub:trustGovt 4.179 2.95e-05 ***
## pDem_Rep:vOwn_Natl:wave.lin -0.073 0.941527
## pDem_Rep:vOwn_Natl:wave.quad 3.847 0.000120 ***
## pDem_Rep:vOwn_Natl:wave.cub -0.625 0.531696
## pParty_Ind:vOwn_Natl:wave.lin -1.481 0.138664
## pParty_Ind:vOwn_Natl:wave.quad 1.185 0.236233
## pParty_Ind:vOwn_Natl:wave.cub 2.380 0.017336 *
## pDem_Rep:vOwn_Natl:trustGovt 0.940 0.347068
## pParty_Ind:vOwn_Natl:trustGovt -0.648 0.517210
## pDem_Rep:wave.lin:trustGovt -8.471 < 2e-16 ***
## pDem_Rep:wave.quad:trustGovt -4.685 2.83e-06 ***
## pDem_Rep:wave.cub:trustGovt 6.023 1.75e-09 ***
## pParty_Ind:wave.lin:trustGovt 2.069 0.038541 *
## pParty_Ind:wave.quad:trustGovt -1.647 0.099624 .
## pParty_Ind:wave.cub:trustGovt 0.524 0.600098
## vOwn_Natl:wave.lin:trustGovt 1.318 0.187510
## vOwn_Natl:wave.quad:trustGovt 1.136 0.255900
## vOwn_Natl:wave.cub:trustGovt 2.281 0.022579 *
## pDem_Rep:vOwn_Natl:wave.lin:trustGovt -2.966 0.003026 **
## pDem_Rep:vOwn_Natl:wave.quad:trustGovt 1.085 0.278006
## pDem_Rep:vOwn_Natl:wave.cub:trustGovt 1.096 0.273120
## pParty_Ind:vOwn_Natl:wave.lin:trustGovt -1.249 0.211528
## pParty_Ind:vOwn_Natl:wave.quad:trustGovt 1.750 0.080148 .
## pParty_Ind:vOwn_Natl:wave.cub:trustGovt 1.261 0.207328
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2 <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad +
## wave.cub) * trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21443.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.386e+00 2.141e-02 3.707e+03 158.119
## pDem_Rep -6.729e-02 3.650e-02 4.100e+03 -1.844
## pParty_Ind -3.619e-01 4.842e-02 6.980e+03 -7.473
## wave.lin 2.849e-01 3.291e-02 6.218e+03 8.658
## wave.quad 3.719e-01 4.751e-02 5.708e+03 7.829
## wave.cub -6.512e-02 2.856e-02 5.630e+03 -2.280
## trustGovt.c 2.608e-01 1.519e-02 7.976e+03 17.177
## pDem_Rep:wave.lin 7.135e-01 5.610e-02 6.418e+03 12.718
## pDem_Rep:wave.quad 1.156e+00 7.982e-02 5.674e+03 14.477
## pDem_Rep:wave.cub -5.675e-01 4.769e-02 5.573e+03 -11.901
## pParty_Ind:wave.lin 7.548e-02 8.653e-02 6.184e+03 0.872
## pParty_Ind:wave.quad 5.392e-02 1.261e-01 5.791e+03 0.427
## pParty_Ind:wave.cub 1.173e-01 7.589e-02 5.707e+03 1.546
## pDem_Rep:trustGovt.c 9.052e-03 2.549e-02 7.973e+03 0.355
## pParty_Ind:trustGovt.c 3.921e-02 3.826e-02 7.864e+03 1.025
## wave.lin:trustGovt.c -8.169e-02 3.141e-02 6.620e+03 -2.601
## wave.quad:trustGovt.c -2.388e-01 4.473e-02 5.789e+03 -5.339
## wave.cub:trustGovt.c 1.193e-01 2.769e-02 5.741e+03 4.308
## pDem_Rep:wave.lin:trustGovt.c -3.265e-01 5.190e-02 6.500e+03 -6.291
## pDem_Rep:wave.quad:trustGovt.c -2.813e-01 7.383e-02 5.779e+03 -3.811
## pDem_Rep:wave.cub:trustGovt.c 2.136e-01 4.496e-02 5.695e+03 4.752
## pParty_Ind:wave.lin:trustGovt.c 1.030e-01 8.292e-02 6.626e+03 1.242
## pParty_Ind:wave.quad:trustGovt.c -1.890e-02 1.188e-01 5.837e+03 -0.159
## pParty_Ind:wave.cub:trustGovt.c 9.326e-02 7.389e-02 5.800e+03 1.262
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep 0.06532 .
## pParty_Ind 8.77e-14 ***
## wave.lin < 2e-16 ***
## wave.quad 5.82e-15 ***
## wave.cub 0.02262 *
## trustGovt.c < 2e-16 ***
## pDem_Rep:wave.lin < 2e-16 ***
## pDem_Rep:wave.quad < 2e-16 ***
## pDem_Rep:wave.cub < 2e-16 ***
## pParty_Ind:wave.lin 0.38305
## pParty_Ind:wave.quad 0.66908
## pParty_Ind:wave.cub 0.12221
## pDem_Rep:trustGovt.c 0.72255
## pParty_Ind:trustGovt.c 0.30557
## wave.lin:trustGovt.c 0.00933 **
## wave.quad:trustGovt.c 9.68e-08 ***
## wave.cub:trustGovt.c 1.67e-05 ***
## pDem_Rep:wave.lin:trustGovt.c 3.36e-10 ***
## pDem_Rep:wave.quad:trustGovt.c 0.00014 ***
## pDem_Rep:wave.cub:trustGovt.c 2.06e-06 ***
## pParty_Ind:wave.lin:trustGovt.c 0.21427
## pParty_Ind:wave.quad:trustGovt.c 0.87366
## pParty_Ind:wave.cub:trustGovt.c 0.20694
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Simple-effects models
PEL.m2.w4 <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave4_3 + wave4_2 + wave4_1) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave4_3 + wave4_2 +
## wave4_1) * trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21449.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.451e+00 3.643e-02 7.974e+03 94.744
## pDem_Rep 1.425e-01 5.906e-02 7.976e+03 2.412
## pParty_Ind -3.669e-01 9.240e-02 7.164e+03 -3.971
## wave4_3 6.590e-02 3.876e-02 5.689e+03 1.700
## wave4_2 -1.145e-02 3.802e-02 5.914e+03 -0.301
## wave4_1 -3.175e-01 3.726e-02 6.096e+03 -8.522
## trustGovt.c 2.499e-01 2.931e-02 6.369e+03 8.525
## pDem_Rep:wave4_3 -2.625e-02 6.137e-02 5.678e+03 -0.428
## pDem_Rep:wave4_2 1.845e-01 6.387e-02 6.048e+03 2.889
## pDem_Rep:wave4_1 -9.973e-01 6.349e-02 6.242e+03 -15.708
## pParty_Ind:wave4_3 9.607e-02 1.044e-01 5.746e+03 0.920
## pParty_Ind:wave4_2 -5.898e-02 1.005e-01 5.907e+03 -0.587
## pParty_Ind:wave4_1 -1.682e-02 9.822e-02 6.105e+03 -0.171
## pDem_Rep:trustGovt.c -1.373e-01 4.748e-02 6.324e+03 -2.891
## pParty_Ind:trustGovt.c 7.211e-02 7.741e-02 6.292e+03 0.932
## wave4_3:trustGovt.c -9.544e-03 3.628e-02 5.822e+03 -0.263
## wave4_2:trustGovt.c -8.797e-02 3.553e-02 6.225e+03 -2.476
## wave4_1:trustGovt.c 1.413e-01 3.449e-02 6.396e+03 4.097
## pDem_Rep:wave4_3:trustGovt.c 1.012e-01 5.820e-02 5.859e+03 1.739
## pDem_Rep:wave4_2:trustGovt.c 5.079e-02 5.822e-02 6.151e+03 0.872
## pDem_Rep:wave4_1:trustGovt.c 4.333e-01 5.782e-02 6.347e+03 7.494
## pParty_Ind:wave4_3:trustGovt.c 3.475e-02 9.683e-02 5.832e+03 0.359
## pParty_Ind:wave4_2:trustGovt.c -1.100e-01 9.406e-02 6.226e+03 -1.170
## pParty_Ind:wave4_1:trustGovt.c -5.636e-02 9.088e-02 6.401e+03 -0.620
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep 0.01588 *
## pParty_Ind 7.22e-05 ***
## wave4_3 0.08917 .
## wave4_2 0.76328
## wave4_1 < 2e-16 ***
## trustGovt.c < 2e-16 ***
## pDem_Rep:wave4_3 0.66880
## pDem_Rep:wave4_2 0.00388 **
## pDem_Rep:wave4_1 < 2e-16 ***
## pParty_Ind:wave4_3 0.35752
## pParty_Ind:wave4_2 0.55721
## pParty_Ind:wave4_1 0.86401
## pDem_Rep:trustGovt.c 0.00385 **
## pParty_Ind:trustGovt.c 0.35163
## wave4_3:trustGovt.c 0.79249
## wave4_2:trustGovt.c 0.01330 *
## wave4_1:trustGovt.c 4.23e-05 ***
## pDem_Rep:wave4_3:trustGovt.c 0.08215 .
## pDem_Rep:wave4_2:trustGovt.c 0.38304
## pDem_Rep:wave4_1:trustGovt.c 7.60e-14 ***
## pParty_Ind:wave4_3:trustGovt.c 0.71971
## pParty_Ind:wave4_2:trustGovt.c 0.24220
## pParty_Ind:wave4_1:trustGovt.c 0.53517
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.w1 <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave1_3 + wave1_2 + wave1_4) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.w1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave1_3 + wave1_2 +
## wave1_4) * trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21449.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.13390 0.02494 5868.47662 125.633
## pDem_Rep -0.85482 0.04679 6957.86829 -18.271
## pParty_Ind -0.38377 0.05744 7916.39550 -6.681
## wave1_3 0.38340 0.03046 6047.44429 12.589
## wave1_2 0.30605 0.02747 5743.88938 11.141
## wave1_4 0.31750 0.03726 6096.48620 8.522
## trustGovt.c 0.39122 0.02121 7889.86641 18.444
## pDem_Rep:wave1_3 0.97103 0.05191 6076.29221 18.704
## pDem_Rep:wave1_2 1.18182 0.05107 5680.51607 23.142
## pDem_Rep:wave1_4 0.99728 0.06349 6241.75871 15.708
## pParty_Ind:wave1_3 0.11290 0.08038 6090.44534 1.404
## pParty_Ind:wave1_2 -0.04216 0.07078 5884.29367 -0.596
## pParty_Ind:wave1_4 0.01682 0.09822 6104.71915 0.171
## pDem_Rep:trustGovt.c 0.29603 0.03812 7801.13655 7.766
## pParty_Ind:trustGovt.c 0.01575 0.05319 7715.46552 0.296
## wave1_3:trustGovt.c -0.15087 0.03059 6265.85995 -4.932
## wave1_2:trustGovt.c -0.22930 0.02605 5712.37243 -8.802
## wave1_4:trustGovt.c -0.14132 0.03449 6395.56604 -4.097
## pDem_Rep:wave1_3:trustGovt.c -0.33210 0.05010 6146.85558 -6.629
## pDem_Rep:wave1_2:trustGovt.c -0.38250 0.04535 5670.27930 -8.434
## pDem_Rep:wave1_4:trustGovt.c -0.43329 0.05782 6346.68932 -7.494
## pParty_Ind:wave1_3:trustGovt.c 0.09111 0.08136 6327.19459 1.120
## pParty_Ind:wave1_2:trustGovt.c -0.05365 0.06857 5823.92427 -0.782
## pParty_Ind:wave1_4:trustGovt.c 0.05636 0.09088 6401.46452 0.620
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep < 2e-16 ***
## pParty_Ind 2.54e-11 ***
## wave1_3 < 2e-16 ***
## wave1_2 < 2e-16 ***
## wave1_4 < 2e-16 ***
## trustGovt.c < 2e-16 ***
## pDem_Rep:wave1_3 < 2e-16 ***
## pDem_Rep:wave1_2 < 2e-16 ***
## pDem_Rep:wave1_4 < 2e-16 ***
## pParty_Ind:wave1_3 0.160
## pParty_Ind:wave1_2 0.551
## pParty_Ind:wave1_4 0.864
## pDem_Rep:trustGovt.c 9.16e-15 ***
## pParty_Ind:trustGovt.c 0.767
## wave1_3:trustGovt.c 8.34e-07 ***
## wave1_2:trustGovt.c < 2e-16 ***
## wave1_4:trustGovt.c 4.23e-05 ***
## pDem_Rep:wave1_3:trustGovt.c 3.68e-11 ***
## pDem_Rep:wave1_2:trustGovt.c < 2e-16 ***
## pDem_Rep:wave1_4:trustGovt.c 7.60e-14 ***
## pParty_Ind:wave1_3:trustGovt.c 0.263
## pParty_Ind:wave1_2:trustGovt.c 0.434
## pParty_Ind:wave1_4:trustGovt.c 0.535
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.d <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.d)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave.lin + wave.quad +
## wave.cub) * trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21443.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.540e+00 2.562e-02 3.682e+03 138.171 < 2e-16
## pDem_R -6.729e-02 3.650e-02 4.100e+03 -1.844 0.06532
## pDem_I -3.955e-01 5.139e-02 6.704e+03 -7.696 1.61e-14
## wave.lin -9.698e-02 4.101e-02 6.665e+03 -2.365 0.01808
## wave.quad -2.238e-01 5.654e-02 5.686e+03 -3.958 7.64e-05
## wave.cub 1.795e-01 3.337e-02 5.597e+03 5.381 7.71e-08
## trustGovt.c 2.433e-01 1.678e-02 7.965e+03 14.499 < 2e-16
## pDem_R:wave.lin 7.135e-01 5.610e-02 6.418e+03 12.718 < 2e-16
## pDem_R:wave.quad 1.156e+00 7.982e-02 5.674e+03 14.477 < 2e-16
## pDem_R:wave.cub -5.675e-01 4.769e-02 5.573e+03 -11.901 < 2e-16
## pDem_I:wave.lin 4.322e-01 9.154e-02 6.254e+03 4.722 2.39e-06
## pDem_I:wave.quad 6.317e-01 1.323e-01 5.779e+03 4.776 1.84e-06
## pDem_I:wave.cub -1.665e-01 7.943e-02 5.702e+03 -2.096 0.03616
## pDem_R:trustGovt.c 9.052e-03 2.549e-02 7.973e+03 0.355 0.72255
## pDem_I:trustGovt.c 4.373e-02 3.973e-02 7.860e+03 1.101 0.27111
## wave.lin:trustGovt.c 4.722e-02 3.529e-02 6.553e+03 1.338 0.18092
## wave.quad:trustGovt.c -9.188e-02 4.978e-02 5.779e+03 -1.846 0.06499
## wave.cub:trustGovt.c -1.863e-02 3.038e-02 5.723e+03 -0.613 0.53966
## pDem_R:wave.lin:trustGovt.c -3.265e-01 5.190e-02 6.500e+03 -6.291 3.36e-10
## pDem_R:wave.quad:trustGovt.c -2.813e-01 7.383e-02 5.779e+03 -3.811 0.00014
## pDem_R:wave.cub:trustGovt.c 2.136e-01 4.496e-02 5.695e+03 4.752 2.06e-06
## pDem_I:wave.lin:trustGovt.c -6.024e-02 8.631e-02 6.628e+03 -0.698 0.48523
## pDem_I:wave.quad:trustGovt.c -1.596e-01 1.234e-01 5.831e+03 -1.293 0.19620
## pDem_I:wave.cub:trustGovt.c 2.001e-01 7.675e-02 5.803e+03 2.607 0.00916
##
## (Intercept) ***
## pDem_R .
## pDem_I ***
## wave.lin *
## wave.quad ***
## wave.cub ***
## trustGovt.c ***
## pDem_R:wave.lin ***
## pDem_R:wave.quad ***
## pDem_R:wave.cub ***
## pDem_I:wave.lin ***
## pDem_I:wave.quad ***
## pDem_I:wave.cub *
## pDem_R:trustGovt.c
## pDem_I:trustGovt.c
## wave.lin:trustGovt.c
## wave.quad:trustGovt.c .
## wave.cub:trustGovt.c
## pDem_R:wave.lin:trustGovt.c ***
## pDem_R:wave.quad:trustGovt.c ***
## pDem_R:wave.cub:trustGovt.c ***
## pDem_I:wave.lin:trustGovt.c
## pDem_I:wave.quad:trustGovt.c
## pDem_I:wave.cub:trustGovt.c **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.d.w1 <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave1_3 + wave1_2 + wave1_4) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.d.w1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave1_3 + wave1_2 + wave1_4) *
## trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21449.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.68924 0.03280 6607.67744 112.462 < 2e-16
## pDem_R -0.85482 0.04679 6957.86967 -18.271 < 2e-16
## pDem_I -0.81118 0.06166 7864.41589 -13.155 < 2e-16
## wave1_3 -0.13975 0.03595 6314.29417 -3.887 0.000103
## wave1_2 -0.27081 0.03600 5687.51236 -7.522 6.24e-14
## wave1_4 -0.18675 0.04626 6393.85517 -4.037 5.48e-05
## trustGovt.c 0.23796 0.02460 7798.24032 9.672 < 2e-16
## pDem_R:wave1_3 0.97103 0.05191 6076.29180 18.704 < 2e-16
## pDem_R:wave1_2 1.18182 0.05107 5680.51567 23.142 < 2e-16
## pDem_R:wave1_4 0.99728 0.06349 6241.75836 15.708 < 2e-16
## pDem_I:wave1_3 0.59841 0.08413 6127.85043 7.113 1.27e-12
## pDem_I:wave1_2 0.54875 0.07526 5868.51842 7.292 3.47e-13
## pDem_I:wave1_4 0.51546 0.10385 6148.43355 4.964 7.11e-07
## pDem_R:trustGovt.c 0.29603 0.03812 7801.13638 7.766 9.16e-15
## pDem_I:trustGovt.c 0.16376 0.05543 7724.25557 2.954 0.003144
## wave1_3:trustGovt.c -0.01519 0.03353 6252.54772 -0.453 0.650569
## wave1_2:trustGovt.c -0.02016 0.02981 5682.38415 -0.676 0.498843
## wave1_4:trustGovt.c 0.05653 0.03912 6355.65202 1.445 0.148530
## pDem_R:wave1_3:trustGovt.c -0.33210 0.05010 6146.85524 -6.629 3.68e-11
## pDem_R:wave1_2:trustGovt.c -0.38250 0.04535 5670.27890 -8.434 < 2e-16
## pDem_R:wave1_4:trustGovt.c -0.43329 0.05782 6346.68901 -7.494 7.60e-14
## pDem_I:wave1_3:trustGovt.c -0.07494 0.08437 6334.08808 -0.888 0.374489
## pDem_I:wave1_2:trustGovt.c -0.24490 0.07125 5815.70952 -3.437 0.000592
## pDem_I:wave1_4:trustGovt.c -0.16028 0.09467 6402.97242 -1.693 0.090488
##
## (Intercept) ***
## pDem_R ***
## pDem_I ***
## wave1_3 ***
## wave1_2 ***
## wave1_4 ***
## trustGovt.c ***
## pDem_R:wave1_3 ***
## pDem_R:wave1_2 ***
## pDem_R:wave1_4 ***
## pDem_I:wave1_3 ***
## pDem_I:wave1_2 ***
## pDem_I:wave1_4 ***
## pDem_R:trustGovt.c ***
## pDem_I:trustGovt.c **
## wave1_3:trustGovt.c
## wave1_2:trustGovt.c
## wave1_4:trustGovt.c
## pDem_R:wave1_3:trustGovt.c ***
## pDem_R:wave1_2:trustGovt.c ***
## pDem_R:wave1_4:trustGovt.c ***
## pDem_I:wave1_3:trustGovt.c
## pDem_I:wave1_2:trustGovt.c ***
## pDem_I:wave1_4:trustGovt.c .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.d.w4 <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave4_3 + wave4_2 + wave4_1) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.d.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave4_3 + wave4_2 + wave4_1) *
## trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21449.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.50249 0.04291 7974.24842 81.628 < 2e-16
