Institutional Signaling Pilot 2
Marcus
5/07/2023
1 Setup
Libraries and functions
knitr::opts_chunk$set(warning = FALSE, message = FALSE)
Mypackages <-
c("lme4","tidyverse","effects","ggplot2","psych",
"MASS","Rmisc","lmerTest","ggthemes", "knitr",
"lsmeans","pastecs","sjstats","car","ordinal",
"Rcpp","corrplot", "ggpubr", "EnvStats",
"easyStats", "cowplot","see","datawizard", "ggcorrplot",
"corrplot", "effects"
)
# install.packages(Mypackages) #you must remove the # in this comment if you need to install the packages!
lapply(Mypackages,
require,
character.only = TRUE)
options(knitr.kable.NA = '—')
set.seed(1) 1.1 Load Data
# read in data files
gjg <-read.csv("/Users/mtrenfield17/Desktop/Research/Boston College Research/Institutional Signaling/Institutional Virtue Signaling Pilot 2.csv")1.2 Functions
plot_cooker <- function(data, iv, dv, title) {
part1 <- ggplot(data, aes(x = {{iv}}, y = {{dv}}, fill = {{iv}})) +
geom_violin(alpha = 0.3, scale = "count") +
stat_summary(fun = "mean", geom = "point", size = 3, color = "black") +
stat_summary(fun.data = mean_cl_normal, geom = "errorbar", width = 0.2,
#change to make a data set from allEffects with mean, low CI, high CI
size = 1.5, color = "black") +
theme_classic() +
xlab("") +
ylab("") +
ggtitle(title)
ggpar(part1, legend = "none")
}
wrapped_plot_cooker <- function(data, iv, dv, title, facet_var) {
part1 <- ggplot(data, aes(x = {{iv}}, y = {{dv}}, fill = {{iv}})) +
geom_violin(alpha = 0.3, scale = "count") +
stat_summary(fun = "mean", geom = "point", size = 3, color = "black") +
stat_summary(fun.data = mean_cl_normal, geom = "errorbar", width = 0.2,
size = 1.5, color = "black") +
theme_classic() +
xlab("") +
ylab("") +
ggtitle(title) +
facet_wrap(vars({{facet_var}}))
ggpar(part1, legend = "none")
}
by_line <- function(data, iv, dv, x_label, y_label, color_label, plot_title) {
ggplot(data, aes(x = {{iv}}, y = {{dv}}, color = condition)) +
stat_summary(fun.data = "mean_cl_normal", geom = "line") +
geom_point(position = position_jitter(width = 0.1, height = 0.1), alpha = 0.2) +
labs(x = x_label, y = y_label, color = color_label, title = plot_title)
}1.3 Reshaping data
#### filtering people who failed the attn check ####
filtered_gjg <- gjg %>% filter(attentionCheck_text == "Companies' Social Media")
#### make dataset long ####
gjg_long<-filtered_gjg %>% gather(stim, resp, "B_S_Chic_staticNorm":"C_N_Tar_Prior")
gjg_long<-gjg_long %>%
separate(stim, into= c("social_issue", "signal", "company", "DV"), sep="_")
## shift dataset back to wide format ##
gjg_long <- spread(gjg_long, DV, resp)
names(gjg_long)## [1] "StartDate" "EndDate" "Status"
## [4] "IPAddress" "Progress" "Duration..in.seconds."
## [7] "Finished" "RecordedDate" "ResponseId"
## [10] "RecipientLastName" "RecipientFirstName" "RecipientEmail"
## [13] "ExternalReference" "LocationLatitude" "LocationLongitude"
## [16] "DistributionChannel" "UserLanguage" "prolificID"
## [19] "consent" "attentionCheck" "attentionCheck_text"
## [22] "inc" "inc_text" "edu"
## [25] "edu_text" "age" "gen"
## [28] "gen_3_TEXT" "gen_text" "pol"
## [31] "pol_text" "pid" "pid_text"
## [34] "area" "area_text" "race"
## [37] "race_text" "post_Real_Check" "openFeedback"
## [40] "confusion" "PID" "PROLIFIC_PID"
## [43] "STUDY_ID" "SESSION_ID" "cluster"
## [46] "social_issue" "signal" "company"
## [49] "dyNorm" "noisyMin" "OComp"
## [52] "OLike" "OMotivate" "OTrust"
## [55] "peerPress" "Prior" "Profit"
## [58] "pubPress" "Rep" "riskInact"
## [61] "SComp" "SGen" "SImport"
## [64] "SLike" "SRelImport" "staticNorm"
## [67] "STrust" "surprise"gjg_long <- gjg_long %>% mutate_at(c("dyNorm", "noisyMin", "OComp", "OLike", "OMotivate", "OTrust", "peerPress", "Prior", "Profit", "pubPress", "Rep", "riskInact", "SComp", "SGen", "SImport", "SLike", "SRelImport", "staticNorm", "STrust", "surprise","post_Real_Check", "age", "pid", "area", "pol", "edu", "gen", "inc"), as.numeric)
## Rename Vignettes
gjg_long <- gjg_long %>%
mutate(companyLeaning = case_when(
company == "Bud" ~ "R",
company == "CAR" ~ "R",
company == "Chic" ~ "R",
company == "Dis" ~ "L",
company == "Pop" ~ "L",
company == "Star" ~ "L",
company == "Tar" ~ "L",
company == "Wal" ~ "R",
company == "WNBA" ~ "L",
company == "Fox" ~ "R",
company == "NBC" ~ "L",
company == "NBA" ~ "L",
company == "NFL" ~ "R",
TRUE ~ company # if none of the above conditions are met, keep the original value
))
gjg_long$condition <- paste0(gjg_long$companyLeaning, gjg_long$signal)
gjg_long <- subset(gjg_long, !(condition == "CS" & company == "Chic" & !is.na(Rep)))
gjg_long <- gjg_long %>%
mutate(condition = case_when(
condition == "LS" ~ "Liberal \n\ Signal",
condition == "LN" ~ "Liberal \n\ Control",
condition == "RS" ~ "Conservative \n\ Signal",
condition == "RN" ~ "Conservative \n\ Control",
TRUE ~ condition # if none of the above conditions are met, keep the original value
))
gjg_long <- gjg_long %>%
mutate(companyLeaning = case_when(
companyLeaning == "R" ~ "Right",
companyLeaning == "L" ~ "Left",
TRUE ~ companyLeaning # if none of the above conditions are met, keep the original value
))
gjg_long <- gjg_long %>%
mutate(company = case_when(
company == "Bud" ~ "Budweiser",
company == "CAR" ~ "NASCAR",
company == "Chic" ~ "Chick-fil-A",
company == "Dis" ~ "Disney",
company == "Pop" ~ "Popeyes",
company == "Star" ~ "Starbucks",
company == "Tar" ~ "Target",
company == "Wal" ~ "Walmart",
TRUE ~ company # if none of the above conditions are met, keep the original value
))
## Rename Conditions
gjg_long$signal <- as.factor(gjg_long$signal)
gjg_long <- gjg_long %>%
mutate(signal = case_when(
signal == "S" ~ "Signal",
signal == "N" ~ "No Signal",
TRUE ~ signal # if none of the above conditions are met, keep the original value
))
gjg_long$social_issue <- as.factor(gjg_long$social_issue)
gjg_long <- gjg_long %>%
mutate(social_issue = case_when(
social_issue == "T" ~ "Transgendered Representation",
social_issue == "C" ~ "Climate Change",
social_issue == "L" ~ "LGBTQ Representation",
social_issue == "B" ~ "BLM",
TRUE ~ social_issue # if none of the above conditions are met, keep the original value
))
## data frame just with signaling messages
signal_gjg_long <- gjg_long %>%
filter(signal == "Signal")
## filter out rows for condition-vignette pairs people DON'T see
gjg_long <- gjg_long %>% filter(is.na(dyNorm) == FALSE)2 Attention Check
gjg %>%
group_by(attentionCheck) %>%
dplyr::summarise(n = n()) %>%
mutate(freq = n / sum(n))59/801 people failed the attention check.