## pDem_R 0.14246 0.05906 7975.99051 2.412 0.01588
## pDem_I -0.29572 0.09739 7267.24940 -3.036 0.00240
## wave4_3 0.04700 0.04359 5688.09766 1.078 0.28097
## wave4_2 -0.08406 0.04693 6200.37945 -1.791 0.07331
## wave4_1 0.18675 0.04626 6393.85517 4.037 5.48e-05
## trustGovt.c 0.29449 0.03274 6284.94196 8.995 < 2e-16
## pDem_R:wave4_3 -0.02625 0.06137 5678.01785 -0.428 0.66880
## pDem_R:wave4_2 0.18454 0.06387 6048.40919 2.889 0.00388
## pDem_R:wave4_1 -0.99728 0.06349 6241.75836 -15.708 < 2e-16
## pDem_I:wave4_3 0.08295 0.10886 5739.68550 0.762 0.44611
## pDem_I:wave4_2 0.03329 0.10614 5943.99575 0.314 0.75384
## pDem_I:wave4_1 -0.51546 0.10385 6148.43354 -4.964 7.11e-07
## pDem_R:trustGovt.c -0.13726 0.04748 6324.44477 -2.891 0.00385
## pDem_I:trustGovt.c 0.00348 0.08061 6282.97484 0.043 0.96556
## wave4_3:trustGovt.c -0.07172 0.03982 5838.83317 -1.801 0.07172
## wave4_2:trustGovt.c -0.07669 0.03987 6161.48313 -1.923 0.05447
## wave4_1:trustGovt.c -0.05653 0.03913 6355.65203 -1.445 0.14853
## pDem_R:wave4_3:trustGovt.c 0.10119 0.05820 5859.39291 1.739 0.08215
## pDem_R:wave4_2:trustGovt.c 0.05079 0.05822 6150.51872 0.872 0.38304
## pDem_R:wave4_1:trustGovt.c 0.43329 0.05782 6346.68901 7.494 7.60e-14
## pDem_I:wave4_3:trustGovt.c 0.08534 0.10064 5834.02489 0.848 0.39649
## pDem_I:wave4_2:trustGovt.c -0.08462 0.09791 6222.48987 -0.864 0.38748
## pDem_I:wave4_1:trustGovt.c 0.16028 0.09467 6402.97242 1.693 0.09049
##
## (Intercept) ***
## pDem_R *
## pDem_I **
## wave4_3
## wave4_2 .
## wave4_1 ***
## trustGovt.c ***
## pDem_R:wave4_3
## pDem_R:wave4_2 **
## pDem_R:wave4_1 ***
## pDem_I:wave4_3
## pDem_I:wave4_2
## pDem_I:wave4_1 ***
## pDem_R:trustGovt.c **
## pDem_I:trustGovt.c
## wave4_3:trustGovt.c .
## wave4_2:trustGovt.c .
## wave4_1:trustGovt.c
## pDem_R:wave4_3:trustGovt.c .
## pDem_R:wave4_2:trustGovt.c
## pDem_R:wave4_1:trustGovt.c ***
## pDem_I:wave4_3:trustGovt.c
## pDem_I:wave4_2:trustGovt.c
## pDem_I:wave4_1:trustGovt.c .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.r <- lmer(voteconfidence ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.r)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pRep_D + pRep_I) * (wave.lin + wave.quad +
## wave.cub) * trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21443.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.473e+00 2.741e-02 3.353e+03 126.694 < 2e-16
## pRep_D 6.729e-02 3.650e-02 4.100e+03 1.844 0.06532
## pRep_I -3.282e-01 5.210e-02 6.547e+03 -6.300 3.17e-10
## wave.lin 6.165e-01 3.807e-02 6.060e+03 16.194 < 2e-16
## wave.quad 9.318e-01 5.616e-02 5.640e+03 16.590 < 2e-16
## wave.cub -3.880e-01 3.395e-02 5.528e+03 -11.429 < 2e-16
## trustGovt.c 2.523e-01 1.951e-02 7.883e+03 12.934 < 2e-16
## pRep_D:wave.lin -7.135e-01 5.610e-02 6.418e+03 -12.718 < 2e-16
## pRep_D:wave.quad -1.156e+00 7.982e-02 5.674e+03 -14.477 < 2e-16
## pRep_D:wave.cub 5.675e-01 4.769e-02 5.573e+03 11.901 < 2e-16
## pRep_I:wave.lin -2.813e-01 9.037e-02 6.158e+03 -3.112 0.00186
## pRep_I:wave.quad -5.239e-01 1.323e-01 5.782e+03 -3.959 7.62e-05
## pRep_I:wave.cub 4.011e-01 7.967e-02 5.689e+03 5.034 4.94e-07
## pRep_D:trustGovt.c -9.052e-03 2.549e-02 7.973e+03 -0.355 0.72255
## pRep_I:trustGovt.c 3.468e-02 4.092e-02 7.911e+03 0.848 0.39671
## wave.lin:trustGovt.c -2.793e-01 3.805e-02 6.469e+03 -7.339 2.42e-13
## wave.quad:trustGovt.c -3.732e-01 5.434e-02 5.758e+03 -6.869 7.17e-12
## wave.cub:trustGovt.c 1.950e-01 3.303e-02 5.652e+03 5.903 3.77e-09
## pRep_D:wave.lin:trustGovt.c 3.265e-01 5.190e-02 6.500e+03 6.291 3.36e-10
## pRep_D:wave.quad:trustGovt.c 2.813e-01 7.383e-02 5.779e+03 3.811 0.00014
## pRep_D:wave.cub:trustGovt.c -2.136e-01 4.496e-02 5.695e+03 -4.752 2.06e-06
## pRep_I:wave.lin:trustGovt.c 2.662e-01 8.747e-02 6.601e+03 3.044 0.00235
## pRep_I:wave.quad:trustGovt.c 1.218e-01 1.254e-01 5.832e+03 0.971 0.33179
## pRep_I:wave.cub:trustGovt.c -1.355e-02 7.772e-02 5.779e+03 -0.174 0.86157
##
## (Intercept) ***
## pRep_D .
## pRep_I ***
## wave.lin ***
## wave.quad ***
## wave.cub ***
## trustGovt.c ***
## pRep_D:wave.lin ***
## pRep_D:wave.quad ***
## pRep_D:wave.cub ***
## pRep_I:wave.lin **
## pRep_I:wave.quad ***
## pRep_I:wave.cub ***
## pRep_D:trustGovt.c
## pRep_I:trustGovt.c
## wave.lin:trustGovt.c ***
## wave.quad:trustGovt.c ***
## wave.cub:trustGovt.c ***
## pRep_D:wave.lin:trustGovt.c ***
## pRep_D:wave.quad:trustGovt.c ***
## pRep_D:wave.cub:trustGovt.c ***
## pRep_I:wave.lin:trustGovt.c **
## pRep_I:wave.quad:trustGovt.c
## pRep_I:wave.cub:trustGovt.c
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.r.w1 <- lmer(voteconfidence ~ (pRep_D + pRep_I) * (wave1_3 + wave1_2 + wave1_4) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.r.w1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pRep_D + pRep_I) * (wave1_3 + wave1_2 + wave1_4) *
## trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21449.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.83442 0.03436 6192.43343 82.501 < 2e-16
## pRep_D 0.85482 0.04679 6957.86967 18.271 < 2e-16
## pRep_I 0.04364 0.06238 7826.21590 0.700 0.48424
## wave1_3 0.83128 0.03730 5822.20576 22.287 < 2e-16
## wave1_2 0.91101 0.03603 5641.41879 25.283 < 2e-16
## wave1_4 0.81053 0.04321 6003.48658 18.757 < 2e-16
## trustGovt.c 0.53398 0.02934 7871.42581 18.200 < 2e-16
## pRep_D:wave1_3 -0.97103 0.05191 6076.29180 -18.704 < 2e-16
## pRep_D:wave1_2 -1.18182 0.05107 5680.51567 -23.142 < 2e-16
## pRep_D:wave1_4 -0.99728 0.06349 6241.75836 -15.708 < 2e-16
## pRep_I:wave1_3 -0.37262 0.08481 6050.95477 -4.394 1.13e-05
## pRep_I:wave1_2 -0.63307 0.07524 5853.02344 -8.414 < 2e-16
## pRep_I:wave1_4 -0.48182 0.10260 6086.19645 -4.696 2.71e-06
## pRep_D:trustGovt.c -0.29603 0.03812 7801.13638 -7.766 9.16e-15
## pRep_I:trustGovt.c -0.13226 0.05756 7727.59844 -2.298 0.02159
## wave1_3:trustGovt.c -0.34729 0.03716 6055.01150 -9.346 < 2e-16
## wave1_2:trustGovt.c -0.40267 0.03400 5627.56785 -11.843 < 2e-16
## wave1_4:trustGovt.c -0.37676 0.04248 6339.71487 -8.868 < 2e-16
## pRep_D:wave1_3:trustGovt.c 0.33210 0.05010 6146.85524 6.629 3.68e-11
## pRep_D:wave1_2:trustGovt.c 0.38250 0.04535 5670.27890 8.434 < 2e-16
## pRep_D:wave1_4:trustGovt.c 0.43329 0.05782 6346.68901 7.494 7.60e-14
## pRep_I:wave1_3:trustGovt.c 0.25717 0.08589 6289.95938 2.994 0.00276
## pRep_I:wave1_2:trustGovt.c 0.13760 0.07317 5802.13742 1.880 0.06009
## pRep_I:wave1_4:trustGovt.c 0.27301 0.09607 6390.09592 2.842 0.00450
##
## (Intercept) ***
## pRep_D ***
## pRep_I
## wave1_3 ***
## wave1_2 ***
## wave1_4 ***
## trustGovt.c ***
## pRep_D:wave1_3 ***
## pRep_D:wave1_2 ***
## pRep_D:wave1_4 ***
## pRep_I:wave1_3 ***
## pRep_I:wave1_2 ***
## pRep_I:wave1_4 ***
## pRep_D:trustGovt.c ***
## pRep_I:trustGovt.c *
## wave1_3:trustGovt.c ***
## wave1_2:trustGovt.c ***
## wave1_4:trustGovt.c ***
## pRep_D:wave1_3:trustGovt.c ***
## pRep_D:wave1_2:trustGovt.c ***
## pRep_D:wave1_4:trustGovt.c ***
## pRep_I:wave1_3:trustGovt.c **
## pRep_I:wave1_2:trustGovt.c .
## pRep_I:wave1_4:trustGovt.c **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.r.w4 <- lmer(voteconfidence ~ (pRep_D + pRep_I) * (wave4_3 + wave4_2 + wave4_1) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.r.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pRep_D + pRep_I) * (wave4_3 + wave4_2 + wave4_1) *
## trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21449.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.64495 0.04149 7772.17209 87.845 < 2e-16
## pRep_D -0.14246 0.05906 7975.99051 -2.412 0.01588
## pRep_I -0.43818 0.09662 7324.11554 -4.535 5.85e-06
## wave4_3 0.02075 0.04305 5642.29192 0.482 0.62990
## wave4_2 0.10048 0.04317 5821.04146 2.328 0.01997
## wave4_1 -0.81053 0.04321 6003.48657 -18.757 < 2e-16
## trustGovt.c 0.15723 0.03447 6415.73145 4.561 5.18e-06
## pRep_D:wave4_3 0.02625 0.06136 5678.01785 0.428 0.66880
## pRep_D:wave4_2 -0.18453 0.06387 6048.40919 -2.889 0.00388
## pRep_D:wave4_1 0.99728 0.06349 6241.75836 15.708 < 2e-16
## pRep_I:wave4_3 0.10920 0.10879 5741.96950 1.004 0.31552
## pRep_I:wave4_2 -0.15125 0.10471 5894.78962 -1.444 0.14868
## pRep_I:wave4_1 0.48182 0.10260 6086.19645 4.696 2.71e-06
## pRep_D:trustGovt.c 0.13726 0.04748 6324.44478 2.891 0.00385
## pRep_I:trustGovt.c 0.14074 0.08133 6306.64647 1.730 0.08360
## wave4_3:trustGovt.c 0.02947 0.04233 5861.22465 0.696 0.48637
## wave4_2:trustGovt.c -0.02591 0.04240 6149.78189 -0.611 0.54117
## wave4_1:trustGovt.c 0.37676 0.04248 6339.71488 8.868 < 2e-16
## pRep_D:wave4_3:trustGovt.c -0.10119 0.05820 5859.39291 -1.739 0.08215
## pRep_D:wave4_2:trustGovt.c -0.05079 0.05822 6150.51872 -0.872 0.38304
## pRep_D:wave4_1:trustGovt.c -0.43329 0.05782 6346.68901 -7.494 7.60e-14
## pRep_I:wave4_3:trustGovt.c -0.01584 0.10158 5833.97983 -0.156 0.87606
## pRep_I:wave4_2:trustGovt.c -0.13541 0.09901 6217.24138 -1.368 0.17147
## pRep_I:wave4_1:trustGovt.c -0.27301 0.09607 6390.09593 -2.842 0.00450
##
## (Intercept) ***
## pRep_D *
## pRep_I ***
## wave4_3
## wave4_2 *
## wave4_1 ***
## trustGovt.c ***
## pRep_D:wave4_3
## pRep_D:wave4_2 **
## pRep_D:wave4_1 ***
## pRep_I:wave4_3
## pRep_I:wave4_2
## pRep_I:wave4_1 ***
## pRep_D:trustGovt.c **
## pRep_I:trustGovt.c .
## wave4_3:trustGovt.c
## wave4_2:trustGovt.c
## wave4_1:trustGovt.c ***
## pRep_D:wave4_3:trustGovt.c .
## pRep_D:wave4_2:trustGovt.c
## pRep_D:wave4_1:trustGovt.c ***
## pRep_I:wave4_3:trustGovt.c
## pRep_I:wave4_2:trustGovt.c
## pRep_I:wave4_1:trustGovt.c **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.i <- lmer(voteconfidence ~ (pInd_R + pInd_D) * (wave.lin + wave.quad + wave.cub) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.i)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pInd_R + pInd_D) * (wave.lin + wave.quad +
## wave.cub) * trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21443.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.14438 0.04687 6323.70366 67.084 < 2e-16
## pInd_R 0.32824 0.05210 6546.66551 6.300 3.17e-10
## pInd_D 0.39552 0.05139 6704.02659 7.696 1.61e-14
## wave.lin 0.33526 0.08175 6160.03440 4.101 4.16e-05
## wave.quad 0.40789 0.11922 5782.89832 3.421 0.000627
## wave.cub 0.01309 0.07181 5704.93326 0.182 0.855368
## trustGovt.c 0.28699 0.03648 7890.71741 7.867 4.12e-15
## pInd_R:wave.lin 0.28127 0.09037 6157.96542 3.112 0.001865
## pInd_R:wave.quad 0.52387 0.13233 5782.06954 3.959 7.62e-05
## pInd_R:wave.cub -0.40109 0.07967 5689.05672 -5.034 4.94e-07
## pInd_D:wave.lin -0.43224 0.09154 6253.98905 -4.722 2.39e-06
## pInd_D:wave.quad -0.63170 0.13227 5779.10131 -4.776 1.84e-06
## pInd_D:wave.cub 0.16646 0.07943 5701.66655 2.096 0.036164
## pInd_R:trustGovt.c -0.03468 0.04092 7911.21341 -0.848 0.396709
## pInd_D:trustGovt.c -0.04373 0.03973 7860.01858 -1.101 0.271109
## wave.lin:trustGovt.c -0.01302 0.07873 6646.60651 -0.165 0.868608
## wave.quad:trustGovt.c -0.25144 0.11276 5831.07319 -2.230 0.025789
## wave.cub:trustGovt.c 0.18145 0.07026 5798.13629 2.583 0.009828
## pInd_R:wave.lin:trustGovt.c -0.26623 0.08747 6601.30677 -3.044 0.002345
## pInd_R:wave.quad:trustGovt.c -0.12176 0.12545 5831.89550 -0.971 0.331790
## pInd_R:wave.cub:trustGovt.c 0.01355 0.07772 5778.82809 0.174 0.861568
## pInd_D:wave.lin:trustGovt.c 0.06024 0.08631 6628.36409 0.698 0.485233
## pInd_D:wave.quad:trustGovt.c 0.15956 0.12344 5831.18426 1.293 0.196205
## pInd_D:wave.cub:trustGovt.c -0.20008 0.07675 5802.89021 -2.607 0.009156
##
## (Intercept) ***
## pInd_R ***
## pInd_D ***
## wave.lin ***
## wave.quad ***
## wave.cub
## trustGovt.c ***
## pInd_R:wave.lin **
## pInd_R:wave.quad ***
## pInd_R:wave.cub ***
## pInd_D:wave.lin ***
## pInd_D:wave.quad ***
## pInd_D:wave.cub *
## pInd_R:trustGovt.c
## pInd_D:trustGovt.c
## wave.lin:trustGovt.c
## wave.quad:trustGovt.c *
## wave.cub:trustGovt.c **
## pInd_R:wave.lin:trustGovt.c **
## pInd_R:wave.quad:trustGovt.c
## pInd_R:wave.cub:trustGovt.c
## pInd_D:wave.lin:trustGovt.c
## pInd_D:wave.quad:trustGovt.c
## pInd_D:wave.cub:trustGovt.c **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m2.i <- lmer(voteconfidence ~ (pInd_R + pInd_D) * (wave.lin + wave.quad + wave.cub) * trustGovt.c + (1 | pid),
data = d)
summary(PEL.m2.i)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pInd_R + pInd_D) * (wave.lin + wave.quad +
## wave.cub) * trustGovt.c + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21443.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.14438 0.04687 6323.70366 67.084 < 2e-16
## pInd_R 0.32824 0.05210 6546.66551 6.300 3.17e-10
## pInd_D 0.39552 0.05139 6704.02659 7.696 1.61e-14
## wave.lin 0.33526 0.08175 6160.03440 4.101 4.16e-05
## wave.quad 0.40789 0.11922 5782.89832 3.421 0.000627
## wave.cub 0.01309 0.07181 5704.93326 0.182 0.855368
## trustGovt.c 0.28699 0.03648 7890.71741 7.867 4.12e-15
## pInd_R:wave.lin 0.28127 0.09037 6157.96542 3.112 0.001865
## pInd_R:wave.quad 0.52387 0.13233 5782.06954 3.959 7.62e-05
## pInd_R:wave.cub -0.40109 0.07967 5689.05672 -5.034 4.94e-07
## pInd_D:wave.lin -0.43224 0.09154 6253.98905 -4.722 2.39e-06
## pInd_D:wave.quad -0.63170 0.13227 5779.10131 -4.776 1.84e-06
## pInd_D:wave.cub 0.16646 0.07943 5701.66655 2.096 0.036164
## pInd_R:trustGovt.c -0.03468 0.04092 7911.21341 -0.848 0.396709
## pInd_D:trustGovt.c -0.04373 0.03973 7860.01858 -1.101 0.271109
## wave.lin:trustGovt.c -0.01302 0.07873 6646.60651 -0.165 0.868608
## wave.quad:trustGovt.c -0.25144 0.11276 5831.07319 -2.230 0.025789
## wave.cub:trustGovt.c 0.18145 0.07026 5798.13629 2.583 0.009828
## pInd_R:wave.lin:trustGovt.c -0.26623 0.08747 6601.30677 -3.044 0.002345
## pInd_R:wave.quad:trustGovt.c -0.12176 0.12545 5831.89550 -0.971 0.331790
## pInd_R:wave.cub:trustGovt.c 0.01355 0.07772 5778.82809 0.174 0.861568
## pInd_D:wave.lin:trustGovt.c 0.06024 0.08631 6628.36409 0.698 0.485233
## pInd_D:wave.quad:trustGovt.c 0.15956 0.12344 5831.18426 1.293 0.196205
## pInd_D:wave.cub:trustGovt.c -0.20008 0.07675 5802.89021 -2.607 0.009156
##
## (Intercept) ***
## pInd_R ***
## pInd_D ***
## wave.lin ***
## wave.quad ***
## wave.cub
## trustGovt.c ***
## pInd_R:wave.lin **
## pInd_R:wave.quad ***
## pInd_R:wave.cub ***
## pInd_D:wave.lin ***
## pInd_D:wave.quad ***
## pInd_D:wave.cub *
## pInd_R:trustGovt.c
## pInd_D:trustGovt.c
## wave.lin:trustGovt.c
## wave.quad:trustGovt.c *
## wave.cub:trustGovt.c **
## pInd_R:wave.lin:trustGovt.c **
## pInd_R:wave.quad:trustGovt.c
## pInd_R:wave.cub:trustGovt.c
## pInd_D:wave.lin:trustGovt.c
## pInd_D:wave.quad:trustGovt.c
## pInd_D:wave.cub:trustGovt.c **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1d$trustGovt.hi <- d$trustGovt - (mean(d$trustGovt, na.rm = T) + sd(d$trustGovt, na.rm = T))
d$trustGovt.lo <- d$trustGovt + (mean(d$trustGovt, na.rm = T) + sd(d$trustGovt, na.rm = T))
PEL.m2.hiGT <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) * trustGovt.hi + (1 | pid),
data = d)
summary(PEL.m2.hiGT)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad +
## wave.cub) * trustGovt.hi + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21443.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6615 -0.5076 0.0520 0.5374 4.0936
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6126 0.7827
## Residual 0.5228 0.7230
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.674e+00 2.964e-02 6.313e+03 123.932
## pDem_Rep -5.729e-02 4.681e-02 6.114e+03 -1.224
## pParty_Ind -3.186e-01 7.309e-02 7.929e+03 -4.359
## wave.lin 1.947e-01 5.563e-02 6.363e+03 3.500
## wave.quad 1.081e-01 7.942e-02 5.801e+03 1.361
## wave.cub 6.664e-02 4.775e-02 5.725e+03 1.396
## trustGovt.hi 2.608e-01 1.519e-02 7.976e+03 17.177
## pDem_Rep:wave.lin 3.529e-01 8.400e-02 6.343e+03 4.200
## pDem_Rep:wave.quad 8.448e-01 1.194e-01 5.756e+03 7.076
## pDem_Rep:wave.cub -3.315e-01 7.091e-02 5.648e+03 -4.675
## pParty_Ind:wave.lin 1.893e-01 1.506e-01 6.375e+03 1.257
## pParty_Ind:wave.quad 3.304e-02 2.162e-01 5.857e+03 0.153
## pParty_Ind:wave.cub 2.203e-01 1.303e-01 5.782e+03 1.691
## pDem_Rep:trustGovt.hi 9.052e-03 2.549e-02 7.973e+03 0.355
## pParty_Ind:trustGovt.hi 3.921e-02 3.826e-02 7.864e+03 1.025
## wave.lin:trustGovt.hi -8.169e-02 3.141e-02 6.620e+03 -2.601
## wave.quad:trustGovt.hi -2.388e-01 4.473e-02 5.789e+03 -5.339
## wave.cub:trustGovt.hi 1.193e-01 2.769e-02 5.741e+03 4.308
## pDem_Rep:wave.lin:trustGovt.hi -3.265e-01 5.190e-02 6.500e+03 -6.291
## pDem_Rep:wave.quad:trustGovt.hi -2.813e-01 7.383e-02 5.779e+03 -3.811
## pDem_Rep:wave.cub:trustGovt.hi 2.136e-01 4.496e-02 5.695e+03 4.752
## pParty_Ind:wave.lin:trustGovt.hi 1.030e-01 8.292e-02 6.626e+03 1.242
## pParty_Ind:wave.quad:trustGovt.hi -1.890e-02 1.188e-01 5.837e+03 -0.159
## pParty_Ind:wave.cub:trustGovt.hi 9.326e-02 7.389e-02 5.800e+03 1.262
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep 0.221029
## pParty_Ind 1.32e-05 ***
## wave.lin 0.000468 ***
## wave.quad 0.173525
## wave.cub 0.162880
## trustGovt.hi < 2e-16 ***
## pDem_Rep:wave.lin 2.70e-05 ***
## pDem_Rep:wave.quad 1.66e-12 ***
## pDem_Rep:wave.cub 3.00e-06 ***
## pParty_Ind:wave.lin 0.208908
## pParty_Ind:wave.quad 0.878569
## pParty_Ind:wave.cub 0.090809 .
## pDem_Rep:trustGovt.hi 0.722546
## pParty_Ind:trustGovt.hi 0.305568
## wave.lin:trustGovt.hi 0.009328 **
## wave.quad:trustGovt.hi 9.68e-08 ***
## wave.cub:trustGovt.hi 1.67e-05 ***
## pDem_Rep:wave.lin:trustGovt.hi 3.36e-10 ***
## pDem_Rep:wave.quad:trustGovt.hi 0.000140 ***
## pDem_Rep:wave.cub:trustGovt.hi 2.06e-06 ***
## pParty_Ind:wave.lin:trustGovt.hi 0.214265
## pParty_Ind:wave.quad:trustGovt.hi 0.873664
## pParty_Ind:wave.cub:trustGovt.hi 0.206943
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 13. Moderator: Emotions
Positive Emotions
ggplot(d[!is.na(d$party_factor),],
aes(x = Pos_Emo,
y = voteconfidence,
fill = party_factor,
color = party_factor)) +
geom_smooth(method = "lm") +
facet_grid(~wave, labeller = as_labeller(wave_label)) +
# geom_text(data = na.omit(n_bins_govtrust), aes(label = paste0("n = ", n)),
# x = 1.4, y = 1.2,
# size = 3,
# inherit.aes = FALSE) +
labs(x = "Positive Emotions",
y = "Perceived Election Legitimacy") +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
scale_color_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1)) +
theme_bw()
party.wave_label <- c("Democrat" = "Democrat", "Independent" = "Independent", "Republican" = "Republican",
`1` = "Wave 1", `2` = "Wave 2", `3` = "Wave 3", `4` = "Wave 4")
ggplot(d.EL[!is.na(d.EL$party_factor),],
aes(x = Pos_Emo,
y = voteconf,
color = Vote_Type,
group = Vote_Type)) +
geom_smooth(method = "lm") +
facet_grid(wave~party_factor, labeller = as_labeller(party.wave_label)) +
# geom_text(data = na.omit(n_bins_govtrust), aes(label = paste0("n = ", n)),
# x = 1.4, y = 1.2,
# size = 3,
# inherit.aes = FALSE) +
labs(x = "Positive Emotions",
y = "Perceived Election Legitimacy") +
scale_color_manual("Vote Type",
values = c("#00C9A8","#FF0000"),
labels = c("Own Vote", "National Votes")) +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1)) +
theme_bw()
Negative Emotions
ggplot(d, aes(x=Neg_Emo, y = voteconfidence)) +
geom_smooth(method="lm", color="#69b3a2") +
theme_bw() +
labs(x = "Negative Emotions",
y = "Perceived Election Legitimacy") +
coord_cartesian(ylim = c(1,5))
ggplot(d[!is.na(d$party_factor),],
aes(x = Neg_Emo,
y = voteconfidence,
fill = party_factor,
color = party_factor)) +
geom_smooth(method = "lm") +
facet_grid(~wave, labeller = as_labeller(wave_label)) +
# geom_text(data = na.omit(n_bins_govtrust), aes(label = paste0("n = ", n)),
# x = 1.4, y = 1.2,
# size = 3,
# inherit.aes = FALSE) +
labs(x = "Negative Emotions",
y = "Perceived Election Legitimacy") +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
scale_color_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1)) +
theme_bw()
ggplot(d.EL[!is.na(d.EL$party_factor),],
aes(x = Neg_Emo,
y = voteconf,
color = Vote_Type,
group = Vote_Type)) +
geom_smooth(method = "lm") +
facet_grid(wave~party_factor, labeller = as_labeller(party.wave_label)) +
# geom_text(data = na.omit(n_bins_govtrust), aes(label = paste0("n = ", n)),
# x = 1.4, y = 1.2,
# size = 3,
# inherit.aes = FALSE) +
labs(x = "Negative Emotions",
y = "Perceived Election Legitimacy") +
scale_color_manual("Vote Type",
values = c("#00C9A8","#FF0000"),
labels = c("Own Vote", "National Votes")) +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1)) +
theme_bw()
Summary
Positive Emotions
Positive emotions (hope and pride; r = .75) are positively related to PEL (b = 0.22, p < .001), though more strongly for Republicans than for Democrats (b = 0.06, p < .001). The positive emotions-PEL relationship does not change linearly over time, though there is a 3-way interaction of positive emotions, party ID (Dem vs. Rep), and quadratic time (b = 0.15, p = .016), such that the emotions-PEL slope is more similar for Republicans and Democrats in waves 1 and 4 than for waves 2 and 3.
Negative Emotions
Negative emotions (anger, fear, and disgust; \(\alpha = .90\)) are negatively related to PEL (b = -0.14, p < .001), though more strongly for Democrats than for Republicans (b = -0.08, p < .001). The negative emotions-PEL relationship does not change linearly over time, though it does change as a function of cubic time (b = -0.08, p < .001).
There is a 3-way interaction of negative emotions, party ID (Dem vs. Rep), and linear time (b = 0.24, p < .001), such that the emotions-PEL slope becomes stronger/more negative over time for Democrats (b = -0.11, p < .001), and attenuates/becomes less negative over time for Republicans (b = 0.13, p = .001).
Negative emotions-PEL slope for: Democrats in wave 1 (b = -0.05, p = .018) and wave 4 (b = -0.19, p < .001); Republicans in wave 1 (b = -0.20, p < .001) and wave 4 (b = -0.12, p = .004).
Models
# Positive Emotions
PEL.m3.l <- lmer(voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin + wave.quad + wave.cub) * Pos_Emo + (1 | pid),
data = d.EL)
summary(PEL.m3.l)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin +
## wave.quad + wave.cub) * Pos_Emo + (1 | pid)
## Data: d.EL
##
## REML criterion at convergence: 41563.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.4334 -0.5312 0.0448 0.5743 3.7804
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7724 0.8789
## Residual 0.5797 0.7614
## Number of obs: 15628, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.788e+00 3.336e-02 1.008e+04 83.578
## pDem_Rep -4.487e-01 5.907e-02 1.296e+04 -7.596
## pParty_Ind -2.663e-01 7.492e-02 1.528e+04 -3.555
## vOwn_Natl -3.103e-01 3.937e-02 1.306e+04 -7.880
## wave.lin 1.578e-01 5.604e-02 1.393e+04 2.815
## wave.quad 2.838e-01 8.403e-02 1.362e+04 3.377
## wave.cub -2.497e-02 5.119e-02 1.350e+04 -0.488
## Pos_Emo 2.188e-01 1.068e-02 1.557e+04 20.497
## pDem_Rep:vOwn_Natl 2.291e-01 7.165e-02 1.298e+04 3.197
## pParty_Ind:vOwn_Natl 1.343e-01 1.004e-01 1.309e+04 1.338
## pDem_Rep:wave.lin 1.243e+00 1.034e-01 1.390e+04 12.025
## pDem_Rep:wave.quad 1.637e-01 1.557e-01 1.369e+04 1.051
## pDem_Rep:wave.cub -4.300e-01 9.449e-02 1.352e+04 -4.551
## pParty_Ind:wave.lin -7.119e-01 1.435e-01 1.402e+04 -4.960
## pParty_Ind:wave.quad 4.947e-02 2.155e-01 1.367e+04 0.230
## pParty_Ind:wave.cub -9.036e-02 1.312e-01 1.356e+04 -0.689
## vOwn_Natl:wave.lin -4.867e-02 1.010e-01 1.298e+04 -0.482
## vOwn_Natl:wave.quad -1.804e-01 1.556e-01 1.297e+04 -1.159
## vOwn_Natl:wave.cub 1.800e-01 9.603e-02 1.298e+04 1.874
## pDem_Rep:Pos_Emo 6.270e-02 1.677e-02 1.551e+04 3.739
## pParty_Ind:Pos_Emo 7.639e-03 2.751e-02 1.547e+04 0.278
## vOwn_Natl:Pos_Emo 2.447e-02 1.500e-02 1.306e+04 1.631
## wave.lin:Pos_Emo 4.336e-02 2.183e-02 1.393e+04 1.986
## wave.quad:Pos_Emo 5.241e-02 3.226e-02 1.367e+04 1.625
## wave.cub:Pos_Emo -3.580e-02 1.942e-02 1.359e+04 -1.843
## pDem_Rep:vOwn_Natl:wave.lin 5.222e-01 1.849e-01 1.294e+04 2.824
## pDem_Rep:vOwn_Natl:wave.quad 7.872e-01 2.853e-01 1.294e+04 2.759
## pDem_Rep:vOwn_Natl:wave.cub -1.756e-01 1.759e-01 1.294e+04 -0.998
## pParty_Ind:vOwn_Natl:wave.lin 2.762e-01 2.574e-01 1.300e+04 1.073
## pParty_Ind:vOwn_Natl:wave.quad -5.650e-01 3.963e-01 1.298e+04 -1.426
## pParty_Ind:vOwn_Natl:wave.cub 6.757e-02 2.447e-01 1.300e+04 0.276
## pDem_Rep:vOwn_Natl:Pos_Emo -9.605e-02 2.296e-02 1.296e+04 -4.183
## pParty_Ind:vOwn_Natl:Pos_Emo -1.794e-02 4.033e-02 1.308e+04 -0.445
## pDem_Rep:wave.lin:Pos_Emo -6.962e-02 3.385e-02 1.395e+04 -2.057
## pDem_Rep:wave.quad:Pos_Emo 1.568e-01 5.022e-02 1.372e+04 3.123
## pDem_Rep:wave.cub:Pos_Emo 1.249e-02 3.012e-02 1.355e+04 0.415
## pParty_Ind:wave.lin:Pos_Emo 3.221e-01 5.880e-02 1.397e+04 5.478
## pParty_Ind:wave.quad:Pos_Emo 3.680e-02 8.722e-02 1.371e+04 0.422
## pParty_Ind:wave.cub:Pos_Emo 3.003e-02 5.238e-02 1.363e+04 0.573
## vOwn_Natl:wave.lin:Pos_Emo -1.385e-02 3.916e-02 1.299e+04 -0.354
## vOwn_Natl:wave.quad:Pos_Emo 6.292e-02 5.934e-02 1.297e+04 1.060
## vOwn_Natl:wave.cub:Pos_Emo -2.471e-02 3.601e-02 1.298e+04 -0.686
## pDem_Rep:vOwn_Natl:wave.lin:Pos_Emo -1.345e-01 6.000e-02 1.294e+04 -2.241
## pDem_Rep:vOwn_Natl:wave.quad:Pos_Emo -1.494e-01 9.154e-02 1.293e+04 -1.633
## pDem_Rep:vOwn_Natl:wave.cub:Pos_Emo 2.653e-02 5.576e-02 1.294e+04 0.476
## pParty_Ind:vOwn_Natl:wave.lin:Pos_Emo -1.939e-01 1.054e-01 1.301e+04 -1.840
## pParty_Ind:vOwn_Natl:wave.quad:Pos_Emo 2.112e-01 1.594e-01 1.298e+04 1.325
## pParty_Ind:vOwn_Natl:wave.cub:Pos_Emo 4.546e-02 9.667e-02 1.300e+04 0.470
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep 3.26e-14 ***
## pParty_Ind 0.000379 ***
## vOwn_Natl 3.52e-15 ***
## wave.lin 0.004882 **
## wave.quad 0.000734 ***
## wave.cub 0.625620
## Pos_Emo < 2e-16 ***
## pDem_Rep:vOwn_Natl 0.001390 **
## pParty_Ind:vOwn_Natl 0.181046
## pDem_Rep:wave.lin < 2e-16 ***
## pDem_Rep:wave.quad 0.293087
## pDem_Rep:wave.cub 5.38e-06 ***
## pParty_Ind:wave.lin 7.12e-07 ***
## pParty_Ind:wave.quad 0.818445
## pParty_Ind:wave.cub 0.490954
## vOwn_Natl:wave.lin 0.629940
## vOwn_Natl:wave.quad 0.246521
## vOwn_Natl:wave.cub 0.060931 .
## pDem_Rep:Pos_Emo 0.000185 ***
## pParty_Ind:Pos_Emo 0.781301
## vOwn_Natl:Pos_Emo 0.102889
## wave.lin:Pos_Emo 0.047030 *
## wave.quad:Pos_Emo 0.104273
## wave.cub:Pos_Emo 0.065281 .
## pDem_Rep:vOwn_Natl:wave.lin 0.004749 **
## pDem_Rep:vOwn_Natl:wave.quad 0.005806 **
## pDem_Rep:vOwn_Natl:wave.cub 0.318186
## pParty_Ind:vOwn_Natl:wave.lin 0.283268
## pParty_Ind:vOwn_Natl:wave.quad 0.153956
## pParty_Ind:vOwn_Natl:wave.cub 0.782414
## pDem_Rep:vOwn_Natl:Pos_Emo 2.90e-05 ***
## pParty_Ind:vOwn_Natl:Pos_Emo 0.656412
## pDem_Rep:wave.lin:Pos_Emo 0.039741 *
## pDem_Rep:wave.quad:Pos_Emo 0.001793 **
## pDem_Rep:wave.cub:Pos_Emo 0.678322
## pParty_Ind:wave.lin:Pos_Emo 4.38e-08 ***
## pParty_Ind:wave.quad:Pos_Emo 0.673087
## pParty_Ind:wave.cub:Pos_Emo 0.566356
## vOwn_Natl:wave.lin:Pos_Emo 0.723640
## vOwn_Natl:wave.quad:Pos_Emo 0.289026
## vOwn_Natl:wave.cub:Pos_Emo 0.492546
## pDem_Rep:vOwn_Natl:wave.lin:Pos_Emo 0.025022 *
## pDem_Rep:vOwn_Natl:wave.quad:Pos_Emo 0.102573
## pDem_Rep:vOwn_Natl:wave.cub:Pos_Emo 0.634270
## pParty_Ind:vOwn_Natl:wave.lin:Pos_Emo 0.065820 .
## pParty_Ind:vOwn_Natl:wave.quad:Pos_Emo 0.185254
## pParty_Ind:vOwn_Natl:wave.cub:Pos_Emo 0.638162
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m3 <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) * Pos_Emo + (1 | pid),
data = d)
summary(PEL.m3)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad +
## wave.cub) * Pos_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21783
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9365 -0.5022 0.0459 0.5559 3.9174
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7006 0.8370
## Residual 0.5056 0.7111
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.762e+00 3.789e-02 7.504e+03 72.902 < 2e-16
## pDem_Rep -4.950e-01 6.971e-02 7.978e+03 -7.101 1.35e-12
## pParty_Ind -3.163e-01 8.775e-02 8.056e+03 -3.604 0.000315
## wave.lin 1.918e-01 6.918e-02 6.136e+03 2.773 0.005567
## wave.quad 2.212e-01 1.033e-01 5.937e+03 2.142 0.032243
## wave.cub -1.375e-02 6.288e-02 5.883e+03 -0.219 0.826892
## Pos_Emo 2.193e-01 1.280e-02 7.820e+03 17.136 < 2e-16
## pDem_Rep:wave.lin 1.229e+00 1.320e-01 6.136e+03 9.305 < 2e-16
## pDem_Rep:wave.quad 1.949e-01 1.987e-01 6.001e+03 0.981 0.326545
## pDem_Rep:wave.cub -4.395e-01 1.204e-01 5.885e+03 -3.652 0.000263
## pParty_Ind:wave.lin -5.841e-01 1.748e-01 6.196e+03 -3.342 0.000838
## pParty_Ind:wave.quad -1.453e-01 2.604e-01 5.968e+03 -0.558 0.576865
## pParty_Ind:wave.cub -4.502e-02 1.588e-01 5.938e+03 -0.283 0.776867
## pDem_Rep:Pos_Emo 6.216e-02 2.079e-02 7.719e+03 2.990 0.002801
## pParty_Ind:Pos_Emo 6.897e-03 3.278e-02 7.634e+03 0.210 0.833370
## wave.lin:Pos_Emo 2.377e-02 2.663e-02 6.160e+03 0.892 0.372205
## wave.quad:Pos_Emo 7.053e-02 3.932e-02 5.977e+03 1.794 0.072901
## wave.cub:Pos_Emo -2.942e-02 2.368e-02 5.941e+03 -1.242 0.214145
## pDem_Rep:wave.lin:Pos_Emo -7.081e-02 4.342e-02 6.180e+03 -1.631 0.102993
## pDem_Rep:wave.quad:Pos_Emo 1.550e-01 6.443e-02 6.019e+03 2.406 0.016170
## pDem_Rep:wave.cub:Pos_Emo 1.706e-02 3.862e-02 5.907e+03 0.442 0.658666
## pParty_Ind:wave.lin:Pos_Emo 2.566e-01 7.086e-02 6.191e+03 3.621 0.000295
## pParty_Ind:wave.quad:Pos_Emo 1.096e-01 1.047e-01 6.006e+03 1.046 0.295594
## pParty_Ind:wave.cub:Pos_Emo 3.985e-02 6.302e-02 5.983e+03 0.632 0.527236
##
## (Intercept) ***
## pDem_Rep ***
## pParty_Ind ***
## wave.lin **
## wave.quad *
## wave.cub
## Pos_Emo ***
## pDem_Rep:wave.lin ***
## pDem_Rep:wave.quad
## pDem_Rep:wave.cub ***
## pParty_Ind:wave.lin ***
## pParty_Ind:wave.quad
## pParty_Ind:wave.cub
## pDem_Rep:Pos_Emo **
## pParty_Ind:Pos_Emo
## wave.lin:Pos_Emo
## wave.quad:Pos_Emo .
## wave.cub:Pos_Emo
## pDem_Rep:wave.lin:Pos_Emo
## pDem_Rep:wave.quad:Pos_Emo *
## pDem_Rep:wave.cub:Pos_Emo
## pParty_Ind:wave.lin:Pos_Emo ***
## pParty_Ind:wave.quad:Pos_Emo
## pParty_Ind:wave.cub:Pos_Emo
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1# Negative Emotions
PEL.m4.l <- lmer(voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin + wave.quad + wave.cub) * Neg_Emo + (1 | pid),
data = d.EL)
summary(PEL.m4.l)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconf ~ (pDem_Rep + pParty_Ind) * vOwn_Natl * (wave.lin +
## wave.quad + wave.cub) * Neg_Emo + (1 | pid)
## Data: d.EL
##
## REML criterion at convergence: 41920.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5643 -0.5353 0.0429 0.5749 3.8990