3 Demographics
# Subset your data frame to include only the demographic columns
demo_gjg <- gjg[, c("gen_text", "race_text", "inc_text", "edu_text", "pol_text", "pid_text", "area_text")]
# Age
mean(gjg$age, na.rm=TRUE)## [1] 42.75062sd(gjg$age, na.rm=TRUE)## [1] 14.02753# Loop through each demographic column and calculate frequency counts
freq_tables <- list()
for (col in names(demo_gjg)) {
{
freq_table <- as.data.frame(table(demo_gjg[[col]]))
freq_table$Percent <- round(freq_table$Freq / sum(freq_table$Freq) * 100, 2)
freq_tables[[col]] <- freq_table
}
}
# Print the frequency tables
for (i in seq_along(freq_tables)) {
if (!is.null(freq_tables[[i]])) {
cat("\nTable of frequencies for", names(freq_tables)[i], ":\n")
print(freq_tables[[i]])
}
}##
## Table of frequencies for gen_text :
## Var1 Freq Percent
## 1 30 3.6
## 2 I identify as: 10 1.2
## 3 Man 399 47.9
## 4 Woman 394 47.3
##
## Table of frequencies for race_text :
## Var1
## 1
## 2 American Indian and Native Alaskan
## 3 American Indian and Native Alaskan,Black
## 4 American Indian and Native Alaskan,Black,East Asian,South Asian,Southeast Asian,Pacific Islander or Native Hawaiian,Hispanic or Latino/a/x,Middle Eastern and North African,White
## 5 American Indian and Native Alaskan,Black,Hispanic or Latino/a/x,Middle Eastern and North African,White
## 6 American Indian and Native Alaskan,Black,Hispanic or Latino/a/x,White
## 7 American Indian and Native Alaskan,Hispanic or Latino/a/x,White
## 8 American Indian and Native Alaskan,White
## 9 Black
## 10 Black,East Asian,Hispanic or Latino/a/x,White
## 11 Black,Hispanic or Latino/a/x
## 12 Black,White
## 13 East Asian
## 14 East Asian,Hispanic or Latino/a/x,White
## 15 East Asian,Middle Eastern and North African
## 16 East Asian,White
## 17 Hispanic or Latino/a/x
## 18 Hispanic or Latino/a/x,White
## 19 Middle Eastern and North African
## 20 Middle Eastern and North African,White
## 21 South Asian
## 22 South Asian,Hispanic or Latino/a/x,Middle Eastern and North African,White
## 23 Southeast Asian
## 24 Southeast Asian,White
## 25 White
## Freq Percent
## 1 31 3.72
## 2 4 0.48
## 3 1 0.12
## 4 1 0.12
## 5 1 0.12
## 6 1 0.12
## 7 2 0.24
## 8 3 0.36
## 9 61 7.32
## 10 1 0.12
## 11 1 0.12
## 12 11 1.32
## 13 28 3.36
## 14 2 0.24
## 15 1 0.12
## 16 9 1.08
## 17 42 5.04
## 18 21 2.52
## 19 3 0.36
## 20 3 0.36
## 21 8 0.96
## 22 1 0.12
## 23 17 2.04
## 24 2 0.24
## 25 578 69.39
##
## Table of frequencies for inc_text :
## Var1 Freq Percent
## 1 31 3.72
## 2 $100,000 - $149,999 94 11.28
## 3 $150,000 - $199,999 44 5.28
## 4 $25,000 - $49,999 205 24.61
## 5 $50,000 - $74,999 166 19.93
## 6 $75,000 - $99,999 118 14.17
## 7 less than $25,000 143 17.17
## 8 more than $200,000 32 3.84
##
## Table of frequencies for edu_text :
## Var1 Freq Percent
## 1 31 3.72
## 2 Bachelor's degree 289 34.69
## 3 Graduate degree (Masters, PhD, etc) 117 14.05
## 4 High school diploma or GED 137 16.45
## 5 Some college, Technical degree, or Associates degree 250 30.01
## 6 Some schooling, but no high school diploma or degree 9 1.08
##
## Table of frequencies for pol_text :
## Var1 Freq Percent
## 1 30 3.60
## 2 Conservative 132 15.85
## 3 Liberal 138 16.57
## 4 Moderate 185 22.21
## 5 Somewhat Conservative 107 12.85
## 6 Somewhat Liberal 98 11.76
## 7 Very Conservative 59 7.08
## 8 Very Liberal 84 10.08
##
## Table of frequencies for pid_text :
## Var1 Freq Percent
## 1 30 3.60
## 2 Democrat 292 35.05
## 3 Independent / Other 263 31.57
## 4 Republican 248 29.77
##
## Table of frequencies for area_text :
## Var1 Freq Percent
## 1 30 3.60
## 2 Rural 184 22.09
## 3 Suburban 438 52.58
## 4 Urban 181 21.734 Correlation
DVs <- gjg_long[c("staticNorm", "dyNorm", "OMotivate", "surprise", "SImport", "SRelImport", "SGen", "Profit", "Rep", "noisyMin", "peerPress", "pubPress", "riskInact", "SLike", "STrust", "SComp", "OLike", "OTrust", "OComp", "Prior", "post_Real_Check", "age", "pol", "edu", "gen", "inc")]
# Compute pairwise correlations
corr_DVs <- cor(DVs, use = "complete.obs")
colnames(corr_DVs) <- c("static norm", "dynamic norm", "Post motivates others", "Surprise", "I think cause is important", "How relatively important I think cause is", "I think company is genuine", "Reputation Motive", "Profit Motive", "Noisy Minority Motive", "Pressure from Peer organizations motive", "Pressure from public motive", "risky NOT to signal", "I like company", "I trust company", "I think company is competent", "Others like company", "Others trust company", "Others think company is competent", "seen prior", "belief in manipulation", "age", "political leaning", "education", "gender", "income")
rownames(corr_DVs) <- c("static norm", "dynamic norm", "Post motivates others", "Surprise", "I think cause is important", "How relatively important I think cause is", "I think company is genuine", "Reputation Motive", "Profit Motive", "Noisy Minority Motive", "Pressure from Peer organizations motive", "Pressure from public motive", "risky NOT to signal", "I like company", "I trust company", "I think company is competent", "Others like company", "Others trust company", "Others think company is competent", "seen prior", "belief in manipulation", "age", "political leaning", "education", "gender", "income")
# Plot the correlation matrix
corrplot(corr_DVs, is.corr = TRUE, type = "full", method = "circle", tl.cex = 0.5, insig = "label_sig", diag = FALSE)
## Correlation for left leaning companies
gjg_left <- gjg_long %>% filter(companyLeaning == "Left")
DVs <- gjg_left[c("staticNorm", "dyNorm", "OMotivate", "surprise", "SImport", "SRelImport", "SGen", "Profit", "Rep", "noisyMin", "peerPress", "pubPress", "riskInact", "SLike", "STrust", "SComp", "OLike", "OTrust", "OComp", "Prior", "post_Real_Check", "age", "pol", "edu", "gen", "inc")]
# Compute pairwise correlations
corr_DVs <- cor(DVs, use = "complete.obs")
colnames(corr_DVs) <- c("static norm", "dynamic norm", "Post motivates others", "Surprise", "I think cause is important", "How relatively important I think cause is", "I think company is genuine", "Reputation Motive", "Profit Motive", "Noisy Minority Motive", "Pressure from Peer organizations motive", "Pressure from public motive", "risky NOT to signal", "I like company", "I trust company", "I think company is competent", "Others like company", "Others trust company", "Others think company is competent", "seen prior", "belief in manipulation", "age", "political leaning", "education", "gender", "income")
rownames(corr_DVs) <- c("static norm", "dynamic norm", "Post motivates others", "Surprise", "I think cause is important", "How relatively important I think cause is", "I think company is genuine", "Reputation Motive", "Profit Motive", "Noisy Minority Motive", "Pressure from Peer organizations motive", "Pressure from public motive", "risky NOT to signal", "I like company", "I trust company", "I think company is competent", "Others like company", "Others trust company", "Others think company is competent", "seen prior", "belief in manipulation", "age", "political leaning", "education", "gender", "income")
# Plot the correlation matrix
corrplot(corr_DVs, is.corr = TRUE, type = "full", method = "circle", tl.cex = 0.5, insig = "label_sig", diag = FALSE)
4.1 Correlation for right leaning companies
gjg_right <- gjg_long %>% filter(companyLeaning == "Right")