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7970 0.8927
## Residual 0.5924 0.7696
## Number of obs: 15628, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.718e+00 3.243e-02 9.271e+03 114.623
## pDem_Rep -4.017e-02 5.578e-02 1.156e+04 -0.720
## pParty_Ind -4.283e-01 7.347e-02 1.513e+04 -5.830
## vOwn_Natl -2.059e-01 3.693e-02 1.303e+04 -5.575
## wave.lin 3.275e-01 5.345e-02 1.389e+04 6.127
## wave.quad 5.219e-01 7.798e-02 1.354e+04 6.693
## wave.cub -2.988e-01 4.707e-02 1.342e+04 -6.348
## Neg_Emo -1.502e-01 1.059e-02 1.558e+04 -14.179
## pDem_Rep:vOwn_Natl -3.050e-01 6.427e-02 1.296e+04 -4.746
## pParty_Ind:vOwn_Natl -1.780e-01 9.567e-02 1.305e+04 -1.860
## pDem_Rep:wave.lin 4.923e-01 9.380e-02 1.380e+04 5.248
## pDem_Rep:wave.quad 1.194e+00 1.381e-01 1.355e+04 8.650
## pDem_Rep:wave.cub -5.412e-01 8.304e-02 1.343e+04 -6.517
## pParty_Ind:wave.lin 2.663e-01 1.391e-01 1.398e+04 1.915
## pParty_Ind:wave.quad 1.560e-02 2.031e-01 1.360e+04 0.077
## pParty_Ind:wave.cub 3.191e-02 1.228e-01 1.348e+04 0.260
## vOwn_Natl:wave.lin -4.026e-02 9.611e-02 1.297e+04 -0.419
## vOwn_Natl:wave.quad -4.009e-03 1.462e-01 1.296e+04 -0.027
## vOwn_Natl:wave.cub 3.989e-02 8.900e-02 1.296e+04 0.448
## pDem_Rep:Neg_Emo -9.755e-02 1.909e-02 1.545e+04 -5.111
## pParty_Ind:Neg_Emo 3.847e-02 2.579e-02 1.550e+04 1.492
## vOwn_Natl:Neg_Emo -1.550e-02 1.439e-02 1.300e+04 -1.077
## wave.lin:Neg_Emo -3.682e-02 2.079e-02 1.407e+04 -1.771
## wave.quad:Neg_Emo -6.490e-02 3.091e-02 1.363e+04 -2.100
## wave.cub:Neg_Emo 7.756e-02 1.910e-02 1.349e+04 4.061
## pDem_Rep:vOwn_Natl:wave.lin -1.014e-01 1.681e-01 1.293e+04 -0.603
## pDem_Rep:vOwn_Natl:wave.quad 2.101e-01 2.561e-01 1.293e+04 0.821
## pDem_Rep:vOwn_Natl:wave.cub 6.043e-02 1.557e-01 1.292e+04 0.388
## pParty_Ind:vOwn_Natl:wave.lin -5.383e-01 2.489e-01 1.298e+04 -2.162
## pParty_Ind:vOwn_Natl:wave.quad 1.756e-01 3.786e-01 1.297e+04 0.464
## pParty_Ind:vOwn_Natl:wave.cub 3.519e-01 2.306e-01 1.298e+04 1.526
## pDem_Rep:vOwn_Natl:Neg_Emo 9.543e-02 2.665e-02 1.294e+04 3.580
## pParty_Ind:vOwn_Natl:Neg_Emo 1.090e-01 3.647e-02 1.302e+04 2.987
## pDem_Rep:wave.lin:Neg_Emo 2.409e-01 3.888e-02 1.393e+04 6.197
## pDem_Rep:wave.quad:Neg_Emo -1.714e-01 5.844e-02 1.368e+04 -2.932
## pDem_Rep:wave.cub:Neg_Emo 5.753e-02 3.576e-02 1.352e+04 1.609
## pParty_Ind:wave.lin:Neg_Emo -1.226e-01 5.287e-02 1.419e+04 -2.319
## pParty_Ind:wave.quad:Neg_Emo 5.445e-02 7.851e-02 1.368e+04 0.694
## pParty_Ind:wave.cub:Neg_Emo -2.177e-02 4.863e-02 1.354e+04 -0.448
## vOwn_Natl:wave.lin:Neg_Emo -6.371e-03 3.665e-02 1.296e+04 -0.174
## vOwn_Natl:wave.quad:Neg_Emo -2.703e-02 5.721e-02 1.296e+04 -0.472
## vOwn_Natl:wave.cub:Neg_Emo 2.530e-02 3.573e-02 1.296e+04 0.708
## pDem_Rep:vOwn_Natl:wave.lin:Neg_Emo 8.339e-02 6.840e-02 1.293e+04 1.219
## pDem_Rep:vOwn_Natl:wave.quad:Neg_Emo 5.901e-02 1.064e-01 1.292e+04 0.555
## pDem_Rep:vOwn_Natl:wave.cub:Neg_Emo -4.584e-02 6.619e-02 1.292e+04 -0.693
## pParty_Ind:vOwn_Natl:wave.lin:Neg_Emo 1.412e-01 9.264e-02 1.297e+04 1.525
## pParty_Ind:vOwn_Natl:wave.quad:Neg_Emo -9.958e-02 1.448e-01 1.297e+04 -0.688
## pParty_Ind:vOwn_Natl:wave.cub:Neg_Emo -5.062e-02 9.062e-02 1.297e+04 -0.559
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep 0.471399
## pParty_Ind 5.64e-09 ***
## vOwn_Natl 2.52e-08 ***
## wave.lin 9.21e-10 ***
## wave.quad 2.27e-11 ***
## wave.cub 2.25e-10 ***
## Neg_Emo < 2e-16 ***
## pDem_Rep:vOwn_Natl 2.10e-06 ***
## pParty_Ind:vOwn_Natl 0.062902 .
## pDem_Rep:wave.lin 1.56e-07 ***
## pDem_Rep:wave.quad < 2e-16 ***
## pDem_Rep:wave.cub 7.43e-11 ***
## pParty_Ind:wave.lin 0.055493 .
## pParty_Ind:wave.quad 0.938765
## pParty_Ind:wave.cub 0.794960
## vOwn_Natl:wave.lin 0.675307
## vOwn_Natl:wave.quad 0.978128
## vOwn_Natl:wave.cub 0.653975
## pDem_Rep:Neg_Emo 3.25e-07 ***
## pParty_Ind:Neg_Emo 0.135808
## vOwn_Natl:Neg_Emo 0.281625
## wave.lin:Neg_Emo 0.076640 .
## wave.quad:Neg_Emo 0.035786 *
## wave.cub:Neg_Emo 4.91e-05 ***
## pDem_Rep:vOwn_Natl:wave.lin 0.546265
## pDem_Rep:vOwn_Natl:wave.quad 0.411821
## pDem_Rep:vOwn_Natl:wave.cub 0.697923
## pParty_Ind:vOwn_Natl:wave.lin 0.030621 *
## pParty_Ind:vOwn_Natl:wave.quad 0.642800
## pParty_Ind:vOwn_Natl:wave.cub 0.127107
## pDem_Rep:vOwn_Natl:Neg_Emo 0.000344 ***
## pParty_Ind:vOwn_Natl:Neg_Emo 0.002819 **
## pDem_Rep:wave.lin:Neg_Emo 5.93e-10 ***
## pDem_Rep:wave.quad:Neg_Emo 0.003374 **
## pDem_Rep:wave.cub:Neg_Emo 0.107691
## pParty_Ind:wave.lin:Neg_Emo 0.020387 *
## pParty_Ind:wave.quad:Neg_Emo 0.487980
## pParty_Ind:wave.cub:Neg_Emo 0.654412
## vOwn_Natl:wave.lin:Neg_Emo 0.861996
## vOwn_Natl:wave.quad:Neg_Emo 0.636584
## vOwn_Natl:wave.cub:Neg_Emo 0.479015
## pDem_Rep:vOwn_Natl:wave.lin:Neg_Emo 0.222812
## pDem_Rep:vOwn_Natl:wave.quad:Neg_Emo 0.579103
## pDem_Rep:vOwn_Natl:wave.cub:Neg_Emo 0.488599
## pParty_Ind:vOwn_Natl:wave.lin:Neg_Emo 0.127361
## pParty_Ind:vOwn_Natl:wave.quad:Neg_Emo 0.491773
## pParty_Ind:vOwn_Natl:wave.cub:Neg_Emo 0.576412
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m4 <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) * Neg_Emo + (1 | pid),
data = d)
summary(PEL.m4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad +
## wave.cub) * Neg_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22052.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6457 -0.5055 0.0621 0.5514 3.6219
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5240 0.7239
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.65905 0.03641 7267.06976 100.486 < 2e-16
## pDem_Rep -0.12435 0.06525 7697.94750 -1.906 0.056733
## pParty_Ind -0.58006 0.08526 8071.17448 -6.804 1.09e-11
## wave.lin 0.28783 0.06647 6138.22914 4.330 1.51e-05
## wave.quad 0.49952 0.09731 5891.90339 5.133 2.94e-07
## wave.cub -0.23930 0.05859 5835.83647 -4.085 4.47e-05
## Neg_Emo -0.13546 0.01277 7825.73546 -10.604 < 2e-16
## pDem_Rep:wave.lin 0.46433 0.12097 6093.72699 3.838 0.000125
## pDem_Rep:wave.quad 1.20228 0.17855 5905.67486 6.734 1.81e-11
## pDem_Rep:wave.cub -0.52388 0.10735 5826.62679 -4.880 1.09e-06
## pParty_Ind:wave.lin 0.18853 0.17078 6193.33192 1.104 0.269647
## pParty_Ind:wave.quad 0.07593 0.24992 5937.51038 0.304 0.761267
## pParty_Ind:wave.cub 0.16292 0.15086 5899.55902 1.080 0.280223
## pDem_Rep:Neg_Emo -0.08219 0.02388 7618.88927 -3.442 0.000579
## pParty_Ind:Neg_Emo 0.07472 0.03085 7625.47199 2.422 0.015464
## wave.lin:Neg_Emo -0.02284 0.02602 6232.62464 -0.878 0.380144
## wave.quad:Neg_Emo -0.06505 0.03893 5964.12781 -1.671 0.094808
## wave.cub:Neg_Emo 0.06421 0.02396 5880.17972 2.680 0.007383
## pDem_Rep:wave.lin:Neg_Emo 0.24737 0.05015 6179.76111 4.933 8.32e-07
## pDem_Rep:wave.quad:Neg_Emo -0.16478 0.07565 6006.42943 -2.178 0.029426
## pDem_Rep:wave.cub:Neg_Emo 0.05242 0.04628 5888.20237 1.133 0.257327
## pParty_Ind:wave.lin:Neg_Emo -0.10276 0.06530 6304.78833 -1.574 0.115631
## pParty_Ind:wave.quad:Neg_Emo 0.01487 0.09761 5998.72272 0.152 0.878891
## pParty_Ind:wave.cub:Neg_Emo -0.04650 0.06021 5926.01730 -0.772 0.440028
##
## (Intercept) ***
## pDem_Rep .
## pParty_Ind ***
## wave.lin ***
## wave.quad ***
## wave.cub ***
## Neg_Emo ***
## pDem_Rep:wave.lin ***
## pDem_Rep:wave.quad ***
## pDem_Rep:wave.cub ***
## pParty_Ind:wave.lin
## pParty_Ind:wave.quad
## pParty_Ind:wave.cub
## pDem_Rep:Neg_Emo ***
## pParty_Ind:Neg_Emo *
## wave.lin:Neg_Emo
## wave.quad:Neg_Emo .
## wave.cub:Neg_Emo **
## pDem_Rep:wave.lin:Neg_Emo ***
## pDem_Rep:wave.quad:Neg_Emo *
## pDem_Rep:wave.cub:Neg_Emo
## pParty_Ind:wave.lin:Neg_Emo
## pParty_Ind:wave.quad:Neg_Emo
## pParty_Ind:wave.cub:Neg_Emo
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Simple-effects models
# Negative Emotions
PEL.m4.d <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) * Neg_Emo + (1 | pid),
data = d)
summary(PEL.m4.d)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave.lin + wave.quad +
## wave.cub) * Neg_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22052.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6457 -0.5055 0.0621 0.5514 3.6219
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5240 0.7239
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.915e+00 4.903e-02 7.658e+03 79.843 < 2e-16 ***
## pDem_R -1.244e-01 6.525e-02 7.698e+03 -1.906 0.056733 .
## pDem_I -6.422e-01 9.245e-02 8.080e+03 -6.947 4.03e-12 ***
## wave.lin -7.181e-03 8.874e-02 6.045e+03 -0.081 0.935501
## wave.quad -1.269e-01 1.318e-01 5.861e+03 -0.963 0.335606
## wave.cub -3.166e-02 8.014e-02 5.806e+03 -0.395 0.692786
## Neg_Emo -1.193e-01 1.384e-02 8.012e+03 -8.617 < 2e-16 ***
## pDem_R:wave.lin 4.643e-01 1.210e-01 6.094e+03 3.838 0.000125 ***
## pDem_R:wave.quad 1.202e+00 1.786e-01 5.906e+03 6.734 1.81e-11 ***
## pDem_R:wave.cub -5.239e-01 1.073e-01 5.827e+03 -4.880 1.09e-06 ***
## pDem_I:wave.lin 4.207e-01 1.827e-01 6.168e+03 2.303 0.021338 *
## pDem_I:wave.quad 6.771e-01 2.682e-01 5.925e+03 2.525 0.011605 *
## pDem_I:wave.cub -9.902e-02 1.623e-01 5.891e+03 -0.610 0.541934
## pDem_R:Neg_Emo -8.219e-02 2.388e-02 7.619e+03 -3.442 0.000579 ***
## pDem_I:Neg_Emo 3.362e-02 3.155e-02 7.698e+03 1.066 0.286580
## wave.lin:Neg_Emo -1.123e-01 2.730e-02 6.153e+03 -4.112 3.97e-05 ***
## wave.quad:Neg_Emo 1.238e-02 4.010e-02 5.949e+03 0.309 0.757524
## wave.cub:Neg_Emo 5.349e-02 2.404e-02 5.900e+03 2.225 0.026111 *
## pDem_R:wave.lin:Neg_Emo 2.474e-01 5.015e-02 6.180e+03 4.933 8.32e-07 ***
## pDem_R:wave.quad:Neg_Emo -1.648e-01 7.565e-02 6.006e+03 -2.178 0.029426 *
## pDem_R:wave.cub:Neg_Emo 5.242e-02 4.627e-02 5.888e+03 1.133 0.257327
## pDem_I:wave.lin:Neg_Emo 2.092e-02 6.621e-02 6.297e+03 0.316 0.752008
## pDem_I:wave.quad:Neg_Emo -6.751e-02 9.859e-02 5.995e+03 -0.685 0.493504
## pDem_I:wave.cub:Neg_Emo -2.029e-02 6.056e-02 5.929e+03 -0.335 0.737675
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m4.d.w1 <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave1_2 + wave1_3 + wave1_4) * Neg_Emo + (1 | pid),
data = d)
summary(PEL.m4.d.w1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave1_2 + wave1_3 + wave1_4) *
## Neg_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22058.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6457 -0.5055 0.0621 0.5514 3.6219
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5240 0.7239
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.942e+00 5.921e-02 8.071e+03 66.573 < 2e-16 ***
## pDem_R -7.881e-01 8.717e-02 7.980e+03 -9.040 < 2e-16 ***
## pDem_I -1.047e+00 1.237e-01 7.832e+03 -8.463 < 2e-16 ***
## wave1_2 -4.151e-02 7.863e-02 6.124e+03 -0.528 0.597549
## wave1_3 -7.677e-02 8.301e-02 6.058e+03 -0.925 0.355106
## wave1_4 8.651e-03 1.013e-01 6.056e+03 0.085 0.931942
## Neg_Emo -5.286e-02 2.234e-02 7.465e+03 -2.366 0.017996 *
## pDem_R:wave1_2 1.110e+00 1.106e-01 6.184e+03 10.038 < 2e-16 ***
## pDem_R:wave1_3 8.184e-01 1.166e-01 6.114e+03 7.019 2.48e-12 ***
## pDem_R:wave1_4 7.263e-01 1.386e-01 6.111e+03 5.239 1.67e-07 ***
## pDem_I:wave1_2 5.180e-01 1.611e-01 6.277e+03 3.215 0.001312 **
## pDem_I:wave1_3 6.293e-01 1.744e-01 6.234e+03 3.608 0.000311 ***
## pDem_I:wave1_4 4.702e-01 2.098e-01 6.184e+03 2.241 0.025079 *
## pDem_R:Neg_Emo -1.516e-01 3.269e-02 7.225e+03 -4.637 3.60e-06 ***
## pDem_I:Neg_Emo 3.497e-02 4.858e-02 7.408e+03 0.720 0.471680
## wave1_2:Neg_Emo -6.200e-02 2.666e-02 6.287e+03 -2.326 0.020060 *
## wave1_3:Neg_Emo -6.464e-02 2.817e-02 6.159e+03 -2.295 0.021784 *
## wave1_4:Neg_Emo -1.390e-01 3.148e-02 6.201e+03 -4.416 1.02e-05 ***
## pDem_R:wave1_2:Neg_Emo -5.986e-02 4.662e-02 6.322e+03 -1.284 0.199154
## pDem_R:wave1_3:Neg_Emo 1.162e-01 4.972e-02 6.217e+03 2.338 0.019406 *
## pDem_R:wave1_4:Neg_Emo 2.212e-01 5.673e-02 6.203e+03 3.898 9.79e-05 ***
## pDem_I:wave1_2:Neg_Emo -1.331e-02 6.282e-02 6.374e+03 -0.212 0.832196
## pDem_I:wave1_3:Neg_Emo -2.314e-02 6.900e-02 6.324e+03 -0.335 0.737395
## pDem_I:wave1_4:Neg_Emo 3.107e-02 7.531e-02 6.323e+03 0.412 0.679996
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m4.d.w4 <- lmer(voteconfidence ~ (pDem_R + pDem_I) * (wave4_3 + wave4_2 + wave4_1) * Neg_Emo + (1 | pid),
data = d)
summary(PEL.m4.d.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_R + pDem_I) * (wave4_3 + wave4_2 + wave4_1) *
## Neg_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22058.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6457 -0.5055 0.0621 0.5514 3.6219
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5240 0.7239
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.951e+00 9.452e-02 7.073e+03 41.799 < 2e-16 ***
## pDem_R -6.179e-02 1.239e-01 7.077e+03 -0.499 0.61800
## pDem_I -5.764e-01 1.874e-01 6.668e+03 -3.076 0.00210 **
## wave4_3 -8.542e-02 1.063e-01 5.741e+03 -0.804 0.42169
## wave4_2 -5.016e-02 1.043e-01 5.837e+03 -0.481 0.63048
## wave4_1 -8.651e-03 1.013e-01 6.056e+03 -0.085 0.93194
## Neg_Emo -1.919e-01 2.540e-02 6.536e+03 -7.553 4.83e-14 ***
## pDem_R:wave4_3 9.215e-02 1.406e-01 5.754e+03 0.655 0.51238
## pDem_R:wave4_2 3.839e-01 1.377e-01 5.857e+03 2.787 0.00533 **
## pDem_R:wave4_1 -7.263e-01 1.386e-01 6.111e+03 -5.239 1.67e-07 ***
## pDem_I:wave4_3 1.591e-01 2.165e-01 5.787e+03 0.735 0.46245
## pDem_I:wave4_2 4.777e-02 2.082e-01 5.855e+03 0.229 0.81853
## pDem_I:wave4_1 -4.702e-01 2.098e-01 6.184e+03 -2.241 0.02508 *
## pDem_R:Neg_Emo 6.958e-02 4.898e-02 6.300e+03 1.421 0.15546
## pDem_I:Neg_Emo 6.603e-02 6.175e-02 6.328e+03 1.069 0.28494
## wave4_3:Neg_Emo 7.438e-02 3.021e-02 5.758e+03 2.462 0.01384 *
## wave4_2:Neg_Emo 7.702e-02 2.908e-02 5.857e+03 2.648 0.00811 **
## wave4_1:Neg_Emo 1.390e-01 3.148e-02 6.201e+03 4.416 1.02e-05 ***
## pDem_R:wave4_3:Neg_Emo -1.049e-01 5.948e-02 5.803e+03 -1.764 0.07780 .
## pDem_R:wave4_2:Neg_Emo -2.810e-01 5.797e-02 5.929e+03 -4.848 1.28e-06 ***
## pDem_R:wave4_1:Neg_Emo -2.212e-01 5.673e-02 6.203e+03 -3.898 9.79e-05 ***
## pDem_I:wave4_3:Neg_Emo -5.420e-02 7.659e-02 5.798e+03 -0.708 0.47917
## pDem_I:wave4_2:Neg_Emo -4.438e-02 7.219e-02 5.889e+03 -0.615 0.53876
## pDem_I:wave4_1:Neg_Emo -3.107e-02 7.531e-02 6.323e+03 -0.412 0.68000
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m4.r <- lmer(voteconfidence ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) * Neg_Emo + (1 | pid),
data = d)
summary(PEL.m4.r)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pRep_D + pRep_I) * (wave.lin + wave.quad +
## wave.cub) * Neg_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22052.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6457 -0.5055 0.0621 0.5514 3.6219
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5240 0.7239
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.79023 0.04424 7071.52188 85.670 < 2e-16 ***
## pRep_D 0.12435 0.06525 7697.94749 1.906 0.056733 .
## pRep_I -0.51788 0.09011 8079.91473 -5.747 9.39e-09 ***
## wave.lin 0.45715 0.08195 6137.86171 5.578 2.54e-08 ***
## wave.quad 1.07535 0.12036 5954.87066 8.934 < 2e-16 ***
## wave.cub -0.55555 0.07137 5850.27620 -7.784 8.24e-15 ***
## Neg_Emo -0.20146 0.01964 7409.98442 -10.256 < 2e-16 ***
## pRep_D:wave.lin -0.46433 0.12097 6093.72699 -3.838 0.000125 ***
## pRep_D:wave.quad -1.20228 0.17855 5905.67485 -6.734 1.81e-11 ***
## pRep_D:wave.cub 0.52388 0.10735 5826.62679 4.880 1.09e-06 ***
## pRep_I:wave.lin -0.04363 0.17962 6197.12815 -0.243 0.808082
## pRep_I:wave.quad -0.52521 0.26257 5943.17516 -2.000 0.045518 *
## pRep_I:wave.cub 0.42486 0.15787 5891.72439 2.691 0.007140 **
## pRep_D:Neg_Emo 0.08219 0.02388 7618.88928 3.442 0.000579 ***
## pRep_I:Neg_Emo 0.11581 0.03454 7559.10432 3.353 0.000805 ***
## wave.lin:Neg_Emo 0.13510 0.04193 6173.39924 3.222 0.001279 **
## wave.quad:Neg_Emo -0.15239 0.06406 6017.64788 -2.379 0.017387 *
## wave.cub:Neg_Emo 0.10592 0.03952 5879.16837 2.680 0.007381 **
## pRep_D:wave.lin:Neg_Emo -0.24737 0.05015 6179.76111 -4.933 8.32e-07 ***
## pRep_D:wave.quad:Neg_Emo 0.16478 0.07565 6006.42943 2.178 0.029426 *
## pRep_D:wave.cub:Neg_Emo -0.05242 0.04628 5888.20237 -1.133 0.257327
## pRep_I:wave.lin:Neg_Emo -0.22645 0.07350 6281.96299 -3.081 0.002073 **
## pRep_I:wave.quad:Neg_Emo 0.09726 0.11044 6003.29446 0.881 0.378514
## pRep_I:wave.cub:Neg_Emo -0.07271 0.06822 5915.06001 -1.066 0.286573
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m4.r.w1 <- lmer(voteconfidence ~ (pRep_D + pRep_I) * (wave1_2 + wave1_3 + wave1_4) * Neg_Emo + (1 | pid),
data = d)
summary(PEL.m4.r.w1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pRep_D + pRep_I) * (wave1_2 + wave1_3 + wave1_4) *
## Neg_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22058.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6457 -0.5055 0.0621 0.5514 3.6219
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5240 0.7239
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.15393 0.06462 8005.94244 48.807 < 2e-16 ***