DVs <- gjg_right[c("staticNorm", "dyNorm", "OMotivate", "surprise", "SImport", "SRelImport", "SGen", "Profit", "Rep", "noisyMin", "peerPress", "pubPress", "riskInact", "SLike", "STrust", "SComp", "OLike", "OTrust", "OComp", "Prior", "post_Real_Check", "age", "pol", "edu", "gen", "inc")]
# Compute pairwise correlations
corr_DVs <- cor(DVs, use = "complete.obs")
colnames(corr_DVs) <- c("static norm", "dynamic norm", "Post motivates others", "Surprise", "I think cause is important", "How relatively important I think cause is", "I think company is genuine", "Reputation Motive", "Profit Motive", "Noisy Minority Motive", "Pressure from Peer organizations motive", "Pressure from public motive", "risky NOT to signal", "I like company", "I trust company", "I think company is competent", "Others like company", "Others trust company", "Others think company is competent", "seen prior", "belief in manipulation", "age", "political leaning", "education", "gender", "income")
rownames(corr_DVs) <- c("static norm", "dynamic norm", "Post motivates others", "Surprise", "I think cause is important", "How relatively important I think cause is", "I think company is genuine", "Reputation Motive", "Profit Motive", "Noisy Minority Motive", "Pressure from Peer organizations motive", "Pressure from public motive", "risky NOT to signal", "I like company", "I trust company", "I think company is competent", "Others like company", "Others trust company", "Others think company is competent", "seen prior", "belief in manipulation", "age", "political leaning", "education", "gender", "income")
# Plot the correlation matrix
corrplot(corr_DVs, is.corr = TRUE, type = "full", method = "circle", tl.cex = 0.5, insig = "label_sig", diag = FALSE)
5 factor analysis
factorDVs <- gjg_long[c("staticNorm", "dyNorm", "OMotivate", "surprise", "SImport", "SRelImport", "SGen", "Profit", "Rep", "noisyMin", "peerPress", "pubPress", "riskInact", "SLike", "STrust", "SComp", "OLike", "OTrust", "OComp")]
corr_DVs = cor(factorDVs, use="complete.obs")
KMO(corr_DVs) #tests how suited data is for factor analysis## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = corr_DVs)
## Overall MSA = 0.87
## MSA for each item =
## staticNorm dyNorm OMotivate surprise SImport SRelImport SGen
## 0.91 0.83 0.93 0.67 0.79 0.77 0.94
## Profit Rep noisyMin peerPress pubPress riskInact SLike
## 0.84 0.81 0.92 0.87 0.81 0.80 0.88
## STrust SComp OLike OTrust OComp
## 0.87 0.92 0.88 0.87 0.87cortest.bartlett(corr_DVs) #tests correlations between variables## $chisq
## [1] 1035.743
##
## $p.value
## [1] 1.085994e-123
##
## $df
## [1] 171ev<-eigen(cor(corr_DVs)) #gets eigenvalues (variance explained by each component)
ev$values## [1] 1.319743e+01 1.666909e+00 1.166101e+00 9.350191e-01 6.322155e-01
## [6] 5.166858e-01 2.226571e-01 1.968918e-01 1.780653e-01 1.173475e-01
## [11] 3.536832e-02 3.325619e-02 3.247048e-02 2.559978e-02 2.040933e-02
## [16] 9.827983e-03 8.159520e-03 5.590463e-03 2.017346e-16scree(corr_DVs) #number of factors until plot levels off
fa.parallel(corr_DVs, n.obs=50, fa="fa") #checks eigenvalues of factors against eigenvalues of identity (no correlation) matrix
## Parallel analysis suggests that the number of factors = 3 and the number of components = NAdat_fa <- na.omit(factorDVs)
view(dat_fa)5.1 4 factors
fit.4 <- factanal(na.omit(dat_fa),factors=4, rotation="promax", scores = "regression")
print(fit.4, digits = 2, cutoff = .4, sort = TRUE)##
## Call:
## factanal(x = na.omit(dat_fa), factors = 4, scores = "regression", rotation = "promax")
##
## Uniquenesses:
## staticNorm dyNorm OMotivate surprise SImport SRelImport SGen
## 0.68 0.92 0.71 0.96 0.12 0.18 0.38
## Profit Rep noisyMin peerPress pubPress riskInact SLike
## 0.50 0.47 0.50 0.37 0.43 0.77 0.21
## STrust SComp OLike OTrust OComp
## 0.12 0.25 0.24 0.22 0.17
##
## Loadings:
## Factor1 Factor2 Factor3 Factor4
## SGen 0.68
## SLike 0.95
## STrust 0.99
## SComp 0.72
## OLike 0.93
## OTrust 0.90
## OComp 0.93
## Profit 0.63
## Rep 0.70
## peerPress 0.74
## pubPress 0.81
## staticNorm 0.51
## SImport 0.98
## SRelImport 0.97
## noisyMin 0.42 -0.51
## dyNorm
## OMotivate
## surprise
## riskInact 0.49
##
## Factor1 Factor2 Factor3 Factor4
## SS loadings 3.05 2.66 2.60 2.58
## Proportion Var 0.16 0.14 0.14 0.14
## Cumulative Var 0.16 0.30 0.44 0.57
##
## Factor Correlations:
## Factor1 Factor2 Factor3 Factor4
## Factor1 1.00 0.50 0.40 0.66
## Factor2 0.50 1.00 0.26 0.47
## Factor3 0.40 0.26 1.00 0.20
## Factor4 0.66 0.47 0.20 1.00
##
## Test of the hypothesis that 4 factors are sufficient.
## The chi square statistic is 1203.02 on 101 degrees of freedom.
## The p-value is 5.56e-1885.2 3 factors
fit.3 <- factanal(na.omit(dat_fa),factors=3, rotation="promax", scores = "regression")
print(fit.3, digits = 2, cutoff = .4, sort = TRUE)##
## Call:
## factanal(x = na.omit(dat_fa), factors = 3, scores = "regression", rotation = "promax")
##
## Uniquenesses:
## staticNorm dyNorm OMotivate surprise SImport SRelImport SGen
## 0.68 0.92 0.70 0.96 0.11 0.18 0.42
## Profit Rep noisyMin peerPress pubPress riskInact SLike
## 0.45 0.44 0.55 0.49 0.58 0.84 0.41
## STrust SComp OLike OTrust OComp
## 0.34 0.32 0.32 0.30 0.25
##
## Loadings:
## Factor1 Factor2 Factor3
## SLike 0.63
## STrust 0.64
## SComp 0.71
## OLike 0.92
## OTrust 0.92
## OComp 0.95
## Profit 0.75
## Rep 0.80
## peerPress 0.66
## pubPress 0.72
## staticNorm 0.51
## SImport 0.99
## SRelImport 0.98
## noisyMin -0.50
## dyNorm
## OMotivate
## surprise
## SGen 0.45 -0.43
## riskInact 0.41
##
## Factor1 Factor2 Factor3
## SS loadings 4.43 3.00 2.61
## Proportion Var 0.23 0.16 0.14
## Cumulative Var 0.23 0.39 0.53
##
## Factor Correlations:
## Factor1 Factor2 Factor3
## Factor1 1.00 -0.53 0.42
## Factor2 -0.53 1.00 -0.35
## Factor3 0.42 -0.35 1.00
##
## Test of the hypothesis that 3 factors are sufficient.
## The chi square statistic is 3281.51 on 117 degrees of freedom.
## The p-value is 06 Plots + Inferential Stats
6.1 All Plots
plot_list <- list(plot_cooker(gjg_long, condition, staticNorm, "Percent of support for issue"),
plot_cooker(gjg_long, condition, dyNorm, "Change in support for issue"),
plot_cooker(gjg_long, condition, SImport, "I think cause is important"),
plot_cooker(gjg_long, condition, SRelImport, "I think cause is important relative to other causes"),
plot_cooker(gjg_long, condition, OMotivate, "Message motivates others to act"),
plot_cooker(gjg_long, condition, surprise, "Surprise"),
plot_cooker(gjg_long, condition, SGen, "I think company is genuine"),
plot_cooker(signal_gjg_long, condition, Rep, "Reputation motive"),
plot_cooker(signal_gjg_long, condition, Profit, "Profit motive"),
plot_cooker(signal_gjg_long, condition, noisyMin, "Motive to cater to noisy minority"),
plot_cooker(signal_gjg_long, condition, peerPress, "Pressured by peer companies"),
plot_cooker(signal_gjg_long, condition, pubPress, "Pressured by public"),
plot_cooker(signal_gjg_long, condition, riskInact, "Risky NOT to send signal"),
plot_cooker(gjg_long, condition, SLike, "I like company"),
plot_cooker(gjg_long, condition, STrust, "I trust company"),
plot_cooker(gjg_long, condition, SComp, "I think company is competent"),
plot_cooker(gjg_long, condition, OLike, "Others like company"),
plot_cooker(gjg_long, condition, OTrust, "Others trust company"),
plot_cooker(gjg_long, condition, OComp, "Others think company is competent"),
plot_cooker(gjg_long, condition, post_Real_Check, "To what extent did you think the posts were fake?")
)
plot_arranged <- ggarrange(plotlist = plot_list, ncol = 5, nrow = 4)
plot_arranged
6.2 Individual Plots + Tests
6.2.1 Static Norm
plot_cooker(gjg_long, condition, staticNorm, "Percent of support for issue")
mod_staticNorm <- lmer(staticNorm ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_staticNorm)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: staticNorm ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 26184.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.1256 -0.5841 0.0427 0.5940 3.6422
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 177.9 13.34
## social_issue (Intercept) 117.0 10.81
## Residual 198.4 14.09
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 55.3544 5.4524 3.0873 10.152 0.0018
## conditionConservative \n Signal 0.8640 0.7184 2301.0007 1.203 0.2292
## conditionLiberal \n Control -0.5539 0.7184 2301.0003 -0.771 0.4407
## conditionLiberal \n Signal 0.5933 0.7184 2301.0007 0.826 0.4090
##
## (Intercept) **
## conditionConservative \n Signal
## conditionLiberal \n Control
## conditionLiberal \n Signal
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.066
## cndtnLbrlCn -0.066 0.500
## cndtnLbrlSg -0.066 0.500 0.5006.2.2 Dynamic Norm
plot_cooker(gjg_long, condition, dyNorm, "Change in support for issue")
## SIGNIFICANT ##
mod_dyNorm <- lmer(dyNorm ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_dyNorm)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: dyNorm ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9585.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7479 -0.4442 0.0547 0.5575 4.0707
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.8301 0.9111
## social_issue (Intercept) 0.0368 0.1918
## Residual 0.8882 0.9424
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.911e+00 1.069e-01 4.356e+00 45.926 5.11e-07
## conditionConservative \n Signal 2.276e-01 4.806e-02 2.301e+03 4.736 2.31e-06
## conditionLiberal \n Control 9.293e-02 4.806e-02 2.301e+03 1.934 0.05329
## conditionLiberal \n Signal 1.482e-01 4.806e-02 2.301e+03 3.084 0.00207
##
## (Intercept) ***
## conditionConservative \n Signal ***
## conditionLiberal \n Control .
## conditionLiberal \n Signal **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.225
## cndtnLbrlCn -0.225 0.500
## cndtnLbrlSg -0.225 0.500 0.5006.2.3 Issue is important
plot_cooker(gjg_long, condition, SImport, "I think cause is important")
mod_SImport <- lmer(SImport ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SImport)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SImport ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11267.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7777 -0.4726 0.0107 0.5082 3.3585
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 2.5555 1.5986
## social_issue (Intercept) 0.3243 0.5694
## Residual 1.3141 1.1463
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.871e+00 2.934e-01 3.349e+00 16.601
## conditionConservative \n Signal 6.007e-02 5.846e-02 2.301e+03 1.027
## conditionLiberal \n Control -1.142e-01 5.846e-02 2.301e+03 -1.954
## conditionLiberal \n Signal -8.882e-04 5.846e-02 2.301e+03 -0.015
## Pr(>|t|)
## (Intercept) 0.000247 ***
## conditionConservative \n Signal 0.304345
## conditionLiberal \n Control 0.050875 .
## conditionLiberal \n Signal 0.987880
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.100
## cndtnLbrlCn -0.100 0.500
## cndtnLbrlSg -0.100 0.500 0.5006.2.4 Issue is relatively important
plot_cooker(gjg_long, condition, SRelImport, "I think cause is important relative to other causes")
mod_SRelImport <- lmer(SRelImport ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SRelImport)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SRelImport ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 10589.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.4988 -0.5790 -0.0023 0.5326 3.5653
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.9201 1.3857
## social_issue (Intercept) 0.4561 0.6753
## Residual 1.0726 1.0357
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.930e+00 3.434e-01 3.189e+00 11.445
## conditionConservative \n Signal 8.142e-02 5.282e-02 2.301e+03 1.541
## conditionLiberal \n Control -5.640e-02 5.282e-02 2.301e+03 -1.068
## conditionLiberal \n Signal -3.791e-03 5.282e-02 2.301e+03 -0.072
## Pr(>|t|)
## (Intercept) 0.00107 **
## conditionConservative \n Signal 0.12336
## conditionLiberal \n Control 0.28576
## conditionLiberal \n Signal 0.94280
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.077
## cndtnLbrlCn -0.077 0.500
## cndtnLbrlSg -0.077 0.500 0.5006.2.5 Message motivates others
plot_cooker(gjg_long, condition, OMotivate, "Message motivates others to act")
## SIGNIFICANT ##
mod_OMotivate <- lmer(OMotivate ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OMotivate)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OMotivate ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11384.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.00156 -0.66804 0.04285 0.67324 2.64065
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.68950 0.8304
## social_issue (Intercept) 0.01739 0.1319
## Residual 1.88086 1.3714
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.07562 0.08769 7.21147 35.074
## conditionConservative \n Signal 1.60041 0.06994 2301.05656 22.881
## conditionLiberal \n Control -0.08913 0.06994 2301.03561 -1.274
## conditionLiberal \n Signal 1.90144 0.06994 2301.05656 27.185
## Pr(>|t|)
## (Intercept) 2.52e-09 ***
## conditionConservative \n Signal < 2e-16 ***
## conditionLiberal \n Control 0.203
## conditionLiberal \n Signal < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.399
## cndtnLbrlCn -0.399 0.500
## cndtnLbrlSg -0.399 0.500 0.5006.2.6 Surprise
plot_cooker(gjg_long, condition, surprise, "Surprise")
## SIGNIFICANT ##
mod_surprise <- lmer(surprise ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_surprise)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: surprise ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11803.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.6841 -0.6883 -0.1527 0.6432 3.2124
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.6774 0.8231
## social_issue (Intercept) 0.1227 0.3503
## Residual 2.2076 1.4858
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.96443 0.18557 3.60771 15.975
## conditionConservative \n Signal 1.34118 0.07578 2301.01069 17.699
## conditionLiberal \n Control -0.55460 0.07578 2301.00678 -7.319
## conditionLiberal \n Signal -0.12415 0.07578 2301.01069 -1.638
## Pr(>|t|)
## (Intercept) 0.000177 ***
## conditionConservative \n Signal < 2e-16 ***
## conditionLiberal \n Control 3.44e-13 ***
## conditionLiberal \n Signal 0.101489
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.204
## cndtnLbrlCn -0.204 0.500
## cndtnLbrlSg -0.204 0.500 0.5006.2.7 Company is genuine
plot_cooker(gjg_long, condition, SGen, "I think company is genuine")
## SIGNIFICANT ##
mod_SGen <- lmer(SGen ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SGen)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SGen ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11191.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.2489 -0.6036 0.0364 0.5927 3.5574
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.14300 1.0691
## social_issue (Intercept) 0.01935 0.1391
## Residual 1.57413 1.2546
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.405e+00 9.150e-02 7.341e+00 37.211 1.24e-09
## conditionConservative \n Signal 2.797e-01 6.399e-02 2.301e+03 4.371 1.29e-05
## conditionLiberal \n Control 6.637e-01 6.399e-02 2.301e+03 10.372 < 2e-16
## conditionLiberal \n Signal 9.799e-01 6.399e-02 2.301e+03 15.314 < 2e-16
##
## (Intercept) ***
## conditionConservative \n Signal ***
## conditionLiberal \n Control ***
## conditionLiberal \n Signal ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.350
## cndtnLbrlCn -0.350 0.500
## cndtnLbrlSg -0.350 0.500 0.5006.2.8 Reputation motive
plot_cooker(signal_gjg_long, condition, Rep, "Reputation motive")
## SIGNIFICANT ##
mod_Rep <- lmer(Rep ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Rep)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Rep ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5401.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.2477 -0.4034 0.1514 0.5805 2.1612
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.69493 0.8336
## social_issue (Intercept) 0.01872 0.1368
## Residual 1.37375 1.1721
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 5.35082 0.08586 5.20678 62.323 1.1e-08 ***
## conditionLiberal \n Signal -0.13592 0.05978 765.73216 -2.274 0.0233 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr)
## cndtnLbrlSg -0.3486.2.9 Profit motive
plot_cooker(signal_gjg_long, condition, Profit, "Profit motive")
mod_Profit <- lmer(Profit ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Profit)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Profit ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5671.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.8345 -0.4347 0.1422 0.6066 2.1534
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.01578 1.0079
## social_issue (Intercept) 0.02395 0.1547
## Residual 1.51837 1.2322
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.98874 0.09634 4.96489 51.780 5.59e-08 ***
## conditionLiberal \n Signal -0.11931 0.06284 765.93790 -1.899 0.058 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr)
## cndtnLbrlSg -0.3266.2.10 Noisy minority
plot_cooker(signal_gjg_long, condition, noisyMin, "Motive to cater to noisy minority")
## SIGNIFICANT ##
mod_noisyMin <- lmer(noisyMin ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_noisyMin)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: noisyMin ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5975
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.70483 -0.56999 -0.00067 0.58141 2.44471
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.3836 1.1763