## pRep_D 0.78806 0.08717 7980.27844 9.040 < 2e-16 ***
## pRep_I -0.25855 0.12612 7761.95301 -2.050 0.040392 *
## wave1_2 1.06862 0.07759 6234.71607 13.773 < 2e-16 ***
## wave1_3 0.74165 0.08167 6159.61109 9.081 < 2e-16 ***
## wave1_4 0.73492 0.09440 6164.15780 7.785 8.13e-15 ***
## Neg_Emo -0.20443 0.02393 7035.35153 -8.544 < 2e-16 ***
## pRep_D:wave1_2 -1.11014 0.11059 6183.81092 -10.038 < 2e-16 ***
## pRep_D:wave1_3 -0.81842 0.11661 6114.05298 -7.019 2.48e-12 ***
## pRep_D:wave1_4 -0.72627 0.13864 6111.33580 -5.239 1.67e-07 ***
## pRep_I:wave1_2 -0.59216 0.16039 6293.48993 -3.692 0.000224 ***
## pRep_I:wave1_3 -0.18911 0.17384 6262.39606 -1.088 0.276711
## pRep_I:wave1_4 -0.25606 0.20661 6211.64686 -1.239 0.215270
## pRep_D:Neg_Emo 0.15158 0.03269 7225.44007 4.637 3.60e-06 ***
## pRep_I:Neg_Emo 0.18654 0.04941 7341.68102 3.775 0.000161 ***
## wave1_2:Neg_Emo -0.12186 0.03811 6313.69646 -3.197 0.001395 **
## wave1_3:Neg_Emo 0.05161 0.04083 6222.88375 1.264 0.206247
## wave1_4:Neg_Emo 0.08214 0.04704 6185.04135 1.746 0.080842 .
## pRep_D:wave1_2:Neg_Emo 0.05986 0.04662 6322.27929 1.284 0.199154
## pRep_D:wave1_3:Neg_Emo -0.11624 0.04971 6217.39202 -2.338 0.019406 *
## pRep_D:wave1_4:Neg_Emo -0.22116 0.05673 6203.45904 -3.898 9.79e-05 ***
## pRep_I:wave1_2:Neg_Emo 0.04655 0.06839 6360.01762 0.681 0.496112
## pRep_I:wave1_3:Neg_Emo -0.13938 0.07514 6324.75585 -1.855 0.063641 .
## pRep_I:wave1_4:Neg_Emo -0.19009 0.08303 6296.21573 -2.290 0.022079 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1PEL.m4.r.w4 <- lmer(voteconfidence ~ (pRep_D + pRep_I) * (wave4_3 + wave4_2 + wave4_1) * Neg_Emo + (1 | pid),
data = d)
summary(PEL.m4.r.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pRep_D + pRep_I) * (wave4_3 + wave4_2 + wave4_1) *
## Neg_Emo + (1 | pid)
## Data: d
##
## REML criterion at convergence: 22058.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6457 -0.5055 0.0621 0.5514 3.6219
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.7198 0.8484
## Residual 0.5240 0.7239
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.889e+00 8.073e-02 7.357e+03 48.171 < 2e-16 ***
## pRep_D 6.179e-02 1.239e-01 7.077e+03 0.499 0.617998
## pRep_I -5.146e-01 1.808e-01 6.676e+03 -2.847 0.004428 **
## wave4_3 6.729e-03 9.211e-02 5.772e+03 0.073 0.941764
## wave4_2 3.337e-01 8.986e-02 5.877e+03 3.714 0.000206 ***
## wave4_1 -7.349e-01 9.440e-02 6.164e+03 -7.785 8.13e-15 ***
## Neg_Emo -1.223e-01 4.195e-02 6.248e+03 -2.915 0.003567 **
## pRep_D:wave4_3 -9.215e-02 1.406e-01 5.754e+03 -0.655 0.512383
## pRep_D:wave4_2 -3.839e-01 1.377e-01 5.857e+03 -2.787 0.005334 **
## pRep_D:wave4_1 7.263e-01 1.386e-01 6.111e+03 5.239 1.67e-07 ***
## pRep_I:wave4_3 6.695e-02 2.097e-01 5.790e+03 0.319 0.749515
## pRep_I:wave4_2 -3.361e-01 2.013e-01 5.862e+03 -1.670 0.095020 .
## pRep_I:wave4_1 2.561e-01 2.066e-01 6.212e+03 1.239 0.215270
## pRep_D:Neg_Emo -6.958e-02 4.898e-02 6.300e+03 -1.421 0.155457
## pRep_I:Neg_Emo -3.549e-03 7.023e-02 6.279e+03 -0.051 0.959702
## wave4_3:Neg_Emo -3.054e-02 5.123e-02 5.817e+03 -0.596 0.551133
## wave4_2:Neg_Emo -2.040e-01 5.009e-02 5.948e+03 -4.072 4.71e-05 ***
## wave4_1:Neg_Emo -8.214e-02 4.704e-02 6.185e+03 -1.746 0.080842 .
## pRep_D:wave4_3:Neg_Emo 1.049e-01 5.948e-02 5.803e+03 1.764 0.077796 .
## pRep_D:wave4_2:Neg_Emo 2.810e-01 5.797e-02 5.929e+03 4.848 1.28e-06 ***
## pRep_D:wave4_1:Neg_Emo 2.212e-01 5.673e-02 6.203e+03 3.898 9.79e-05 ***
## pRep_I:wave4_3:Neg_Emo 5.071e-02 8.705e-02 5.808e+03 0.583 0.560213
## pRep_I:wave4_2:Neg_Emo 2.366e-01 8.287e-02 5.911e+03 2.856 0.004309 **
## pRep_I:wave4_1:Neg_Emo 1.901e-01 8.303e-02 6.296e+03 2.290 0.022079 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 14. Full Model: Emotions & Trust in Gov’t
# fit model with 3-way-interaction
d$party_factor <- as.factor(as.character(d$party_factor))
PEL.m6 <- lmer(voteconfidence ~ trustGovt * Neg_Emo * wave * party_factor + (1|pid), data = d)
# select only mean, +1 SD, -1 SD for negative emotions
sjPlot::plot_model(PEL.m6, type = "eff", terms = c("trustGovt", "Neg_Emo [1.07,2.39,3.71]", "wave")) +
labs(x = "Trust in Federal Government",
y = "Perceived Election Legitimacy",
color = "Negative Emotions",
title = NULL) +
theme_bw()
# select only mean, +1 SD, -1 SD for negative emotions
sjPlot::plot_model(PEL.m6, type = "eff", terms = c("trustGovt", "Neg_Emo [1.07,2.39,3.71]", "party_factor")) +
labs(x = "Trust in Federal Government",
y = "Perceived Election Legitimacy",
color = "Negative Emotions",
title = NULL) +
theme_bw()
library(ggplot2)
library(dplyr)
library(ggplot2)
library(dplyr)
wave_party_labels = c("Democrat" = "Democrat",
"Independent" = "Independent",
"Republican" = "Republican",
`1` = "Wave 1",
`2` = "Wave 2",
`3` = "Wave 3",
`4` = "Wave 4")
# Slice z into categories
d <- d %>%
mutate(negemo_group = cut(Neg_Emo, breaks = quantile(Neg_Emo, probs = c(0, 0.33, 0.66, 1), na.rm = TRUE),
include.lowest = TRUE, labels = c("Low", "Medium", "High")))
#paletteer::paletteer_d("lisa::OskarSchlemmer")
#paletteer::paletteer_d("rcartocolor::Temps")
#paletteer::paletteer_d("khroma::BuRd")
ggplot(d[!is.na(d$party_factor),], aes(x = trustGovt, y = voteconfidence, color = negemo_group)) +
geom_jitter(height = .3, width = .3, alpha = 0.3, size = .2) +
geom_smooth(method = "lm", se = FALSE, size = .5, fullrange = T) +
labs(x = "Trust in Federal Government",
y = "Perceived Election Legitimacy",
title = "Perceived Election Legitimacy: Raw Data") +
scale_color_manual("Negative
Emotion", values = c("#009392FF","#E9E29CFF","#B2182BFF")) +
facet_grid(wave ~ party_factor, labeller = as_labeller(wave_party_labels)) +
theme_minimal()
library(ggeffects)
PEL.plot <- predict_response(PEL.m6, terms = c("trustGovt", "Neg_Emo", "party_factor", "wave"))
plot(PEL.plot) +
labs(x = "Trust in Federal Government",
y = "Perceived Election Legitimacy",
color = "Negative
Emotions",
title = "Perceived Election Legitimacy: Model Predicted Relationships") +
theme_bw()
Models
PEL.m5 <- lmer(voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) * (Pos_Emo + Neg_Emo) * trustGovt + (1 | pid),
data = d)
summary(PEL.m5)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: voteconfidence ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad +
## wave.cub) * (Pos_Emo + Neg_Emo) * trustGovt + (1 | pid)
## Data: d
##
## REML criterion at convergence: 21190.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7264 -0.4995 0.0414 0.5455 4.2060
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6146 0.7840
## Residual 0.4854 0.6967
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.271e+00 7.116e-02 7.824e+03 45.966