## social_issue (Intercept) 0.1015 0.3186
## Residual 1.7605 1.3268
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.45985 0.17165 3.62257 25.983 3e-05 ***
## conditionLiberal \n Signal -0.24994 0.06767 765.97114 -3.694 0.000237 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr)
## cndtnLbrlSg -0.1976.2.11 Pressured by peer companies
plot_cooker(signal_gjg_long, condition, peerPress, "Pressured by peer companies")
mod_peerPress <- lmer(peerPress ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_peerPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: peerPress ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5811.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.62328 -0.59190 0.04645 0.61811 2.34407
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.103927 1.05068
## social_issue (Intercept) 0.002456 0.04955
## Residual 1.675204 1.29430
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.59534 0.06502 11.82908 70.67 < 2e-16 ***
## conditionLiberal \n Signal -0.38219 0.06601 766.82034 -5.79 1.03e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr)
## cndtnLbrlSg -0.5086.2.12 Pressured by public
plot_cooker(signal_gjg_long, condition, pubPress, "Pressured by public")
## SIGNIFICANT ##
mod_pubPress <- lmer(pubPress ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_pubPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: pubPress ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5858.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.7012 -0.6063 0.0366 0.6230 2.5734
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.23194 1.1099
## social_issue (Intercept) 0.05768 0.2402
## Residual 1.66303 1.2896
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.32670 0.13485 4.12230 32.085 4.2e-06 ***
## conditionLiberal \n Signal -0.24377 0.06577 765.88756 -3.706 0.000225 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr)
## cndtnLbrlSg -0.2446.2.13 Risky to NOT send signal
plot_cooker(signal_gjg_long, condition, riskInact, "Risky NOT to send signal")
mod_riskInact <- lmer(riskInact ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_riskInact)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: riskInact ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5865.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.48764 -0.61921 0.00533 0.60579 2.57312
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.9621 0.9809
## social_issue (Intercept) 0.1157 0.3401
## Residual 1.8360 1.3550
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.79627 0.18046 3.49928 21.037 8.25e-05 ***
## conditionLiberal \n Signal 0.06948 0.06911 765.94050 1.005 0.315
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr)
## cndtnLbrlSg -0.1916.2.14 I like company
plot_cooker(gjg_long, condition, SLike, "I like company")
mod_SLike <- lmer(SLike ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SLike ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 12044.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.9206 -0.6591 0.1073 0.6346 2.8131
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.86456 0.9298
## social_issue (Intercept) 0.05492 0.2344
## Residual 2.32460 1.5247
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.882e+00 1.337e-01 4.569e+00 29.037 2.33e-06
## conditionConservative \n Signal 1.359e-03 7.776e-02 2.301e+03 0.017 0.986
## conditionLiberal \n Control 6.269e-01 7.776e-02 2.301e+03 8.063 1.19e-15
## conditionLiberal \n Signal 5.790e-01 7.776e-02 2.301e+03 7.447 1.35e-13
##
## (Intercept) ***
## conditionConservative \n Signal
## conditionLiberal \n Control ***
## conditionLiberal \n Signal ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.291
## cndtnLbrlCn -0.291 0.500
## cndtnLbrlSg -0.291 0.500 0.5006.2.15 I trust company
plot_cooker(gjg_long, condition, STrust, "I trust company")
mod_STrust <- lmer(STrust ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_STrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: STrust ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11339.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.2446 -0.5459 0.0647 0.5547 3.4354
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.17526 1.0841
## social_issue (Intercept) 0.01531 0.1237
## Residual 1.65972 1.2883
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.691e+00 8.669e-02 8.871e+00 42.574 1.44e-11
## conditionConservative \n Signal 1.285e-02 6.570e-02 2.301e+03 0.196 0.845
## conditionLiberal \n Control 4.490e-01 6.570e-02 2.301e+03 6.834 1.05e-11
## conditionLiberal \n Signal 4.205e-01 6.570e-02 2.301e+03 6.400 1.88e-10
##
## (Intercept) ***
## conditionConservative \n Signal
## conditionLiberal \n Control ***
## conditionLiberal \n Signal ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.379
## cndtnLbrlCn -0.379 0.500
## cndtnLbrlSg -0.379 0.500 0.5006.2.16 I think company is competent
plot_cooker(gjg_long, condition, SComp, "I think company is competent")
mod_SComp <- lmer(SComp ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SComp ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11300.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.2967 -0.4544 0.1212 0.5710 3.2038
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.99311 0.9965
## social_issue (Intercept) 0.01881 0.1372
## Residual 1.69547 1.3021
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.44732 0.09055 7.30209 49.116
## conditionConservative \n Signal -0.03095 0.06641 2301.04809 -0.466
## conditionLiberal \n Control 0.37370 0.06641 2301.03024 5.627
## conditionLiberal \n Signal 0.39204 0.06641 2301.04809 5.904
## Pr(>|t|)
## (Intercept) 1.80e-10 ***
## conditionConservative \n Signal 0.641
## conditionLiberal \n Control 2.05e-08 ***
## conditionLiberal \n Signal 4.08e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.367
## cndtnLbrlCn -0.367 0.500
## cndtnLbrlSg -0.367 0.500 0.5006.2.17 Others like company
plot_cooker(gjg_long, condition, OLike, "Others like company")
mod_OLike <- lmer(OLike ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OLike ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9614.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5829 -0.4291 0.1192 0.5517 2.8147
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.492696 0.7019
## social_issue (Intercept) 0.008153 0.0903
## Residual 1.011049 1.0055
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 5.148e+00 6.320e-02 8.534e+00 81.457 1.22e-13
## conditionConservative \n Signal 2.612e-02 5.128e-02 2.301e+03 0.509 0.611
## conditionLiberal \n Control 3.115e-01 5.128e-02 2.301e+03 6.074 1.46e-09
## conditionLiberal \n Signal 3.428e-01 5.128e-02 2.301e+03 6.685 2.90e-11
##
## (Intercept) ***
## conditionConservative \n Signal
## conditionLiberal \n Control ***
## conditionLiberal \n Signal ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.406
## cndtnLbrlCn -0.406 0.500
## cndtnLbrlSg -0.406 0.500 0.5006.2.18 Others trust company
plot_cooker(gjg_long, condition, OTrust, "Others trust company")
mod_OTrust <- lmer(OTrust ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OTrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OTrust ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9784.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.3821 -0.4219 0.0797 0.5438 3.1316
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.613491 0.78326
## social_issue (Intercept) 0.005183 0.07199
## Residual 1.033397 1.01656
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.84386 0.05863 13.28597 82.619
## conditionConservative \n Signal -0.04743 0.05184 2301.09340 -0.915
## conditionLiberal \n Control 0.20857 0.05184 2301.05859 4.023
## conditionLiberal \n Signal 0.23583 0.05184 2301.09340 4.549
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.36
## conditionLiberal \n Control 5.93e-05 ***
## conditionLiberal \n Signal 5.67e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.442
## cndtnLbrlCn -0.442 0.500
## cndtnLbrlSg -0.442 0.500 0.5006.2.19 Others think company is competent
plot_cooker(gjg_long, condition, OComp, "Others think company is competent")
mod_OComp <- lmer(OComp ~ condition + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OComp ~ condition + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9935.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.1498 -0.4199 0.1126 0.5594 3.1420
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.61295 0.7829
## social_issue (Intercept) 0.01992 0.1411
## Residual 1.09543 1.0466
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.917e+00 8.486e-02 5.463e+00 57.941
## conditionConservative \n Signal -9.141e-03 5.338e-02 2.301e+03 -0.171
## conditionLiberal \n Control 2.699e-01 5.338e-02 2.301e+03 5.057
## conditionLiberal \n Signal 3.242e-01 5.338e-02 2.301e+03 6.074
## Pr(>|t|)
## (Intercept) 7.85e-09 ***
## conditionConservative \n Signal 0.864
## conditionLiberal \n Control 4.59e-07 ***
## conditionLiberal \n Signal 1.45e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC
## cndtnCnsrvS -0.315
## cndtnLbrlCn -0.315 0.500
## cndtnLbrlSg -0.315 0.500 0.5006.3 Political Affilliation Line
6.3.1 Static Norm
by_line(gjg_long, pol, staticNorm, "political leaning", "static norm", "Condition", "Percent of support for issue")
6.3.2 Dynamic Norm (Look into)
by_line(gjg_long, pol, dyNorm, "political leaning", "dynamic norm", "Condition", "Change in support for issue")
## SIGNIFICANT ##
mod_dyNorm <- lmer(dyNorm ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_dyNorm)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: dyNorm ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9604.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7432 -0.4408 0.0568 0.5620 4.1412
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.83022 0.9112
## social_issue (Intercept) 0.03678 0.1918
## Residual 0.88828 0.9425
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.905e+00 1.526e-01 1.800e+01 32.151
## conditionConservative \n Signal 2.045e-01 1.207e-01 2.298e+03 1.695
## conditionLiberal \n Control -3.675e-02 1.207e-01 2.298e+03 -0.304
## conditionLiberal \n Signal -4.407e-04 1.207e-01 2.298e+03 -0.004
## pol 1.512e-03 2.649e-02 1.806e+03 0.057
## conditionConservative \n Signal:pol 5.623e-03 2.694e-02 2.298e+03 0.209
## conditionLiberal \n Control:pol 3.157e-02 2.696e-02 2.298e+03 1.171
## conditionLiberal \n Signal:pol 3.619e-02 2.694e-02 2.298e+03 1.343
## Pr(>|t|)
## (Intercept) <2e-16 ***
## conditionConservative \n Signal 0.0902 .
## conditionLiberal \n Control 0.7608
## conditionLiberal \n Signal 0.9971
## pol 0.9545
## conditionConservative \n Signal:pol 0.8347
## conditionLiberal \n Control:pol 0.2417
## conditionLiberal \n Signal:pol 0.1793
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.395
## cndtnLbrlCn -0.396 0.500
## cndtnLbrlSg -0.395 0.500 0.500
## pol -0.713 0.466 0.467 0.466
## cndtnCSgnl: 0.363 -0.917 -0.459 -0.458 -0.509
## cndtnLCntr: 0.363 -0.459 -0.917 -0.459 -0.509 0.500
## cndtnLSgnl: 0.363 -0.458 -0.459 -0.917 -0.509 0.499 0.5006.3.3 Issue is important
by_line(gjg_long, pol, SImport, "political leaning", "issue importance", "Condition", "I think cause is important")
6.3.4 Issue is relatively important
by_line(gjg_long, pol, SRelImport, "political leaning", "issue relative importance", "Condition", "I think cause is important relative to other causes")
6.3.5 Message motivates others
by_line(gjg_long, pol, OMotivate, "political leaning", "", "Condition", "Message motivates others to act")
6.3.6 Surprise
by_line(gjg_long, pol, surprise, "political leaning", "", "Condition", "Surprise")
6.3.7 Company is genuine (Look into)
by_line(gjg_long, pol, SGen, "political leaning", "", "Condition", "I think company is genuine")
## Significant
mod_SGen <- lmer(SGen ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SGen)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SGen ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11145.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.4674 -0.5940 0.0322 0.6101 3.3835
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.14946 1.0721
## social_issue (Intercept) 0.01881 0.1371
## Residual 1.53306 1.2382
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.78065 0.16333 76.85336 23.147
## conditionConservative \n Signal -0.04228 0.15851 2298.39476 -0.267
## conditionLiberal \n Control -0.16805 0.15857 2298.73167 -1.060
## conditionLiberal \n Signal -0.07083 0.15851 2298.39476 -0.447
## pol -0.09150 0.03310 1979.47272 -2.765
## conditionConservative \n Signal:pol 0.07835 0.03539 2298.49620 2.214
## conditionLiberal \n Control:pol 0.20247 0.03541 2298.93897 5.717
## conditionLiberal \n Signal:pol 0.25580 0.03539 2298.49620 7.227
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.78970
## conditionLiberal \n Control 0.28936
## conditionLiberal \n Signal 0.65503
## pol 0.00575 **
## conditionConservative \n Signal:pol 0.02695 *
## conditionLiberal \n Control:pol 1.22e-08 ***
## conditionLiberal \n Signal:pol 6.68e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.485
## cndtnLbrlCn -0.485 0.500
## cndtnLbrlSg -0.485 0.500 0.500
## pol -0.832 0.490 0.491 0.490
## cndtnCSgnl: 0.445 -0.917 -0.459 -0.458 -0.535
## cndtnLCntr: 0.445 -0.459 -0.917 -0.459 -0.535 0.500
## cndtnLSgnl: 0.445 -0.458 -0.459 -0.917 -0.535 0.499 0.5006.3.8 Reputation motive
by_line(signal_gjg_long, pol, Rep, "political leaning", "", "Condition", "Reputation motive")
mod_Rep <- lmer(Rep ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Rep)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Rep ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5405.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.2719 -0.4259 0.1282 0.5907 2.1306
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.69949 0.8364
## social_issue (Intercept) 0.01913 0.1383
## Residual 1.36509 1.1684
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 5.27668 0.14732 42.78877 35.817
## conditionLiberal \n Signal 0.19508 0.14974 765.53511 1.303
## pol 0.01806 0.02905 1376.28289 0.622
## conditionLiberal \n Signal:pol -0.08059 0.03345 765.77024 -2.410
## Pr(>|t|)
## (Intercept) <2e-16 ***
## conditionLiberal \n Signal 0.1930
## pol 0.5343
## conditionLiberal \n Signal:pol 0.0162 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS pol
## cndtnLbrlSg -0.508
## pol -0.810 0.528
## cndtnLSgnl: 0.466 -0.917 -0.5766.3.9 Profit motive
by_line(signal_gjg_long, pol, Profit, "political leaning", "", "Condition", "Profit motive")
mod_Profit <- lmer(Profit ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Profit)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Profit ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5662.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.9975 -0.4813 0.1043 0.5803 2.3120
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.02896 1.0144
## social_issue (Intercept) 0.02546 0.1596
## Residual 1.48702 1.2194
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.85213 0.16427 37.48506 29.537
## conditionLiberal \n Signal 0.47211 0.15629 765.58112 3.021
## pol 0.03328 0.03206 1314.30616 1.038
## conditionLiberal \n Signal:pol -0.14401 0.03491 765.77314 -4.125
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionLiberal \n Signal 0.00261 **
## pol 0.29955
## conditionLiberal \n Signal:pol 4.11e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS pol
## cndtnLbrlSg -0.476
## pol -0.802 0.499
## cndtnLSgnl: 0.436 -0.917 -0.5446.3.10 Noisy minority
by_line(signal_gjg_long, pol, noisyMin, "political leaning", "", "Condition", "Motive to cater to noisy minority")
## SIGNIFICANT ##
mod_noisyMin <- lmer(noisyMin ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_noisyMin)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: noisyMin ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5796.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.11272 -0.55765 0.03651 0.61922 2.54500
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.9035 0.9505
## social_issue (Intercept) 0.1009 0.3176
## Residual 1.7545 1.3246
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 5.91327 0.21680 9.39334 27.275
## conditionLiberal \n Signal 0.04652 0.16979 765.19291 0.274
## pol -0.35380 0.03296 1374.83036 -10.734
## conditionLiberal \n Signal:pol -0.07219 0.03793 765.26392 -1.903
## Pr(>|t|)
## (Intercept) 2.9e-10 ***
## conditionLiberal \n Signal 0.7842
## pol < 2e-16 ***
## conditionLiberal \n Signal:pol 0.0574 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS pol
## cndtnLbrlSg -0.392
## pol -0.625 0.528
## cndtnLSgnl: 0.359 -0.917 -0.5756.3.11 Pressured by peer companies
by_line(signal_gjg_long, pol, peerPress, "political leaning", "", "Condition", "Pressured by peer companies")
mod_peerPress <- lmer(peerPress ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_peerPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: peerPress ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5762.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.70300 -0.56138 0.06176 0.64840 2.23842
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.001122 1.00056
## social_issue (Intercept) 0.001201 0.03466
## Residual 1.652413 1.28546
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 5.12223 0.14844 347.78146 34.508
## conditionLiberal \n Signal 0.13866 0.16456 766.26997 0.843
## pol -0.12823 0.03292 1342.68064 -3.896
## conditionLiberal \n Signal:pol -0.12681 0.03675 765.28554 -3.451
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionLiberal \n Signal 0.399734
## pol 0.000103 ***
## conditionLiberal \n Signal:pol 0.000589 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS pol
## cndtnLbrlSg -0.554
## pol -0.911 0.512
## cndtnLSgnl: 0.508 -0.917 -0.5586.3.12 Pressured by public
by_line(signal_gjg_long, pol, pubPress, "political leaning", "", "Condition", "Pressured by public")
## SIGNIFICANT ##
mod_pubPress <- lmer(pubPress ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_pubPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: pubPress ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5858.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.66777 -0.62153 0.03204 0.60806 2.52784
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.24292 1.1149
## social_issue (Intercept) 0.05539 0.2354
## Residual 1.64413 1.2822
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.16714 0.19368 18.81897 21.516
## conditionLiberal \n Signal 0.23130 0.16436 765.25656 1.407
## pol 0.03886 0.03435 1294.38926 1.131
## conditionLiberal \n Signal:pol -0.11567 0.03671 765.37278 -3.151
## Pr(>|t|)
## (Intercept) 1.04e-14 ***
## conditionLiberal \n Signal 0.15974
## pol 0.25817
## conditionLiberal \n Signal:pol 0.00169 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS pol
## cndtnLbrlSg -0.424
## pol -0.729 0.490
## cndtnLSgnl: 0.389 -0.917 -0.5346.3.13 Risky to NOT send signal
by_line(signal_gjg_long, pol, riskInact, "political leaning", "", "Condition", "Risky NOT to signal")
mod_riskInact <- lmer(riskInact ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_riskInact)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: riskInact ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5865.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.55187 -0.63741 0.02176 0.58295 2.51774
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.9392 0.9691
## social_issue (Intercept) 0.1159 0.3405
## Residual 1.8383 1.3558
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.455e+00 2.275e-01 8.791e+00 15.189 1.3e-07
## conditionLiberal \n Signal 3.594e-02 1.738e-01 7.651e+02 0.207 0.8362
## pol 8.297e-02 3.369e-02 1.376e+03 2.462 0.0139
## conditionLiberal \n Signal:pol 8.167e-03 3.882e-02 7.652e+02 0.210 0.8335
##
## (Intercept) ***
## conditionLiberal \n Signal
## pol *
## conditionLiberal \n Signal:pol
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS pol
## cndtnLbrlSg -0.382
## pol -0.608 0.529
## cndtnLSgnl: 0.350 -0.917 -0.5766.3.14 I like company
by_line(gjg_long, pol, SLike, "political leaning", "", "Condition", "I like company")
#SIGNIFICANT#
mod_SLike <- lmer(SLike ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SLike ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11921
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.2888 -0.6601 0.0767 0.6457 2.7586
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.88787 0.9423
## social_issue (Intercept) 0.04894 0.2212
## Residual 2.19309 1.4809
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.51794 0.19359 25.01162 23.338
## conditionConservative \n Signal -0.36069 0.18959 2298.22916 -1.902
## conditionLiberal \n Control -0.71904 0.18967 2298.43184 -3.791
## conditionLiberal \n Signal -1.23857 0.18959 2298.22916 -6.533
## pol -0.15468 0.03548 2456.88636 -4.360
## conditionConservative \n Signal:pol 0.08809 0.04233 2298.28954 2.081
## conditionLiberal \n Control:pol 0.32765 0.04236 2298.55995 7.735
## conditionLiberal \n Signal:pol 0.44250 0.04233 2298.28954 10.452
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.057238 .