## pDem_Rep -3.731e-01 1.129e-01 7.887e+03 -3.305
## pParty_Ind -1.138e-01 1.836e-01 7.422e+03 -0.620
## wave.lin 5.885e-01 1.626e-01 6.220e+03 3.619
## wave.quad -6.129e-02 2.345e-01 5.947e+03 -0.261
## wave.cub 1.023e-02 1.380e-01 5.950e+03 0.074
## Pos_Emo 1.370e-01 1.708e-02 7.414e+03 8.022
## Neg_Emo -6.382e-02 1.839e-02 7.626e+03 -3.470
## trustGovt 2.664e-01 4.880e-02 7.301e+03 5.458
## pDem_Rep:wave.lin 9.292e-02 2.374e-01 6.124e+03 0.391
## pDem_Rep:wave.quad 2.268e-01 3.505e-01 5.870e+03 0.647
## pDem_Rep:wave.cub -4.858e-01 2.107e-01 5.793e+03 -2.306
## pParty_Ind:wave.lin 3.187e-01 4.432e-01 6.258e+03 0.719
## pParty_Ind:wave.quad -4.529e-01 6.376e-01 5.995e+03 -0.710
## pParty_Ind:wave.cub 1.567e-01 3.735e-01 6.016e+03 0.420
## pDem_Rep:Pos_Emo 5.288e-02 2.477e-02 7.484e+03 2.135
## pDem_Rep:Neg_Emo -2.159e-02 2.817e-02 7.680e+03 -0.767
## pParty_Ind:Pos_Emo -3.176e-02 4.545e-02 7.174e+03 -0.699
## pParty_Ind:Neg_Emo -3.347e-02 4.835e-02 7.431e+03 -0.692
## wave.lin:Pos_Emo -4.679e-02 3.975e-02 6.066e+03 -1.177
## wave.lin:Neg_Emo -8.999e-02 4.133e-02 6.298e+03 -2.177
## wave.quad:Pos_Emo 1.779e-01 5.739e-02 5.927e+03 3.099
## wave.quad:Neg_Emo -1.055e-01 5.979e-02 5.888e+03 -1.764
## wave.cub:Pos_Emo -2.892e-02 3.353e-02 5.960e+03 -0.863
## wave.cub:Neg_Emo 1.306e-02 3.615e-02 5.901e+03 0.361
## pDem_Rep:trustGovt -1.506e-02 8.289e-02 7.340e+03 -0.182
## pParty_Ind:trustGovt 2.515e-01 1.256e-01 7.145e+03 2.003
## wave.lin:trustGovt 3.253e-02 1.186e-01 6.510e+03 0.274
## wave.quad:trustGovt -1.195e-01 1.682e-01 5.925e+03 -0.710
## wave.cub:trustGovt 8.201e-02 1.006e-01 5.916e+03 0.815
## Pos_Emo:trustGovt -1.170e-02 1.181e-02 7.096e+03 -0.990
## Neg_Emo:trustGovt -5.790e-03 1.219e-02 7.323e+03 -0.475
## pDem_Rep:wave.lin:Pos_Emo 8.835e-02 5.445e-02 6.173e+03 1.623
## pDem_Rep:wave.lin:Neg_Emo 9.262e-02 6.117e-02 6.137e+03 1.514
## pDem_Rep:wave.quad:Pos_Emo 1.736e-01 8.105e-02 5.935e+03 2.142
## pDem_Rep:wave.quad:Neg_Emo -1.237e-01 8.918e-02 5.878e+03 -1.387
## pDem_Rep:wave.cub:Pos_Emo 5.261e-02 4.892e-02 5.846e+03 1.075
## pDem_Rep:wave.cub:Neg_Emo 5.405e-02 5.266e-02 5.767e+03 1.026
## pParty_Ind:wave.lin:Pos_Emo 1.421e-01 1.097e-01 6.063e+03 1.295
## pParty_Ind:wave.lin:Neg_Emo -2.704e-01 1.126e-01 6.366e+03 -2.401
## pParty_Ind:wave.quad:Pos_Emo 2.475e-01 1.583e-01 5.967e+03 1.564
## pParty_Ind:wave.quad:Neg_Emo -2.814e-02 1.623e-01 5.901e+03 -0.173
## pParty_Ind:wave.cub:Pos_Emo 2.532e-02 9.158e-02 6.009e+03 0.276
## pParty_Ind:wave.cub:Neg_Emo -6.311e-02 9.887e-02 5.959e+03 -0.638
## pDem_Rep:wave.lin:trustGovt 5.801e-02 1.844e-01 6.175e+03 0.315
## pDem_Rep:wave.quad:trustGovt -2.886e-01 2.780e-01 5.933e+03 -1.038
## pDem_Rep:wave.cub:trustGovt 8.723e-02 1.705e-01 5.842e+03 0.512
## pParty_Ind:wave.lin:trustGovt 9.670e-01 3.165e-01 6.564e+03 3.055
## pParty_Ind:wave.quad:trustGovt -2.742e-01 4.461e-01 5.955e+03 -0.615
## pParty_Ind:wave.cub:trustGovt 4.416e-02 2.655e-01 5.992e+03 0.166
## pDem_Rep:Pos_Emo:trustGovt 7.290e-03 1.811e-02 7.179e+03 0.402
## pDem_Rep:Neg_Emo:trustGovt 2.274e-02 2.042e-02 7.334e+03 1.114
## pParty_Ind:Pos_Emo:trustGovt -2.471e-02 3.150e-02 6.991e+03 -0.785
## pParty_Ind:Neg_Emo:trustGovt -7.836e-02 3.149e-02 7.205e+03 -2.489
## wave.lin:Pos_Emo:trustGovt -1.763e-02 2.910e-02 6.304e+03 -0.606
## wave.lin:Neg_Emo:trustGovt -5.105e-02 2.877e-02 6.500e+03 -1.775
## wave.quad:Pos_Emo:trustGovt 1.654e-03 4.138e-02 5.922e+03 0.040
## wave.quad:Neg_Emo:trustGovt -3.954e-02 4.138e-02 5.896e+03 -0.956
## wave.cub:Pos_Emo:trustGovt 3.488e-02 2.433e-02 5.949e+03 1.434
## wave.cub:Neg_Emo:trustGovt -3.801e-02 2.517e-02 5.865e+03 -1.510
## pDem_Rep:wave.lin:Pos_Emo:trustGovt -5.123e-02 4.089e-02 6.220e+03 -1.253
## pDem_Rep:wave.lin:Neg_Emo:trustGovt -1.003e-01 4.679e-02 6.166e+03 -2.143
## pDem_Rep:wave.quad:Pos_Emo:trustGovt 1.551e-03 6.216e-02 5.985e+03 0.025
## pDem_Rep:wave.quad:Neg_Emo:trustGovt 2.105e-02 6.911e-02 5.960e+03 0.305
## pDem_Rep:wave.cub:Pos_Emo:trustGovt 3.476e-05 3.847e-02 5.900e+03 0.001
## pDem_Rep:wave.cub:Neg_Emo:trustGovt -2.730e-02 4.101e-02 5.820e+03 -0.666
## pParty_Ind:wave.lin:Pos_Emo:trustGovt -2.237e-01 7.969e-02 6.317e+03 -2.807
## pParty_Ind:wave.lin:Neg_Emo:trustGovt -1.892e-01 7.616e-02 6.583e+03 -2.484
## pParty_Ind:wave.quad:Pos_Emo:trustGovt 4.627e-02 1.122e-01 5.929e+03 0.412
## pParty_Ind:wave.quad:Neg_Emo:trustGovt -2.161e-02 1.092e-01 5.903e+03 -0.198
## pParty_Ind:wave.cub:Pos_Emo:trustGovt 3.292e-02 6.531e-02 6.002e+03 0.504
## pParty_Ind:wave.cub:Neg_Emo:trustGovt -1.037e-02 6.710e-02 5.921e+03 -0.155
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## pDem_Rep 0.000953 ***
## pParty_Ind 0.535430
## wave.lin 0.000298 ***
## wave.quad 0.793804
## wave.cub 0.940942
## Pos_Emo 1.20e-15 ***
## Neg_Emo 0.000523 ***
## trustGovt 4.97e-08 ***
## pDem_Rep:wave.lin 0.695532
## pDem_Rep:wave.quad 0.517676
## pDem_Rep:wave.cub 0.021162 *
## pParty_Ind:wave.lin 0.472156
## pParty_Ind:wave.quad 0.477555
## pParty_Ind:wave.cub 0.674790
## pDem_Rep:Pos_Emo 0.032803 *
## pDem_Rep:Neg_Emo 0.443350
## pParty_Ind:Pos_Emo 0.484722
## pParty_Ind:Neg_Emo 0.488737
## wave.lin:Pos_Emo 0.239208
## wave.lin:Neg_Emo 0.029498 *
## wave.quad:Pos_Emo 0.001948 **
## wave.quad:Neg_Emo 0.077856 .
## wave.cub:Pos_Emo 0.388361
## wave.cub:Neg_Emo 0.717907
## pDem_Rep:trustGovt 0.855860
## pParty_Ind:trustGovt 0.045245 *
## wave.lin:trustGovt 0.783768
## wave.quad:trustGovt 0.477552
## wave.cub:trustGovt 0.415166
## Pos_Emo:trustGovt 0.322017
## Neg_Emo:trustGovt 0.634697
## pDem_Rep:wave.lin:Pos_Emo 0.104734
## pDem_Rep:wave.lin:Neg_Emo 0.130030
## pDem_Rep:wave.quad:Pos_Emo 0.032253 *
## pDem_Rep:wave.quad:Neg_Emo 0.165425
## pDem_Rep:wave.cub:Pos_Emo 0.282250
## pDem_Rep:wave.cub:Neg_Emo 0.304822
## pParty_Ind:wave.lin:Pos_Emo 0.195413
## pParty_Ind:wave.lin:Neg_Emo 0.016388 *
## pParty_Ind:wave.quad:Pos_Emo 0.117846
## pParty_Ind:wave.quad:Neg_Emo 0.862343
## pParty_Ind:wave.cub:Pos_Emo 0.782225
## pParty_Ind:wave.cub:Neg_Emo 0.523298
## pDem_Rep:wave.lin:trustGovt 0.753060
## pDem_Rep:wave.quad:trustGovt 0.299152
## pDem_Rep:wave.cub:trustGovt 0.608922
## pParty_Ind:wave.lin:trustGovt 0.002261 **
## pParty_Ind:wave.quad:trustGovt 0.538803
## pParty_Ind:wave.cub:trustGovt 0.867904
## pDem_Rep:Pos_Emo:trustGovt 0.687341
## pDem_Rep:Neg_Emo:trustGovt 0.265466
## pParty_Ind:Pos_Emo:trustGovt 0.432725
## pParty_Ind:Neg_Emo:trustGovt 0.012834 *
## wave.lin:Pos_Emo:trustGovt 0.544660
## wave.lin:Neg_Emo:trustGovt 0.075991 .
## wave.quad:Pos_Emo:trustGovt 0.968120
## wave.quad:Neg_Emo:trustGovt 0.339318
## wave.cub:Pos_Emo:trustGovt 0.151728
## wave.cub:Neg_Emo:trustGovt 0.131022
## pDem_Rep:wave.lin:Pos_Emo:trustGovt 0.210288
## pDem_Rep:wave.lin:Neg_Emo:trustGovt 0.032165 *
## pDem_Rep:wave.quad:Pos_Emo:trustGovt 0.980093
## pDem_Rep:wave.quad:Neg_Emo:trustGovt 0.760651
## pDem_Rep:wave.cub:Pos_Emo:trustGovt 0.999279
## pDem_Rep:wave.cub:Neg_Emo:trustGovt 0.505691
## pParty_Ind:wave.lin:Pos_Emo:trustGovt 0.005009 **
## pParty_Ind:wave.lin:Neg_Emo:trustGovt 0.013028 *
## pParty_Ind:wave.quad:Pos_Emo:trustGovt 0.680071
## pParty_Ind:wave.quad:Neg_Emo:trustGovt 0.843149
## pParty_Ind:wave.cub:Pos_Emo:trustGovt 0.614255
## pParty_Ind:wave.cub:Neg_Emo:trustGovt 0.877194
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1misc. other plots
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = voteconf_natl,
fill = party_factor)) +
geom_bar(stat = "summary",
fun = "mean",
position = position_dodge(.9)) +
stat_summary(geom = "errorbar",position = position_dodge(.9), color = "black", width = .1) +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy (National)") +
coord_cartesian(ylim = c(1,5)) 
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = voteconf_natl,
color = wave,
group = 1)) +
stat_summary(geom = "path", fun = "mean", color = "black", linetype = "dashed") +
stat_summary(geom = "errorbar",position = position_dodge(.9), color = "black", width = .1) +
stat_summary(geom = "point", fun = "mean", position = position_dodge(.9)) +
facet_wrap(~party_factor) +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy (National)") +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1))
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = voteconf_self,
fill = party_factor)) +
geom_bar(stat = "summary",
fun = "mean",
position = position_dodge(.9)) +
stat_summary(geom = "errorbar",position = position_dodge(.9), color = "black", width = .1) +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy (Own Vote)") +
coord_cartesian(ylim = c(1,5)) 
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = voteconf_self,
color = wave,
group = 1)) +
stat_summary(geom = "path", fun = "mean", color = "black", linetype = "dashed") +
stat_summary(geom = "errorbar",position = position_dodge(.9), color = "black", width = .1) +
stat_summary(geom = "point", fun = "mean", position = position_dodge(.9)) +
facet_wrap(~party_factor) +
labs(x = "Participant Party ID",
y = "Perceived Election Legitimacy (Own Vote)") +
coord_cartesian(ylim = c(1,5)) +
scale_y_continuous(breaks = seq(1,5,1))
DV: Trust in gov’t
ggplot(d, aes(x=trustGovt)) +
geom_density(fill="#69b3a2", color="#e9ecef", alpha=0.9) +
theme_bw() +
labs(x = "Trust in Federal Government")
ggplot(d[!is.na(d$party_factor),], aes(x=trustGovt, fill = party_factor)) +
geom_density(color="black", alpha=0.5, position = 'identity') +
theme_bw() +
facet_grid(wave~., labeller = as_labeller(wave_label)) +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
labs(x = "Trust in Federal Government")
#ggplot(d[!is.na(d$party_factor),],
# aes(x = party_factor,
# y = trustGovt,
# fill = party_factor,
# color = party_factor)) +
# geom_jitter(height = .3, width =.3, alpha=0.4, size = .5, show.legend = F ) +
# stat_summary(geom = "errorbar", color = "black", width = .1, show.legend = F) +
# stat_summary( geom = "point", fun = "mean", color = "black", size = 1 , show.legend = F) +
# theme_bw() +
# scale_fill_manual(values = c("#1696d2","grey","#db2b27")) +
# scale_color_manual(values = c("#1696d2","grey","#db2b27")) +
# labs(x = "Participant Party ID",
# y = "Trust in Federal Government")1. Trust over time
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = trustGovt,
fill = party_factor)) +
geom_jitter(aes(x = wave,
y = trustGovt,
color = party_factor),
position = position_jitterdodge(jitter.width = NULL,
jitter.height = .2,
dodge.width = 0.7),
alpha=0.4, size = .2, show.legend = F) +
geom_bar(stat = "summary",
fun = "mean",
position = position_dodge(),
color = "black") +
stat_summary(geom = "errorbar",
position = position_dodge(.9),
color = "black",
width = .1) +
labs(x = "Wave",
y = "Trust in Federal Government") +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
scale_color_manual("Participant Party ID",
values = c("#1696d2","black","#db2b27")) +
theme_bw()+
coord_cartesian(ylim = c(-2,2))
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = trustGovt,
color = wave,
group = 1)) +
geom_jitter(size = .2,
height = .2,
width = .2,
alpha = .3,
show.legend = F) +
stat_summary(geom = "path",
fun = "mean",
color = "black",
linetype = "dashed",
show.legend = F) +
stat_summary(geom = "errorbar",
position = position_dodge(.9),
color = "black",
width = .1,
show.legend = F) +
stat_summary(geom = "point",
fun = "mean",
position = position_dodge(.9),
show.legend = F) +
facet_wrap(~party_factor) +
labs(x = "",
y = "Trust in Federal Government") +
scale_y_continuous(breaks = seq(-2,2, .5)) +
scale_x_discrete(labels = c("Wave 1", "Wave 2", "Wave 3", "Wave 4")) +
coord_cartesian(ylim = c(-2,2)) +
theme_bw()
Summary
Trust in the federal government is overall negative (b = -0.63, p < .001), and it decreases over time (b = -0.48, p < .001). Collapsing across time, Republicans express less governmental trust than Democrats (b = -0.22, p < .001), though this interacts with linear time (b = 1.68, p < .001), such that the effect of time is positive for Republicans (b = 0.39, p < .001) and negative for Democrats (b = -1.30, p < .001).
Democrats’ governmental trust holds steady from wave 1 to wave 2 (p = .93), but decreases from wave 1 to wave 3 (b = -0.74, p < .001) and decreases sharply from wave 1 to wave 4 (b = -1.25, p < .001). This makes sense given the timing of the surveys; the Biden administration was still in office at wave 2 (Nov. 2024), with wave 4 collected around the two month mark for the Trump administration (March 2025).
For participants high in governmental trust, the effect of party ID is nonsignificant (p = .22), as are overall PEL (b = 3.67, p < .001); in fact, PEL increases slightly over time for high trusters (b = 0.19, p < .001).
Models
GovT.m1 <- lmer(trustGovt ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(GovT.m1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: trustGovt ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad +
## wave.cub) + (1 | pid)
## Data: d
##
## REML criterion at convergence: 20021.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6396 -0.5123 -0.0278 0.5300 4.2338
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6351 0.7969
## Residual 0.4098 0.6401
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -6.315e-01 1.998e-02 3.300e+03 -31.614 < 2e-16 ***
## pDem_Rep -2.222e-01 3.441e-02 4.069e+03 -6.458 1.19e-10 ***
## pParty_Ind -2.456e-01 4.256e-02 7.028e+03 -5.771 8.20e-09 ***
## wave.lin -4.888e-01 2.502e-02 5.862e+03 -19.535 < 2e-16 ***
## wave.quad 1.179e-01 3.735e-02 5.610e+03 3.158 0.00160 **
## wave.cub -8.254e-02 2.293e-02 5.535e+03 -3.601 0.00032 ***
## pDem_Rep:wave.lin 1.682e+00 4.403e-02 5.784e+03 38.198 < 2e-16 ***
## pDem_Rep:wave.quad -7.829e-01 6.537e-02 5.589e+03 -11.977 < 2e-16 ***
## pDem_Rep:wave.cub 2.844e-02 3.949e-02 5.514e+03 0.720 0.47143
## pParty_Ind:wave.lin -1.005e-01 6.538e-02 5.938e+03 -1.538 0.12418
## pParty_Ind:wave.quad 2.231e-02 9.814e-02 5.686e+03 0.227 0.82015
## pParty_Ind:wave.cub -7.588e-03 6.048e-02 5.600e+03 -0.125 0.90016
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav.ln wav.qd wav.cb pDm_Rp:wv.l
## pDem_Rep 0.068
## pParty_Ind 0.459 -0.038
## wave.lin 0.167 -0.014 0.116
## wave.quad -0.005 -0.010 0.033 -0.212
## wave.cub -0.058 0.010 -0.045 -0.067 0.161
## pDm_Rp:wv.l 0.008 0.150 0.007 0.061 -0.005 -0.008
## pDm_Rp:wv.q -0.008 -0.043 0.001 -0.008 0.059 0.008 -0.208
## pDm_Rp:wv.c -0.003 -0.052 -0.008 -0.008 0.007 0.058 -0.111
## pPrty_Ind:wv.l 0.090 -0.013 0.181 0.568 -0.122 -0.018 -0.037
## pPrty_Ind:wv.q 0.018 0.004 0.014 -0.118 0.574 0.094 0.005
## pPrty_Ind:wv.c -0.030 0.004 -0.065 -0.016 0.095 0.590 0.005
## pDm_Rp:wv.q pDm_Rp:wv.c pPrty_Ind:wv.l pPrty_Ind:wv.q
## pDem_Rep
## pParty_Ind
## wave.lin
## wave.quad
## wave.cub
## pDm_Rp:wv.l
## pDm_Rp:wv.q
## pDm_Rp:wv.c 0.157
## pPrty_Ind:wv.l 0.002 0.005
## pPrty_Ind:wv.q -0.036 -0.004 -0.209
## pPrty_Ind:wv.c -0.003 -0.031 -0.057 0.161Simple-effects models
GovT.m1.d <- lmer(trustGovt ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(GovT.m1.d)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: trustGovt ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 20021.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6396 -0.5123 -0.0278 0.5300 4.2338
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6351 0.7969
## Residual 0.4098 0.6401
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -4.385e-01 2.390e-02 3.290e+03 -18.345 < 2e-16 ***
## pDem_R -2.222e-01 3.441e-02 4.069e+03 -6.458 1.19e-10 ***
## pDem_I -3.567e-01 4.530e-02 6.652e+03 -7.875 3.95e-15 ***
## wave.lin -1.296e+00 2.937e-02 5.788e+03 -44.126 < 2e-16 ***
## wave.quad 5.019e-01 4.370e-02 5.590e+03 11.487 < 2e-16 ***
## wave.cub -9.424e-02 2.644e-02 5.507e+03 -3.564 0.000368 ***
## pDem_R:wave.lin 1.682e+00 4.403e-02 5.784e+03 38.198 < 2e-16 ***
## pDem_R:wave.quad -7.829e-01 6.537e-02 5.589e+03 -11.977 < 2e-16 ***
## pDem_R:wave.cub 2.844e-02 3.949e-02 5.514e+03 0.720 0.471431
## pDem_I:wave.lin 7.403e-01 6.821e-02 5.924e+03 10.854 < 2e-16 ***
## pDem_I:wave.quad -3.691e-01 1.023e-01 5.678e+03 -3.607 0.000312 ***
## pDem_I:wave.cub 6.633e-03 6.302e-02 5.596e+03 0.105 0.916190
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wav.ln wav.qd wav.cb pDm_R:wv.l pDm_R:wv.q
## pDem_R -0.641
## pDem_I -0.415 0.344
## wave.lin 0.164 -0.114 -0.081
## wave.quad -0.035 0.021 0.023 -0.221
## wave.cub -0.063 0.045 0.033 -0.106 0.162
## pDm_R:wv.ln -0.105 0.150 0.064 -0.670 0.147 0.072
## pDm_R:wv.qd 0.024 -0.043 -0.015 0.147 -0.671 -0.108 -0.208
## pDm_R:wv.cb 0.040 -0.052 -0.027 0.072 -0.108 -0.672 -0.111 0.157
## pDm_I:wv.ln -0.056 0.036 0.178 -0.437 0.096 0.046 0.287 -0.065
## pDm_I:wv.qd 0.011 -0.010 0.010 0.095 -0.436 -0.071 -0.061 0.285
## pDm_I:wv.cb 0.023 -0.012 -0.066 0.047 -0.069 -0.429 -0.030 0.047
## pDm_R:wv.c pDm_I:wv.l pDm_I:wv.q
## pDem_R
## pDem_I
## wave.lin
## wave.quad
## wave.cub
## pDm_R:wv.ln
## pDm_R:wv.qd
## pDm_R:wv.cb
## pDm_I:wv.ln -0.030
## pDm_I:wv.qd 0.046 -0.211
## pDm_I:wv.cb 0.283 -0.061 0.161GovT.m1.d.wd <- lmer(trustGovt ~ (pDem_R + pDem_I) * wave + (1 | pid),
data = d)
summary(GovT.m1.d.wd)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: trustGovt ~ (pDem_R + pDem_I) * wave + (1 | pid)
## Data: d
##
## REML criterion at convergence: 20024.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6396 -0.5123 -0.0278 0.5300 4.2338
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6351 0.7969
## Residual 0.4098 0.6401
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 6.053e-02 2.755e-02 5.324e+03 2.197 0.0281 *
## pDem_R -8.603e-01 4.083e-02 6.325e+03 -21.069 < 2e-16 ***
## pDem_I -6.330e-01 5.493e-02 7.868e+03 -11.523 < 2e-16 ***
## wave2 -2.405e-03 2.728e-02 5.663e+03 -0.088 0.9298
## wave3 -7.447e-01 2.845e-02 5.741e+03 -26.179 < 2e-16 ***
## wave4 -1.249e+00 3.347e-02 5.785e+03 -37.322 < 2e-16 ***
## pDem_R:wave2 7.663e-03 4.105e-02 5.645e+03 0.187 0.8519
## pDem_R:wave3 8.770e-01 4.286e-02 5.727e+03 20.463 < 2e-16 ***
## pDem_R:wave4 1.668e+00 5.020e-02 5.777e+03 33.215 < 2e-16 ***
## pDem_I:wave2 -4.455e-03 6.397e-02 5.801e+03 -0.070 0.9445
## pDem_I:wave3 3.723e-01 6.739e-02 5.883e+03 5.526 3.42e-08 ***
## pDem_I:wave4 7.370e-01 7.686e-02 5.905e+03 9.589 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wave2 wave3 wave4 pD_R:2 pD_R:3 pD_R:4
## pDem_R -0.639
## pDem_I -0.437 0.329
## wave2 -0.433 0.292 0.228
## wave3 -0.420 0.284 0.222 0.465
## wave4 -0.358 0.243 0.188 0.396 0.401
## pDem_R:wav2 0.294 -0.464 -0.142 -0.669 -0.311 -0.266
## pDem_R:wav3 0.284 -0.449 -0.139 -0.311 -0.667 -0.268 0.475
## pDem_R:wav4 0.245 -0.389 -0.115 -0.267 -0.269 -0.670 0.406 0.410
## pDem_I:wav2 0.193 -0.132 -0.473 -0.436 -0.203 -0.173 0.284 0.131 0.115
## pDem_I:wav3 0.188 -0.127 -0.465 -0.200 -0.431 -0.171 0.130 0.281 0.114
## pDem_I:wav4 0.173 -0.117 -0.429 -0.176 -0.177 -0.443 0.114 0.114 0.291
## pD_I:2 pD_I:3
## pDem_R
## pDem_I
## wave2
## wave3
## wave4
## pDem_R:wav2
## pDem_R:wav3
## pDem_R:wav4
## pDem_I:wav2
## pDem_I:wav3 0.436
## pDem_I:wav4 0.383 0.392GovT.m1.r <- lmer(trustGovt ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(GovT.m1.r)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: trustGovt ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 20021.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6396 -0.5123 -0.0278 0.5300 4.2338
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6351 0.7969
## Residual 0.4098 0.6401
## Number of obs: 8000, groups: pid, 2601
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.66074 0.02648 3391.33915 -24.952 < 2e-16 ***
## pRep_D 0.22221 0.03441 4068.71132 6.458 1.19e-10 ***
## pRep_I -0.13454 0.04651 6581.00424 -2.893 0.00383 **
## wave.lin 0.38556 0.03270 5771.83637 11.790 < 2e-16 ***
## wave.quad -0.28096 0.04847 5573.44725 -5.796 7.15e-09 ***
## wave.cub -0.06580 0.02923 5504.05055 -2.251 0.02441 *
## pRep_D:wave.lin -1.68176 0.04403 5784.29140 -38.198 < 2e-16 ***
## pRep_D:wave.quad 0.78289 0.06537 5588.64888 11.977 < 2e-16 ***
## pRep_D:wave.cub -0.02844 0.03949 5514.08316 -0.720 0.47143
## pRep_I:wave.lin -0.94142 0.06976 5919.79256 -13.496 < 2e-16 ***
## pRep_I:wave.quad 0.41376 0.10454 5675.35128 3.958 7.65e-05 ***
## pRep_I:wave.cub -0.02181 0.06420 5588.64810 -0.340 0.73412
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pRep_D pRep_I wav.ln wav.qd wav.cb pRp_D:wv.l pRp_D:wv.q
## pRep_D -0.721
## pRep_I -0.463 0.405
## wave.lin 0.134 -0.099 -0.061
## wave.quad -0.051 0.040 0.030 -0.200
## wave.cub -0.043 0.030 0.015 -0.112 0.155
## pRp_D:wv.ln -0.100 0.150 0.049 -0.745 0.148 0.084
## pRp_D:wv.qd 0.035 -0.043 -0.017 0.147 -0.744 -0.115 -0.208
## pRp_D:wv.cb 0.032 -0.052 -0.012 0.084 -0.114 -0.743 -0.111 0.157
## pRp_I:wv.ln -0.066 0.059 0.175 -0.476 0.092 0.054 0.350 -0.068
## pRp_I:wv.qd 0.019 -0.017 0.006 0.095 -0.473 -0.073 -0.070 0.346
## pRp_I:wv.cb 0.024 -0.020 -0.061 0.053 -0.070 -0.462 -0.039 0.051
## pRp_D:wv.c pRp_I:wv.l pRp_I:wv.q
## pRep_D
## pRep_I
## wave.lin
## wave.quad
## wave.cub
## pRp_D:wv.ln
## pRp_D:wv.qd
## pRp_D:wv.cb
## pRp_I:wv.ln -0.040
## pRp_I:wv.qd 0.053 -0.206
## pRp_I:wv.cb 0.337 -0.064 0.159DV: Emotions
Positive Emotions
ggplot(d, aes(x=Pos_Emo)) +
geom_density(fill="#69b3a2", color="#e9ecef", alpha=0.9) +
theme_bw() +
labs(x = "Positive Emotions")
ggplot(d[!is.na(d$party_factor),],
aes(x = party_factor,
y = Pos_Emo,
fill = party_factor,
color = party_factor)) +
geom_jitter(height = .3, width =.3, alpha=0.4, size = .5, show.legend = F ) +
stat_summary(geom = "errorbar", color = "black", width = .1, show.legend = F) +
stat_summary( geom = "point", fun = "mean", color = "black", size = 1 , show.legend = F) +
theme_bw() +
scale_fill_manual(values = c("#1696d2","grey","#db2b27")) +
scale_color_manual(values = c("#1696d2","grey","#db2b27")) +
labs(x = "Participant Party ID",
y = "Positive Emotions")
Negative Emotions
ggplot(d, aes(x=Neg_Emo)) +
geom_density(fill="#69b3a2", color="#e9ecef", alpha=0.9) +
theme_bw() +
labs(x = "Negative Emotions")
ggplot(d[!is.na(d$party_factor),],
aes(x = party_factor,
y = Neg_Emo,
fill = party_factor,
color = party_factor)) +
geom_jitter(height = .3, width =.3, alpha=0.4, size = .5, show.legend = F ) +
stat_summary(geom = "errorbar", color = "black", width = .1, show.legend = F) +
stat_summary( geom = "point", fun = "mean", color = "black", size = 1 , show.legend = F) +
theme_bw() +
scale_fill_manual(values = c("#1696d2","grey","#db2b27")) +
scale_color_manual(values = c("#1696d2","grey","#db2b27")) +
labs(x = "Participant Party ID",
y = "Negative Emotions")
1. Emotions over time
Positive Emotions
ggplot(d[!is.na(d$party_factor),], aes(x=Pos_Emo, fill = party_factor)) +
geom_density(color="black", alpha=0.5, position = 'identity') +
theme_bw() +
facet_grid(wave~., labeller = as_labeller(wave_label)) +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
labs(x = "Positive Emotions")
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = Pos_Emo,
color = wave,
group = 1)) +
geom_jitter(size = .2,
height = .2,
width = .2,
alpha = .3,
show.legend = F) +
stat_summary(geom = "path",
fun = "mean",
color = "black",
linetype = "dashed",
show.legend = F) +
stat_summary(geom = "errorbar",
position = position_dodge(.9),
color = "black",
width = .1,
show.legend = F) +
stat_summary(geom = "point",
fun = "mean",
position = position_dodge(.9),
show.legend = F) +
facet_wrap(~party_factor) +
labs(x = "",
y = "Positive Emotions") +
scale_y_continuous(breaks = seq(1,5, .5)) +
scale_x_discrete(labels = c("Wave 1", "Wave 2", "Wave 3", "Wave 4")) +
coord_cartesian(ylim = c(1,5)) +
theme_bw()
Mean (and SD) for positive emotions by party over time
# Average PEL
kable(round(tapply(d$Pos_Emo, list(d$party_factor, d$wave), FUN = mean, na.rm = T),2))| 1 | 2 | 3 | 4 | |
|---|---|---|---|---|
| Democrat | 2.94 | 2.06 | 2.03 | 1.99 |
| Independent | 2.43 | 2.26 | 2.20 | 2.07 |
| Republican | 2.77 | 3.64 | 3.45 | 3.38 |
## 1 2 3 4
## Democrat 1.15 1.20 1.14 1.15
## Independent 1.12 1.18 1.10 0.98
## Republican 1.12 1.22 1.23 1.23Negative Emotions
ggplot(d[!is.na(d$party_factor),], aes(x=Neg_Emo, fill = party_factor)) +
geom_density(color="black", alpha=0.5, position = 'identity') +
theme_bw() +
facet_grid(wave~., labeller = as_labeller(wave_label)) +
scale_fill_manual("Participant Party ID",
values = c("#1696d2","grey","#db2b27")) +
labs(x = "Negative Emotions")
ggplot(d[!is.na(d$party_factor),],
aes(x = wave,
y = Neg_Emo,
color = wave,
group = 1)) +
geom_jitter(size = .2,
height = .2,
width = .2,
alpha = .3,
show.legend = F) +
stat_summary(geom = "path",
fun = "mean",
color = "black",
linetype = "dashed",
show.legend = F) +
stat_summary(geom = "errorbar",
position = position_dodge(.9),
color = "black",
width = .1,
show.legend = F) +
stat_summary(geom = "point",
fun = "mean",
position = position_dodge(.9),
show.legend = F) +
facet_wrap(~party_factor) +
labs(x = "",
y = "Negative Emotions") +
scale_y_continuous(breaks = seq(1,5, .5)) +
scale_x_discrete(labels = c("Wave 1", "Wave 2", "Wave 3", "Wave 4")) +
coord_cartesian(ylim = c(1,5)) +
theme_bw()
Mean (and SD) for negative emotions by party over time
# Average PEL
kable(round(tapply(d$Neg_Emo, list(d$party_factor, d$wave), FUN = mean, na.rm = T),2))| 1 | 2 | 3 | 4 | |
|---|---|---|---|---|
| Democrat | 2.29 | 3.21 | 3.09 | 3.40 |
| Independent | 2.19 | 2.20 | 2.18 | 2.57 |
| Republican | 2.29 | 1.53 | 1.55 | 1.63 |
## 1 2 3 4
## Democrat 1.11 1.38 1.27 1.34
## Independent 1.13 1.28 1.16 1.22
## Republican 1.16 0.88 0.84 0.88Summary
Positive emotions
At wave 1, positive and negative emotions Positive emotions decrease sharply from wave 1 to wave 2 for Democrats, and then continue to decrease slightly, while Republicans’ positive emotions increase sharply from wave 1 to wave 2, and then decrease slightly from wave 2 to wave 4.