## conditionLiberal \n Control 0.000154 ***
## conditionLiberal \n Signal 7.92e-11 ***
## pol 1.35e-05 ***
## conditionConservative \n Signal:pol 0.037559 *
## conditionLiberal \n Control:pol 1.53e-14 ***
## conditionLiberal \n Signal:pol < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.490
## cndtnLbrlCn -0.490 0.500
## cndtnLbrlSg -0.490 0.500 0.500
## pol -0.753 0.547 0.548 0.547
## cndtnCSgnl: 0.449 -0.917 -0.459 -0.458 -0.597
## cndtnLCntr: 0.449 -0.459 -0.917 -0.459 -0.597 0.500
## cndtnLSgnl: 0.449 -0.458 -0.459 -0.917 -0.597 0.499 0.5006.3.15 I trust company
by_line(gjg_long, pol, STrust, "political leaning", "", "Condition", "I trust company")
mod_STrust <- lmer(STrust ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_STrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: STrust ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11214.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6311 -0.5590 0.0387 0.5554 3.4384
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.18556 1.0888
## social_issue (Intercept) 0.01227 0.1108
## Residual 1.56568 1.2513
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.21131 0.16001 144.94334 26.318
## conditionConservative \n Signal -0.41880 0.16019 2298.57442 -2.614
## conditionLiberal \n Control -0.78230 0.16025 2299.04836 -4.882
## conditionLiberal \n Signal -1.13504 0.16019 2298.57442 -7.086
## pol -0.12674 0.03352 1971.51104 -3.781
## conditionConservative \n Signal:pol 0.10504 0.03577 2298.71905 2.937
## conditionLiberal \n Control:pol 0.29975 0.03579 2299.32994 8.376
## conditionLiberal \n Signal:pol 0.37870 0.03577 2298.71905 10.588
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.008996 **
## conditionLiberal \n Control 1.12e-06 ***
## conditionLiberal \n Signal 1.83e-12 ***
## pol 0.000161 ***
## conditionConservative \n Signal:pol 0.003350 **
## conditionLiberal \n Control:pol < 2e-16 ***
## conditionLiberal \n Signal:pol < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.501
## cndtnLbrlCn -0.501 0.500
## cndtnLbrlSg -0.501 0.500 0.500
## pol -0.861 0.489 0.490 0.489
## cndtnCSgnl: 0.459 -0.917 -0.459 -0.458 -0.534
## cndtnLCntr: 0.459 -0.459 -0.917 -0.459 -0.534 0.500
## cndtnLSgnl: 0.459 -0.458 -0.459 -0.917 -0.534 0.500 0.5006.3.16 I think company is competent
by_line(gjg_long, pol, SComp, "political leaning", "", "Condition", "I think company is competent")
mod_SComp <- lmer(SComp ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SComp ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11179.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6269 -0.4838 0.1039 0.5793 3.2162
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.97325 0.9865
## social_issue (Intercept) 0.01573 0.1254
## Residual 1.61285 1.2700
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.73676 0.15849 92.34788 29.887
## conditionConservative \n Signal -0.48775 0.16258 2298.47917 -3.000
## conditionLiberal \n Control -0.69323 0.16265 2298.88260 -4.262
## conditionLiberal \n Signal -1.13416 0.16258 2298.47917 -6.976
## pol -0.07046 0.03250 2154.27068 -2.168
## conditionConservative \n Signal:pol 0.11116 0.03630 2298.60139 3.062
## conditionLiberal \n Control:pol 0.25972 0.03632 2299.12694 7.151
## conditionLiberal \n Signal:pol 0.37155 0.03630 2298.60139 10.235
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.00273 **
## conditionLiberal \n Control 2.11e-05 ***
## conditionLiberal \n Signal 3.96e-12 ***
## pol 0.03027 *
## conditionConservative \n Signal:pol 0.00222 **
## conditionLiberal \n Control:pol 1.16e-12 ***
## conditionLiberal \n Signal:pol < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.513
## cndtnLbrlCn -0.513 0.500
## cndtnLbrlSg -0.513 0.500 0.500
## pol -0.842 0.512 0.513 0.512
## cndtnCSgnl: 0.470 -0.917 -0.459 -0.458 -0.559
## cndtnLCntr: 0.471 -0.459 -0.917 -0.459 -0.559 0.500
## cndtnLSgnl: 0.470 -0.458 -0.459 -0.917 -0.559 0.499 0.5006.3.17 Others like company
by_line(gjg_long, pol, OLike, "political leaning", "", "Condition", "Others like company")
mod_OLike <- lmer(OLike ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OLike ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9590.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.6067 -0.4345 0.1228 0.5567 2.8105
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.465859 0.68254
## social_issue (Intercept) 0.008111 0.09006
## Residual 1.005127 1.00256
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.865e+00 1.187e-01 1.038e+02 41.001
## conditionConservative \n Signal 3.415e-02 1.283e-01 2.299e+03 0.266
## conditionLiberal \n Control 2.633e-01 1.284e-01 2.299e+03 2.051
## conditionLiberal \n Signal -5.883e-02 1.283e-01 2.299e+03 -0.458
## pol 6.888e-02 2.451e-02 2.359e+03 2.810
## conditionConservative \n Signal:pol -1.967e-03 2.866e-02 2.299e+03 -0.069
## conditionLiberal \n Control:pol 1.171e-02 2.867e-02 2.299e+03 0.408
## conditionLiberal \n Signal:pol 9.777e-02 2.866e-02 2.299e+03 3.411
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.790196
## conditionLiberal \n Control 0.040400 *
## conditionLiberal \n Signal 0.646757
## pol 0.004993 **
## conditionConservative \n Signal:pol 0.945295
## conditionLiberal \n Control:pol 0.683010
## conditionLiberal \n Signal:pol 0.000657 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.541
## cndtnLbrlCn -0.541 0.500
## cndtnLbrlSg -0.541 0.500 0.500
## pol -0.849 0.536 0.537 0.536
## cndtnCSgnl: 0.496 -0.917 -0.459 -0.458 -0.585
## cndtnLCntr: 0.496 -0.459 -0.917 -0.459 -0.585 0.500
## cndtnLSgnl: 0.496 -0.458 -0.459 -0.917 -0.585 0.500 0.5006.3.18 Others trust company
by_line(gjg_long, pol, OTrust, "political leaning", "", "Condition", "Others trust company")
mod_OTrust <- lmer(OTrust ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OTrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OTrust ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9771.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.4892 -0.4306 0.0848 0.5543 3.1346
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.588428 0.76709
## social_issue (Intercept) 0.005171 0.07191
## Residual 1.029746 1.01476
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.62071 0.12062 219.72680 38.309
## conditionConservative \n Signal -0.11070 0.12991 2298.81136 -0.852
## conditionLiberal \n Control 0.01938 0.12995 2299.44350 0.149
## conditionLiberal \n Signal -0.13294 0.12991 2298.81136 -1.023
## pol 0.05432 0.02571 2197.66962 2.113
## conditionConservative \n Signal:pol 0.01540 0.02901 2299.00827 0.531
## conditionLiberal \n Control:pol 0.04605 0.02902 2299.79820 1.587
## conditionLiberal \n Signal:pol 0.08978 0.02901 2299.00827 3.095
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.39420
## conditionLiberal \n Control 0.88147
## conditionLiberal \n Signal 0.30624
## pol 0.03470 *
## conditionConservative \n Signal:pol 0.59561
## conditionLiberal \n Control:pol 0.11267
## conditionLiberal \n Signal:pol 0.00199 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.539
## cndtnLbrlCn -0.539 0.500
## cndtnLbrlSg -0.539 0.500 0.500
## pol -0.875 0.517 0.518 0.517
## cndtnCSgnl: 0.494 -0.917 -0.459 -0.458 -0.564
## cndtnLCntr: 0.494 -0.459 -0.917 -0.459 -0.564 0.500
## cndtnLSgnl: 0.494 -0.458 -0.459 -0.917 -0.564 0.500 0.5006.3.19 Others think company is competent
by_line(gjg_long, pol, OComp, "political leaning", "", "Condition", "Others think company is competent")