In wave 1, Democrats have slightly higher positive emotions (M = 2.94) than Republicans (M = 2.77, b = 0.26, p < .001), while in wave 4, Republicans’ positive emotions (M = 3.38) are much higher than Dems’ (M = 1.99, b = 1.30, p < .001). For Republicans, positive emotions peak at wave 2 (M = 3.64), and fall slightly from wave 2 to wave 4 (b = -0.28, p < .001).
Negative emotions
Negative emotions increase sharply from wave 1 to wave 2 and then trend upward for Democrats, while Republicans’ negative emotions fall sharply from wave 1 to wave 2 and then trend upward.
At wave 1, Democrats and Republicans have the same level of negative emotions (M = 2.29), though the model predicted difference shows slightly higher negative emotions for Republicans than Democrats (b = 0.09, p = .048). Both Republicans’ (b = 0.11, p = .012) and Democrats’ (b = 0.19, p < .001) negative emotions slightly increase from wave 2 to wave 4.
Models
pos.m1 <- lmer(Pos_Emo ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(pos.m1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## Pos_Emo ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23693.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9321 -0.5731 -0.0615 0.5698 3.5196
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6525 0.8078
## Residual 0.7119 0.8437
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.625e+00 2.199e-02 3.306e+03 119.357 < 2e-16 ***
## pDem_Rep 9.802e-01 3.840e-02 3.638e+03 25.526 < 2e-16 ***
## pParty_Ind -4.484e-01 5.010e-02 6.137e+03 -8.950 < 2e-16 ***
## wave.lin -2.254e-01 3.239e-02 6.108e+03 -6.959 3.78e-12 ***
## wave.quad 4.337e-02 4.874e-02 5.813e+03 0.890 0.3737
## wave.cub 8.762e-03 2.992e-02 5.708e+03 0.293 0.7697
## pDem_Rep:wave.lin 1.171e+00 5.719e-02 6.040e+03 20.481 < 2e-16 ***
## pDem_Rep:wave.quad 1.829e+00 8.538e-02 5.790e+03 21.425 < 2e-16 ***
## pDem_Rep:wave.cub -7.728e-01 5.163e-02 5.685e+03 -14.967 < 2e-16 ***
## pParty_Ind:wave.lin -1.566e-01 8.444e-02 6.201e+03 -1.854 0.0637 .
## pParty_Ind:wave.quad -1.226e-02 1.279e-01 5.926e+03 -0.096 0.9236
## pParty_Ind:wave.cub 1.158e-01 7.877e-02 5.806e+03 1.470 0.1415
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav.ln wav.qd wav.cb pDm_Rp:wv.l
## pDem_Rep 0.066
## pParty_Ind 0.493 -0.037
## wave.lin 0.199 -0.008 0.130
## wave.quad -0.015 -0.009 0.024 -0.219
## wave.cub -0.062 0.008 -0.044 -0.070 0.174
## pDm_Rp:wv.l 0.009 0.181 0.004 0.062 -0.006 -0.008
## pDm_Rp:wv.q -0.009 -0.054 0.002 -0.008 0.058 0.009 -0.215
## pDm_Rp:wv.c -0.002 -0.058 -0.006 -0.008 0.008 0.057 -0.111
## pPrty_Ind:wv.l 0.111 -0.012 0.210 0.564 -0.125 -0.020 -0.037
## pPrty_Ind:wv.q 0.014 0.005 0.003 -0.123 0.573 0.104 0.005
## pPrty_Ind:wv.c -0.032 0.003 -0.067 -0.019 0.104 0.587 0.005
## pDm_Rp:wv.q pDm_Rp:wv.c pPrty_Ind:wv.l pPrty_Ind:wv.q
## pDem_Rep
## pParty_Ind
## wave.lin
## wave.quad
## wave.cub
## pDm_Rp:wv.l
## pDm_Rp:wv.q
## pDm_Rp:wv.c 0.167
## pPrty_Ind:wv.l 0.002 0.006
## pPrty_Ind:wv.q -0.036 -0.004 -0.217
## pPrty_Ind:wv.c -0.003 -0.031 -0.060 0.175neg.m1 <- lmer(Neg_Emo ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(neg.m1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## Neg_Emo ~ (pDem_Rep + pParty_Ind) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23241.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1641 -0.5706 -0.0447 0.5149 3.8782
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6478 0.8048
## Residual 0.6634 0.8145
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.36458 0.02166 3321.00620 109.153 < 2e-16 ***
## pDem_Rep -1.16763 0.03779 3693.71341 -30.900 < 2e-16 ***
## pParty_Ind -0.02822 0.04901 6261.59254 -0.576 0.5649
## wave.lin 0.21207 0.03131 6088.90351 6.774 1.37e-11 ***
## wave.quad -0.20504 0.04708 5804.89478 -4.355 1.35e-05 ***
## wave.cub -0.13379 0.02890 5703.58187 -4.630 3.73e-06 ***
## pDem_Rep:wave.lin -1.36050 0.05527 6022.63445 -24.615 < 2e-16 ***
## pDem_Rep:wave.quad -1.46862 0.08247 5782.64791 -17.808 < 2e-16 ***
## pDem_Rep:wave.cub 0.84957 0.04986 5680.89374 17.039 < 2e-16 ***
## pParty_Ind:wave.lin 0.12019 0.08163 6178.47528 1.472 0.1410
## pParty_Ind:wave.quad -0.27220 0.12353 5913.14854 -2.203 0.0276 *
## pParty_Ind:wave.cub -0.01614 0.07609 5796.49191 -0.212 0.8321
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav.ln wav.qd wav.cb pDm_Rp:wv.l
## pDem_Rep 0.066
## pParty_Ind 0.489 -0.037
## wave.lin 0.196 -0.009 0.129
## wave.quad -0.014 -0.009 0.025 -0.218
## wave.cub -0.061 0.008 -0.044 -0.071 0.174
## pDm_Rp:wv.l 0.009 0.178 0.004 0.062 -0.006 -0.008
## pDm_Rp:wv.q -0.009 -0.053 0.002 -0.008 0.058 0.009 -0.215
## pDm_Rp:wv.c -0.002 -0.057 -0.007 -0.008 0.008 0.057 -0.111
## pPrty_Ind:wv.l 0.109 -0.012 0.207 0.564 -0.125 -0.020 -0.037
## pPrty_Ind:wv.q 0.014 0.005 0.004 -0.122 0.573 0.103 0.005
## pPrty_Ind:wv.c -0.032 0.003 -0.066 -0.019 0.104 0.588 0.005
## pDm_Rp:wv.q pDm_Rp:wv.c pPrty_Ind:wv.l pPrty_Ind:wv.q
## pDem_Rep
## pParty_Ind
## wave.lin
## wave.quad
## wave.cub
## pDm_Rp:wv.l
## pDm_Rp:wv.q
## pDm_Rp:wv.c 0.167
## pPrty_Ind:wv.l 0.002 0.006
## pPrty_Ind:wv.q -0.036 -0.004 -0.216
## pPrty_Ind:wv.c -0.003 -0.031 -0.061 0.175Simple-effects models
# Pos Emo
pos.m1.w1 <- lmer(Pos_Emo ~ (pDem_Rep + pParty_Ind) * (wave1_2 + wave1_3 + wave1_4) + (1 | pid),
data = d)
summary(pos.m1.w1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pos_Emo ~ (pDem_Rep + pParty_Ind) * (wave1_2 + wave1_3 + wave1_4) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23696.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9321 -0.5731 -0.0615 0.5698 3.5196
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6525 0.8078
## Residual 0.7119 0.8437
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.72865 0.02637 6021.50920 103.489 < 2e-16 ***
## pDem_Rep -0.25605 0.04771 6617.02734 -5.366 8.30e-08 ***
## pParty_Ind -0.33807 0.06301 7966.22263 -5.365 8.31e-08 ***
## wave1_2 -0.04124 0.03020 5913.12951 -1.366 0.1720
## wave1_3 -0.14519 0.03192 6000.95633 -4.549 5.51e-06 ***
## wave1_4 -0.22980 0.03662 6091.10469 -6.275 3.73e-10 ***
## pDem_Rep:wave1_2 1.78711 0.05325 5845.08271 33.560 < 2e-16 ***
## pDem_Rep:wave1_3 1.60002 0.05571 5922.30084 28.722 < 2e-16 ***
## pDem_Rep:wave1_4 1.55776 0.06531 6041.08097 23.853 < 2e-16 ***
## pParty_Ind:wave1_2 -0.13215 0.07916 6062.14578 -1.669 0.0951 .
## pParty_Ind:wave1_3 -0.09461 0.08380 6126.39804 -1.129 0.2589
## pParty_Ind:wave1_4 -0.21451 0.09531 6192.91676 -2.251 0.0244 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav1_2 wav1_3 wav1_4 pD_R:1_2 pD_R:1_3
## pDem_Rep 0.088
## pParty_Ind 0.487 -0.047
## wave1_2 -0.478 -0.051 -0.265
## wave1_3 -0.456 -0.048 -0.259 0.436
## wave1_4 -0.404 -0.047 -0.238 0.381 0.383
## pDm_Rp:w1_2 -0.041 -0.515 0.033 0.063 0.034 0.029
## pDm_Rp:w1_3 -0.040 -0.492 0.030 0.034 0.065 0.029 0.469
## pDm_Rp:w1_4 -0.032 -0.425 0.030 0.031 0.030 0.063 0.401 0.399
## pPrty_I:1_2 -0.251 0.022 -0.514 0.569 0.234 0.205 -0.039 -0.022
## pPrty_I:1_3 -0.241 0.020 -0.495 0.234 0.577 0.208 -0.022 -0.039
## pPrty_I:1_4 -0.221 0.015 -0.453 0.205 0.208 0.555 -0.020 -0.020
## pD_R:1_4 pP_I:1_2 pP_I:1_3
## pDem_Rep
## pParty_Ind
## wave1_2
## wave1_3
## wave1_4
## pDm_Rp:w1_2
## pDm_Rp:w1_3
## pDm_Rp:w1_4
## pPrty_I:1_2 -0.017
## pPrty_I:1_3 -0.017 0.430
## pPrty_I:1_4 -0.037 0.378 0.377pos.m1.w4 <- lmer(Pos_Emo ~ (pDem_Rep + pParty_Ind) * (wave4_2 + wave4_3 + wave4_1) + (1 | pid),
data = d)
summary(pos.m1.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pos_Emo ~ (pDem_Rep + pParty_Ind) * (wave4_2 + wave4_3 + wave4_1) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23696.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9321 -0.5731 -0.0615 0.5698 3.5196
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6525 0.8078
## Residual 0.7119 0.8437
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.49885 0.03544 8009.08466 70.512 < 2e-16 ***
## pDem_Rep 1.30171 0.06240 8072.87315 20.861 < 2e-16 ***
## pParty_Ind -0.55258 0.08728 7658.65418 -6.331 2.57e-10 ***
## wave4_2 0.18856 0.03755 5868.49017 5.021 5.29e-07 ***
## wave4_3 0.08461 0.03828 5749.31788 2.210 0.02713 *
## wave4_1 0.22980 0.03662 6091.10470 6.275 3.73e-10 ***
## pDem_Rep:wave4_2 0.22935 0.06565 5843.35184 3.494 0.00048 ***
## pDem_Rep:wave4_3 0.04226 0.06681 5761.70318 0.633 0.52699
## pDem_Rep:wave4_1 -1.55776 0.06531 6041.08097 -23.853 < 2e-16 ***
## pParty_Ind:wave4_2 0.08235 0.09822 5948.22017 0.838 0.40181
## pParty_Ind:wave4_3 0.11990 0.10041 5830.88878 1.194 0.23248
## pParty_Ind:wave4_1 0.21451 0.09531 6192.91676 2.251 0.02444 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav4_2 wav4_3 wav4_1 pD_R:4_2 pD_R:4_3
## pDem_Rep 0.056
## pParty_Ind 0.531 -0.034
## wave4_2 -0.684 -0.035 -0.398
## wave4_3 -0.654 -0.033 -0.383 0.621
## wave4_1 -0.733 -0.030 -0.435 0.669 0.638
## pDm_Rp:w4_2 -0.041 -0.697 0.021 0.055 0.035 0.039
## pDm_Rp:w4_3 -0.040 -0.671 0.019 0.035 0.056 0.037 0.640
## pDm_Rp:w4_1 -0.041 -0.722 0.019 0.037 0.035 0.063 0.669 0.645
## pPrty_I:4_2 -0.377 0.027 -0.709 0.573 0.347 0.374 -0.032 -0.021
## pPrty_I:4_3 -0.359 0.024 -0.681 0.345 0.576 0.354 -0.021 -0.032
## pPrty_I:4_1 -0.409 0.028 -0.765 0.376 0.358 0.555 -0.021 -0.020
## pD_R:4_1 pP_I:4_2 pP_I:4_3
## pDem_Rep
## pParty_Ind
## wave4_2
## wave4_3
## wave4_1
## pDm_Rp:w4_2
## pDm_Rp:w4_3
## pDm_Rp:w4_1
## pPrty_I:4_2 -0.023
## pPrty_I:4_3 -0.021 0.616
## pPrty_I:4_1 -0.037 0.666 0.634pos.m1.d <- lmer(Pos_Emo ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(pos.m1.d)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pos_Emo ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23693.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9321 -0.5731 -0.0615 0.5698 3.5196
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6525 0.8078
## Residual 0.7119 0.8437
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.28397 0.02626 3179.81206 86.974 < 2e-16 ***
## pDem_R 0.98018 0.03840 3638.26578 25.526 < 2e-16 ***
## pDem_I 0.04170 0.05298 5809.01779 0.787 0.431269
## wave.lin -0.75891 0.03818 6043.04511 -19.879 < 2e-16 ***
## wave.quad -0.86723 0.05712 5792.05813 -15.183 < 2e-16 ***
## wave.cub 0.35654 0.03460 5676.90607 10.305 < 2e-16 ***
## pDem_R:wave.lin 1.17137 0.05719 6039.72768 20.481 < 2e-16 ***
## pDem_R:wave.quad 1.82937 0.08538 5790.30563 21.425 < 2e-16 ***
## pDem_R:wave.cub -0.77277 0.05163 5685.03931 -14.967 < 2e-16 ***
## pDem_I:wave.lin 0.42910 0.08815 6187.13708 4.868 1.16e-06 ***
## pDem_I:wave.quad 0.90243 0.13335 5913.28333 6.767 1.44e-11 ***
## pDem_I:wave.cub -0.27055 0.08212 5799.61662 -3.294 0.000992 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wav.ln wav.qd wav.cb pDm_R:wv.l pDm_R:wv.q
## pDem_R -0.652
## pDem_I -0.422 0.327
## wave.lin 0.194 -0.133 -0.093
## wave.quad -0.046 0.029 0.027 -0.228
## wave.cub -0.070 0.048 0.034 -0.106 0.171
## pDm_R:wv.ln -0.127 0.181 0.069 -0.670 0.152 0.072
## pDm_R:wv.qd 0.031 -0.054 -0.018 0.152 -0.671 -0.114 -0.215
## pDm_R:wv.cb 0.045 -0.058 -0.027 0.072 -0.114 -0.673 -0.111 0.167
## pDm_I:wv.ln -0.071 0.047 0.208 -0.439 0.100 0.046 0.289 -0.067
## pDm_I:wv.qd 0.016 -0.012 -0.001 0.098 -0.436 -0.075 -0.064 0.286
## pDm_I:wv.cb 0.027 -0.016 -0.068 0.046 -0.074 -0.430 -0.030 0.049
## pDm_R:wv.c pDm_I:wv.l pDm_I:wv.q
## pDem_R
## pDem_I
## wave.lin
## wave.quad
## wave.cub
## pDm_R:wv.ln
## pDm_R:wv.qd
## pDm_R:wv.cb
## pDm_I:wv.ln -0.030
## pDm_I:wv.qd 0.049 -0.219
## pDm_I:wv.cb 0.284 -0.064 0.176## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pos_Emo ~ (pDem_R + pDem_I) * wave + (1 | pid)
## Data: d
##
## REML criterion at convergence: 23696.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9321 -0.5731 -0.0615 0.5698 3.5196
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6525 0.8078
## Residual 0.7119 0.8437
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.96936 0.03176 5994.51384 93.492 < 2e-16 ***
## pDem_R -0.25605 0.04771 6617.02735 -5.366 8.30e-08 ***
## pDem_I -0.46609 0.06632 7858.53176 -7.028 2.28e-12 ***
## wave2 -0.89075 0.03542 5862.40050 -25.149 < 2e-16 ***
## wave3 -0.91367 0.03700 5940.86679 -24.694 < 2e-16 ***
## wave4 -0.93718 0.04355 6049.15451 -21.521 < 2e-16 ***
## pDem_R:wave2 1.78711 0.05325 5845.08271 33.560 < 2e-16 ***
## pDem_R:wave3 1.60002 0.05571 5922.30083 28.722 < 2e-16 ***
## pDem_R:wave4 1.55776 0.06531 6041.08097 23.853 < 2e-16 ***
## pDem_I:wave2 0.76140 0.08254 6047.94602 9.225 < 2e-16 ***
## pDem_I:wave3 0.70540 0.08727 6113.07904 8.083 7.57e-16 ***
## pDem_I:wave4 0.56437 0.09959 6181.34806 5.667 1.52e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wave2 wave3 wave4 pD_R:2 pD_R:3 pD_R:4
## pDem_R -0.647
## pDem_I -0.444 0.315
## wave2 -0.491 0.327 0.244
## wave3 -0.471 0.314 0.235 0.459
## wave4 -0.401 0.269 0.199 0.390 0.389
## pDem_R:wav2 0.331 -0.515 -0.154 -0.669 -0.307 -0.262
## pDem_R:wav3 0.317 -0.492 -0.149 -0.307 -0.667 -0.260 0.469
## pDem_R:wav4 0.272 -0.425 -0.124 -0.263 -0.262 -0.670 0.401 0.399
## pDem_I:wav2 0.217 -0.145 -0.510 -0.437 -0.201 -0.172 0.285 0.130 0.113
## pDem_I:wav3 0.209 -0.138 -0.492 -0.198 -0.432 -0.167 0.128 0.282 0.111
## pDem_I:wav4 0.190 -0.125 -0.447 -0.174 -0.173 -0.444 0.113 0.112 0.292
## pD_I:2 pD_I:3
## pDem_R
## pDem_I
## wave2
## wave3
## wave4
## pDem_R:wav2
## pDem_R:wav3
## pDem_R:wav4
## pDem_I:wav2
## pDem_I:wav3 0.431
## pDem_I:wav4 0.378 0.377pos.m1.r <- lmer(Pos_Emo ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(pos.m1.r)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pos_Emo ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23693.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9321 -0.5731 -0.0615 0.5698 3.5196
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6525 0.8078
## Residual 0.7119 0.8437
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.26415 0.02913 3221.80044 112.059 < 2e-16 ***
## pRep_D -0.98018 0.03840 3638.26578 -25.526 < 2e-16 ***
## pRep_I -0.93848 0.05432 5738.56272 -17.278 < 2e-16 ***
## wave.lin 0.41246 0.04247 6019.70136 9.711 < 2e-16 ***
## wave.quad 0.96214 0.06331 5769.62926 15.197 < 2e-16 ***
## wave.cub -0.41624 0.03820 5667.45798 -10.896 < 2e-16 ***
## pRep_D:wave.lin -1.17137 0.05719 6039.72767 -20.481 < 2e-16 ***
## pRep_D:wave.quad -1.82937 0.08538 5790.30563 -21.425 < 2e-16 ***
## pRep_D:wave.cub 0.77277 0.05163 5685.03930 14.967 < 2e-16 ***
## pRep_I:wave.lin -0.74228 0.09014 6181.55388 -8.235 < 2e-16 ***
## pRep_I:wave.quad -0.92694 0.13623 5911.32008 -6.804 1.12e-11 ***
## pRep_I:wave.cub 0.50222 0.08366 5788.87577 6.003 2.06e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pRep_D pRep_I wav.ln wav.qd wav.cb pRp_D:wv.l pRp_D:wv.q
## pRep_D -0.730
## pRep_I -0.466 0.388
## wave.lin 0.166 -0.123 -0.077
## wave.quad -0.062 0.047 0.033 -0.206
## wave.cub -0.048 0.035 0.019 -0.113 0.165
## pRp_D:wv.ln -0.124 0.181 0.060 -0.745 0.153 0.085
## pRp_D:wv.qd 0.043 -0.054 -0.021 0.152 -0.743 -0.122 -0.215
## pRp_D:wv.cb 0.036 -0.058 -0.015 0.085 -0.122 -0.742 -0.111 0.167
## pRp_I:wv.ln -0.081 0.068 0.204 -0.477 0.096 0.055 0.352 -0.070
## pRp_I:wv.qd 0.025 -0.022 -0.006 0.098 -0.473 -0.078 -0.072 0.347
## pRp_I:wv.cb 0.026 -0.021 -0.064 0.054 -0.075 -0.463 -0.039 0.055
## pRp_D:wv.c pRp_I:wv.l pRp_I:wv.q
## pRep_D
## pRep_I
## wave.lin
## wave.quad
## wave.cub
## pRp_D:wv.ln
## pRp_D:wv.qd
## pRp_D:wv.cb
## pRp_I:wv.ln -0.041
## pRp_I:wv.qd 0.056 -0.214
## pRp_I:wv.cb 0.338 -0.067 0.173pos.m1.r.w4 <- lmer(Pos_Emo ~ (pRep_D + pRep_I) * (wave4_2 + wave4_3 + wave4_1) + (1 | pid),
data = d)
summary(pos.m1.r.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Pos_Emo ~ (pRep_D + pRep_I) * (wave4_2 + wave4_3 + wave4_1) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23696.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.9321 -0.5731 -0.0615 0.5698 3.5196
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6525 0.8078
## Residual 0.7119 0.8437
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.33390 0.04653 7982.34212 71.654 < 2e-16 ***
## pRep_D -1.30171 0.06240 8072.87315 -20.861 < 2e-16 ***
## pRep_I -1.20343 0.09367 7780.15326 -12.847 < 2e-16 ***
## wave4_2 0.27578 0.04854 5844.74494 5.682 1.4e-08 ***
## wave4_3 0.06578 0.04942 5755.02733 1.331 0.18323
## wave4_1 -0.62058 0.04850 6011.39549 -12.796 < 2e-16 ***
## pRep_D:wave4_2 -0.22935 0.06565 5843.35184 -3.494 0.00048 ***
## pRep_D:wave4_3 -0.04226 0.06681 5761.70317 -0.633 0.52699
## pRep_D:wave4_1 1.55776 0.06531 6041.08097 23.853 < 2e-16 ***
## pRep_I:wave4_2 -0.03232 0.10457 5939.71408 -0.309 0.75726
## pRep_I:wave4_3 0.09876 0.10682 5823.24106 0.925 0.35525
## pRep_I:wave4_1 0.99339 0.10190 6172.80442 9.749 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pRep_D pRep_I wav4_2 wav4_3 wav4_1 pR_D:4_2 pR_D:4_3
## pRep_D -0.734
## pRep_I -0.471 0.364
## wave4_2 -0.692 0.516 0.344
## wave4_3 -0.664 0.495 0.330 0.640
## wave4_1 -0.708 0.527 0.349 0.667 0.641
## pRp_D:wv4_2 0.511 -0.697 -0.251 -0.740 -0.474 -0.494
## pRp_D:wv4_3 0.491 -0.671 -0.241 -0.474 -0.741 -0.475 0.640
## pRp_D:wv4_1 0.527 -0.722 -0.258 -0.496 -0.477 -0.745 0.669 0.645
## pRp_I:wv4_2 0.324 -0.244 -0.708 -0.470 -0.302 -0.314 0.344 0.221
## pRp_I:wv4_3 0.312 -0.232 -0.679 -0.301 -0.470 -0.302 0.220 0.343
## pRp_I:wv4_1 0.342 -0.257 -0.758 -0.320 -0.308 -0.483 0.234 0.225
## pR_D:4_1 pR_I:4_2 pR_I:4_3
## pRep_D
## pRep_I
## wave4_2
## wave4_3
## wave4_1
## pRp_D:wv4_2
## pRp_D:wv4_3
## pRp_D:wv4_1
## pRp_I:wv4_2 0.231
## pRp_I:wv4_3 0.221 0.619
## pRp_I:wv4_1 0.355 0.665 0.635# Neg Emo
neg.m1.w1 <- lmer(Neg_Emo ~ (pDem_Rep + pParty_Ind) * (wave1_2 + wave1_3 + wave1_4) + (1 | pid),
data = d)
summary(neg.m1.w1)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Neg_Emo ~ (pDem_Rep + pParty_Ind) * (wave1_2 + wave1_3 + wave1_4) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23244.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1641 -0.5706 -0.0447 0.5149 3.8782
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6478 0.8048
## Residual 0.6634 0.8145
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.27635 0.02581 5931.79721 88.210 < 2e-16 ***
## pDem_Rep 0.09217 0.04664 6574.56305 1.976 0.0482 *
## pParty_Ind -0.02429 0.06136 7974.89033 -0.396 0.6922
## wave1_2 0.05085 0.02917 5906.78906 1.743 0.0814 .
## wave1_3 0.02309 0.03084 5989.95273 0.749 0.4542
## wave1_4 0.27897 0.03539 6073.34875 7.882 3.79e-15 ***
## pDem_Rep:wave1_2 -1.71161 0.05144 5839.93270 -33.274 < 2e-16 ***
## pDem_Rep:wave1_3 -1.54229 0.05382 5913.62618 -28.656 < 2e-16 ***
## pDem_Rep:wave1_4 -1.78528 0.06311 6024.13232 -28.288 < 2e-16 ***
## pParty_Ind:wave1_2 -0.09395 0.07651 6049.55953 -1.228 0.2195
## pParty_Ind:wave1_3 -0.05000 0.08100 6109.99393 -0.617 0.5371
## pParty_Ind:wave1_4 0.12825 0.09213 6171.13098 1.392 0.1640
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav1_2 wav1_3 wav1_4 pD_R:1_2 pD_R:1_3
## pDem_Rep 0.088
## pParty_Ind 0.485 -0.047
## wave1_2 -0.471 -0.051 -0.262
## wave1_3 -0.450 -0.048 -0.256 0.437
## wave1_4 -0.399 -0.047 -0.236 0.381 0.383
## pDm_Rp:w1_2 -0.040 -0.509 0.033 0.063 0.033 0.029
## pDm_Rp:w1_3 -0.039 -0.486 0.030 0.034 0.065 0.029 0.470
## pDm_Rp:w1_4 -0.032 -0.420 0.030 0.031 0.030 0.063 0.402 0.400
## pPrty_I:1_2 -0.247 0.022 -0.510 0.569 0.234 0.205 -0.039 -0.022
## pPrty_I:1_3 -0.238 0.020 -0.491 0.235 0.577 0.209 -0.022 -0.039
## pPrty_I:1_4 -0.219 0.014 -0.450 0.206 0.208 0.556 -0.020 -0.020
## pD_R:1_4 pP_I:1_2 pP_I:1_3
## pDem_Rep
## pParty_Ind
## wave1_2
## wave1_3
## wave1_4
## pDm_Rp:w1_2
## pDm_Rp:w1_3
## pDm_Rp:w1_4
## pPrty_I:1_2 -0.017
## pPrty_I:1_3 -0.017 0.431
## pPrty_I:1_4 -0.037 0.378 0.378neg.m1.w4 <- lmer(Neg_Emo ~ (pDem_Rep + pParty_Ind) * (wave4_2 + wave4_3 + wave4_1) + (1 | pid),
data = d)
summary(neg.m1.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Neg_Emo ~ (pDem_Rep + pParty_Ind) * (wave4_2 + wave4_3 + wave4_1) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23244.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1641 -0.5706 -0.0447 0.5149 3.8782
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6478 0.8048
## Residual 0.6634 0.8145
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.55532 0.03450 7989.48044 74.060 < 2e-16 ***
## pDem_Rep -1.69311 0.06072 8068.42817 -27.885 < 2e-16 ***
## pParty_Ind 0.10396 0.08466 7639.56314 1.228 0.219458
## wave4_2 -0.22813 0.03628 5855.58125 -6.288 3.45e-10 ***
## wave4_3 -0.25588 0.03697 5740.54754 -6.921 4.98e-12 ***
## wave4_1 -0.27897 0.03539 6073.34877 -7.882 3.79e-15 ***
## pDem_Rep:wave4_2 0.07367 0.06341 5830.69656 1.162 0.245397
## pDem_Rep:wave4_3 0.24299 0.06452 5752.17827 3.766 0.000168 ***
## pDem_Rep:wave4_1 1.78528 0.06311 6024.13232 28.288 < 2e-16 ***
## pParty_Ind:wave4_2 -0.22221 0.09490 5931.92087 -2.341 0.019240 *
## pParty_Ind:wave4_3 -0.17825 0.09699 5818.12190 -1.838 0.066134 .
## pParty_Ind:wave4_1 -0.12825 0.09213 6171.13098 -1.392 0.163952
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDm_Rp pPrt_I wav4_2 wav4_3 wav4_1 pD_R:4_2 pD_R:4_3
## pDem_Rep 0.056
## pParty_Ind 0.529 -0.034
## wave4_2 -0.679 -0.034 -0.396
## wave4_3 -0.649 -0.033 -0.381 0.621
## wave4_1 -0.728 -0.029 -0.434 0.669 0.637
## pDm_Rp:w4_2 -0.041 -0.692 0.021 0.055 0.035 0.039
## pDm_Rp:w4_3 -0.039 -0.666 0.018 0.035 0.056 0.037 0.641
## pDm_Rp:w4_1 -0.041 -0.717 0.019 0.037 0.035 0.063 0.669 0.645
## pPrty_I:4_2 -0.374 0.027 -0.706 0.573 0.347 0.374 -0.032 -0.021
## pPrty_I:4_3 -0.356 0.024 -0.678 0.345 0.576 0.354 -0.021 -0.032
## pPrty_I:4_1 -0.406 0.028 -0.762 0.377 0.358 0.556 -0.021 -0.020
## pD_R:4_1 pP_I:4_2 pP_I:4_3
## pDem_Rep
## pParty_Ind
## wave4_2
## wave4_3
## wave4_1
## pDm_Rp:w4_2
## pDm_Rp:w4_3
## pDm_Rp:w4_1
## pPrty_I:4_2 -0.023
## pPrty_I:4_3 -0.021 0.616
## pPrty_I:4_1 -0.037 0.666 0.634neg.m1.d <- lmer(Neg_Emo ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(neg.m1.d)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Neg_Emo ~ (pDem_R + pDem_I) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23241.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1641 -0.5706 -0.0447 0.5149 3.8782
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6478 0.8048
## Residual 0.6634 0.8145
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.95780 0.02588 3204.81293 114.285 < 2e-16 ***
## pDem_R -1.16763 0.03779 3693.71341 -30.900 < 2e-16 ***
## pDem_I -0.61203 0.05187 5923.91842 -11.800 < 2e-16 ***
## wave.lin 0.85226 0.03689 6026.26672 23.101 < 2e-16 ***
## wave.quad 0.62001 0.05517 5784.76776 11.238 < 2e-16 ***
## wave.cub -0.55320 0.03341 5673.28167 -16.558 < 2e-16 ***
## pDem_R:wave.lin -1.36050 0.05527 6022.63445 -24.615 < 2e-16 ***
## pDem_R:wave.quad -1.46862 0.08247 5782.64791 -17.808 < 2e-16 ***
## pDem_R:wave.cub 0.84957 0.04986 5680.89374 17.039 < 2e-16 ***
## pDem_I:wave.lin -0.56006 0.08521 6165.20092 -6.572 5.36e-11 ***
## pDem_I:wave.quad -1.00651 0.12884 5901.06589 -7.812 6.60e-15 ***
## pDem_I:wave.cub 0.40865 0.07932 5790.50693 5.152 2.67e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wav.ln wav.qd wav.cb pDm_R:wv.l pDm_R:wv.q
## pDem_R -0.651
## pDem_I -0.421 0.329
## wave.lin 0.192 -0.132 -0.092
## wave.quad -0.044 0.028 0.026 -0.228
## wave.cub -0.069 0.048 0.034 -0.106 0.171
## pDm_R:wv.ln -0.125 0.178 0.069 -0.670 0.151 0.072
## pDm_R:wv.qd 0.030 -0.053 -0.018 0.152 -0.671 -0.114 -0.215
## pDm_R:wv.cb 0.044 -0.057 -0.027 0.072 -0.114 -0.673 -0.111 0.167
## pDm_I:wv.ln -0.070 0.046 0.205 -0.439 0.100 0.047 0.289 -0.067
## pDm_I:wv.qd 0.015 -0.012 0.000 0.098 -0.436 -0.075 -0.064 0.286
## pDm_I:wv.cb 0.026 -0.015 -0.068 0.047 -0.074 -0.430 -0.030 0.049
## pDm_R:wv.c pDm_I:wv.l pDm_I:wv.q
## pDem_R
## pDem_I
## wave.lin
## wave.quad
## wave.cub
## pDm_R:wv.ln
## pDm_R:wv.qd
## pDm_R:wv.cb
## pDm_I:wv.ln -0.031
## pDm_I:wv.qd 0.049 -0.218
## pDm_I:wv.cb 0.284 -0.064 0.175neg.m1.d.w4 <- lmer(Neg_Emo ~ (pDem_R + pDem_I) * (wave4_2 + wave4_3 + wave4_1) + (1 | pid),
data = d)
summary(neg.m1.d.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Neg_Emo ~ (pDem_R + pDem_I) * (wave4_2 + wave4_3 + wave4_1) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23244.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1641 -0.5706 -0.0447 0.5149 3.8782
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6478 0.8048
## Residual 0.6634 0.8145
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.36723 0.04126 7944.25637 81.603 < 2e-16 ***
## pDem_R -1.69311 0.06072 8068.42817 -27.885 < 2e-16 ***
## pDem_I -0.74259 0.08896 7734.15181 -8.347 < 2e-16 ***
## wave4_2 -0.19089 0.04262 5817.34659 -4.479 7.64e-06 ***
## wave4_3 -0.31796 0.04330 5742.62460 -7.342 2.39e-13 ***
## wave4_1 -1.12886 0.04208 6032.40739 -26.824 < 2e-16 ***
## pDem_R:wave4_2 0.07367 0.06341 5830.69656 1.162 0.245397
## pDem_R:wave4_3 0.24299 0.06452 5752.17827 3.766 0.000168 ***
## pDem_R:wave4_1 1.78528 0.06311 6024.13232 28.288 < 2e-16 ***
## pDem_I:wave4_2 -0.18537 0.09907 5919.66693 -1.871 0.061391 .
## pDem_I:wave4_3 -0.05676 0.10123 5812.21942 -0.561 0.575039
## pDem_I:wave4_1 0.76439 0.09626 6159.91644 7.941 2.38e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pDem_R pDem_I wav4_2 wav4_3 wav4_1 pD_R:4_2 pD_R:4_3
## pDem_R -0.666
## pDem_I -0.433 0.309
## wave4_2 -0.686 0.466 0.322
## wave4_3 -0.662 0.450 0.313 0.641
## wave4_1 -0.722 0.492 0.337 0.674 0.650
## pDm_R:wv4_2 0.461 -0.692 -0.216 -0.673 -0.432 -0.454
## pDm_R:wv4_3 0.444 -0.666 -0.210 -0.431 -0.673 -0.437 0.641
## pDm_R:wv4_1 0.481 -0.717 -0.227 -0.450 -0.435 -0.670 0.669 0.645
## pDm_I:wv4_2 0.292 -0.196 -0.704 -0.436 -0.280 -0.293 0.289 0.185
## pDm_I:wv4_3 0.283 -0.189 -0.677 -0.279 -0.436 -0.283 0.184 0.288
## pDm_I:wv4_1 0.312 -0.208 -0.759 -0.299 -0.289 -0.444 0.199 0.192
## pD_R:4_1 pD_I:4_2 pD_I:4_3
## pDem_R
## pDem_I
## wave4_2
## wave4_3
## wave4_1
## pDm_R:wv4_2
## pDm_R:wv4_3
## pDm_R:wv4_1
## pDm_I:wv4_2 0.192
## pDm_I:wv4_3 0.185 0.618
## pDm_I:wv4_1 0.292 0.667 0.636neg.m1.r <- lmer(Neg_Emo ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) + (1 | pid),
data = d)
summary(neg.m1.r)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Neg_Emo ~ (pRep_D + pRep_I) * (wave.lin + wave.quad + wave.cub) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23241.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1641 -0.5706 -0.0447 0.5149 3.8782
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6478 0.8048
## Residual 0.6634 0.8145
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.79017 0.02870 3252.20166 62.367 < 2e-16 ***
## pRep_D 1.16763 0.03779 3693.71340 30.900 < 2e-16 ***
## pRep_I 0.55560 0.05318 5853.10172 10.447 < 2e-16 ***
## wave.lin -0.50824 0.04104 6003.39104 -12.383 < 2e-16 ***
## wave.quad -0.84861 0.06115 5762.56023 -13.878 < 2e-16 ***
## wave.cub 0.29637 0.03689 5664.07350 8.034 1.14e-15 ***
## pRep_D:wave.lin 1.36050 0.05527 6022.63445 24.615 < 2e-16 ***
## pRep_D:wave.quad 1.46862 0.08247 5782.64791 17.808 < 2e-16 ***
## pRep_D:wave.cub -0.84957 0.04986 5680.89374 -17.039 < 2e-16 ***
## pRep_I:wave.lin 0.80043 0.08713 6159.83674 9.187 < 2e-16 ***
## pRep_I:wave.quad 0.46211 0.13162 5899.06056 3.511 0.00045 ***
## pRep_I:wave.cub -0.44092 0.08081 5780.20231 -5.456 5.06e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pRep_D pRep_I wav.ln wav.qd wav.cb pRp_D:wv.l pRp_D:wv.q
## pRep_D -0.729
## pRep_I -0.466 0.390
## wave.lin 0.163 -0.121 -0.076
## wave.quad -0.060 0.046 0.033 -0.206
## wave.cub -0.047 0.034 0.019 -0.113 0.165
## pRp_D:wv.ln -0.121 0.178 0.059 -0.745 0.153 0.085
## pRp_D:wv.qd 0.042 -0.053 -0.020 0.152 -0.743 -0.122 -0.215
## pRp_D:wv.cb 0.036 -0.057 -0.014 0.085 -0.122 -0.742 -0.111 0.167
## pRp_I:wv.ln -0.079 0.068 0.201 -0.477 0.096 0.055 0.351 -0.070
## pRp_I:wv.qd 0.024 -0.021 -0.004 0.098 -0.473 -0.078 -0.072 0.347
## pRp_I:wv.cb 0.026 -0.020 -0.063 0.054 -0.075 -0.463 -0.039 0.055
## pRp_D:wv.c pRp_I:wv.l pRp_I:wv.q
## pRep_D
## pRep_I
## wave.lin
## wave.quad
## wave.cub
## pRp_D:wv.ln
## pRp_D:wv.qd
## pRp_D:wv.cb
## pRp_I:wv.ln -0.041
## pRp_I:wv.qd 0.056 -0.213
## pRp_I:wv.cb 0.338 -0.068 0.173neg.m1.r.w4 <- lmer(Neg_Emo ~ (pRep_D + pRep_I) * (wave4_2 + wave4_3 + wave4_1) + (1 | pid),
data = d)
summary(neg.m1.r.w4)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Neg_Emo ~ (pRep_D + pRep_I) * (wave4_2 + wave4_3 + wave4_1) +
## (1 | pid)
## Data: d
##
## REML criterion at convergence: 23244.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1641 -0.5706 -0.0447 0.5149 3.8782
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.6478 0.8048
## Residual 0.6634 0.8145
## Number of obs: 8104, groups: pid, 2615
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.67411 0.04531 7962.79410 36.951 < 2e-16 ***
## pRep_D 1.69311 0.06072 8068.42817 27.885 < 2e-16 ***
## pRep_I 0.95052 0.09090 7768.47833 10.457 < 2e-16 ***
## wave4_2 -0.11722 0.04689 5832.09629 -2.500 0.012442 *
## wave4_3 -0.07497 0.04773 5745.88269 -1.571 0.116280
## wave4_1 0.65642 0.04687 5995.61437 14.006 < 2e-16 ***
## pRep_D:wave4_2 -0.07367 0.06341 5830.69655 -1.162 0.245397
## pRep_D:wave4_3 -0.24299 0.06452 5752.17826 -3.766 0.000168 ***
## pRep_D:wave4_1 -1.78528 0.06311 6024.13231 -28.288 < 2e-16 ***
## pRep_I:wave4_2 -0.25904 0.10103 5923.74037 -2.564 0.010371 *
## pRep_I:wave4_3 -0.29974 0.10319 5810.89465 -2.905 0.003688 **
## pRep_I:wave4_1 -1.02089 0.09850 6151.68212 -10.365 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) pRep_D pRep_I wav4_2 wav4_3 wav4_1 pR_D:4_2 pR_D:4_3
## pRep_D -0.734
## pRep_I -0.471 0.365
## wave4_2 -0.687 0.512 0.342
## wave4_3 -0.659 0.492 0.329 0.640
## wave4_1 -0.702 0.523 0.347 0.667 0.641
## pRp_D:wv4_2 0.508 -0.692 -0.250 -0.740 -0.474 -0.494
## pRp_D:wv4_3 0.488 -0.666 -0.240 -0.474 -0.741 -0.475 0.641
## pRp_D:wv4_1 0.523 -0.717 -0.257 -0.496 -0.477 -0.745 0.669 0.645
## pRp_I:wv4_2 0.322 -0.242 -0.704 -0.470 -0.302 -0.314 0.344 0.221
## pRp_I:wv4_3 0.310 -0.231 -0.676 -0.301 -0.470 -0.302 0.220 0.343
## pRp_I:wv4_1 0.340 -0.256 -0.755 -0.320 -0.308 -0.483 0.234 0.225
## pR_D:4_1 pR_I:4_2 pR_I:4_3
## pRep_D
## pRep_I
## wave4_2
## wave4_3
## wave4_1
## pRp_D:wv4_2
## pRp_D:wv4_3
## pRp_D:wv4_1
## pRp_I:wv4_2 0.231
## pRp_I:wv4_3 0.221 0.619
## pRp_I:wv4_1 0.355 0.665 0.634Overall Summary
As in previous research, perceived election legitimacy (PEL) is responsive to election outcome: Democrats’ PEL decreased after the 2024 election and Republicans’ PEL increased. This correlates with changes in positive and negative emotions: emotions predict PEL in line with their valence (positive emotions predict PEL positively, negative emotions predict PEL negatively), and partisans’ emotions follow expected patterns relative to the 2024 election: from wave 1 to wave 4, Democrats increase in negative and decrease in positive emotions, while Republicans decrease in negative and increase in positive emotions, with the steepest changes happening from wave 1 (pre-election) to wave 2 (immediately post-election).
Trust in government seems to buffer against these trends—for those high in governmental trust, PEL is also high, regardless of party ID. Governmental trust may also moderate the effect of negative emotions: there was a significant 4-way interaction of governmental trust, negative emotions, party ID (Dem vs. Rep), and linear time (b = -0.10, p = .032); there was also a significant 4-way interaction of governmental trust, negative emotions, party ID (partisans vs. Ind), and linear time (b = -0.22, p = .005). No such interactions were present for positive emotions.