mod_OComp <- lmer(OComp ~ condition*pol + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OComp ~ condition * pol + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9924.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.1483 -0.4202 0.1013 0.5648 3.0988
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.5952 0.7715
## social_issue (Intercept) 0.0199 0.1411
## Residual 1.0896 1.0438
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.74898 0.13703 36.89535 34.655
## conditionConservative \n Signal -0.05581 0.13364 2298.27603 -0.418
## conditionLiberal \n Control 0.11238 0.13369 2298.51756 0.841
## conditionLiberal \n Signal -0.11315 0.13364 2298.27603 -0.847
## pol 0.04086 0.02623 2233.35620 1.558
## conditionConservative \n Signal:pol 0.01135 0.02984 2298.34818 0.380
## conditionLiberal \n Control:pol 0.03835 0.02986 2298.66914 1.284
## conditionLiberal \n Signal:pol 0.10648 0.02984 2298.34819 3.568
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionConservative \n Signal 0.676255
## conditionLiberal \n Control 0.400640
## conditionLiberal \n Signal 0.397252
## pol 0.119468
## conditionConservative \n Signal:pol 0.703719
## conditionLiberal \n Control:pol 0.199146
## conditionLiberal \n Signal:pol 0.000367 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS pol cndCS: cndLC:
## cndtnCnsrvS -0.488
## cndtnLbrlCn -0.488 0.500
## cndtnLbrlSg -0.488 0.500 0.500
## pol -0.786 0.522 0.522 0.522
## cndtnCSgnl: 0.447 -0.917 -0.459 -0.458 -0.569
## cndtnLCntr: 0.447 -0.459 -0.917 -0.459 -0.569 0.500
## cndtnLSgnl: 0.447 -0.458 -0.459 -0.917 -0.569 0.499 0.5006.4 Genuine Line
6.4.1 Static Norm
by_line(gjg_long, SGen, staticNorm, "Genuine", "static norm", "Condition", "Percent of support for issue")
6.4.2 Dynamic Norm
by_line(gjg_long, SGen, dyNorm, "Genuine", "dynamic norm", "Condition", "Change in support for issue")
## SIGNIFICANT ##
mod_dyNorm <- lmer(dyNorm ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_dyNorm)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: dyNorm ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9556.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5167 -0.4643 0.0496 0.5558 4.2503
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.79090 0.8893
## social_issue (Intercept) 0.03747 0.1936
## Residual 0.88155 0.9389
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.616e+00 1.353e-01 1.079e+01 34.108
## conditionConservative \n Signal 1.795e-01 1.174e-01 2.426e+03 1.529
## conditionLiberal \n Control 2.720e-02 1.316e-01 2.452e+03 0.207
## conditionLiberal \n Signal -8.605e-02 1.308e-01 2.455e+03 -0.658
## SGen 8.664e-02 2.418e-02 2.730e+03 3.583
## conditionConservative \n Signal:SGen 6.486e-03 3.035e-02 2.454e+03 0.214
## conditionLiberal \n Control:SGen 2.027e-03 3.254e-02 2.468e+03 0.062
## conditionLiberal \n Signal:SGen 3.406e-02 3.119e-02 2.473e+03 1.092
## Pr(>|t|)
## (Intercept) 2.47e-12 ***
## conditionConservative \n Signal 0.126284
## conditionLiberal \n Control 0.836230
## conditionLiberal \n Signal 0.510790
## SGen 0.000345 ***
## conditionConservative \n Signal:SGen 0.830782
## conditionLiberal \n Control:SGen 0.950336
## conditionLiberal \n Signal:SGen 0.274917
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS SGen cCS:SG cLC:SG
## cndtnCnsrvS -0.443
## cndtnLbrlCn -0.386 0.456
## cndtnLbrlSg -0.391 0.458 0.428
## SGen -0.608 0.610 0.530 0.536
## cndtnCSg:SG 0.426 -0.912 -0.433 -0.436 -0.701
## cndtnLCn:SG 0.394 -0.454 -0.927 -0.425 -0.648 0.516
## cndtnLSg:SG 0.417 -0.473 -0.438 -0.921 -0.686 0.538 0.5186.4.3 Issue is important
by_line(gjg_long, SGen, SImport, "Genuine", "issue importance", "Condition", "I think cause is important")
6.4.4 Issue is relatively important
by_line(gjg_long, SGen, SRelImport, "Genuine", "issue relative importance", "Condition", "I think cause is important relative to other causes")
6.4.5 Message motivates others
by_line(gjg_long, SGen, OMotivate, "Genuine", "", "Condition", "Message motivates others to act")
6.4.6 Surprise
by_line(gjg_long, SGen, surprise, "Genuine", "", "Condition", "Surprise")
6.4.7 Reputation motive
by_line(signal_gjg_long, SGen, Rep, "Genuine", "", "Condition", "Reputation motive")
mod_Rep <- lmer(Rep ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Rep)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Rep ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5197.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7870 -0.4374 0.1240 0.5686 2.5911
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.54408 0.7376
## social_issue (Intercept) 0.02552 0.1597
## Residual 1.23563 1.1116
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 6.35429 0.13418 18.59548 47.355
## conditionLiberal \n Signal 0.33922 0.15531 1059.37822 2.184
## SGen -0.27230 0.02618 1462.20090 -10.400
## conditionLiberal \n Signal:SGen -0.06491 0.03550 1099.98284 -1.828
## Pr(>|t|)
## (Intercept) <2e-16 ***
## conditionLiberal \n Signal 0.0292 *
## SGen <2e-16 ***
## conditionLiberal \n Signal:SGen 0.0678 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS SGen
## cndtnLbrlSg -0.456
## SGen -0.719 0.527
## cndtnLSg:SG 0.463 -0.927 -0.6446.4.8 Profit motive
by_line(signal_gjg_long, SGen, Profit, "Genuine", "", "Condition", "Profit motive")
mod_Profit <- lmer(Profit ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Profit)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Profit ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5372.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3216 -0.4953 0.1054 0.5750 2.1886
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.74027 0.8604
## social_issue (Intercept) 0.02866 0.1693
## Residual 1.29829 1.1394
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 6.32010 0.14175 18.52529 44.587
## conditionLiberal \n Signal 0.42408 0.16085 1027.95465 2.637
## SGen -0.36127 0.02751 1432.46962 -13.134
## conditionLiberal \n Signal:SGen -0.06627 0.03681 1062.19208 -1.800
## Pr(>|t|)
## (Intercept) <2e-16 ***
## conditionLiberal \n Signal 0.0085 **
## SGen <2e-16 ***
## conditionLiberal \n Signal:SGen 0.0721 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS SGen
## cndtnLbrlSg -0.444
## SGen -0.715 0.517
## cndtnLSg:SG 0.454 -0.928 -0.6346.4.9 Noisy minority
by_line(signal_gjg_long, SGen, noisyMin, "Genuine", "", "Condition", "Motive to cater to noisy minority")
## SIGNIFICANT ##
mod_noisyMin <- lmer(noisyMin ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_noisyMin)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: noisyMin ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5832.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.13545 -0.56750 0.03813 0.56813 2.50884
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.1913 1.0915
## social_issue (Intercept) 0.1008 0.3175
## Residual 1.6318 1.2774
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 5.40155 0.20604 7.60241 26.217
## conditionLiberal \n Signal 0.39891 0.18214 993.66896 2.190
## SGen -0.25557 0.03162 1394.44496 -8.083
## conditionLiberal \n Signal:SGen -0.10716 0.04173 1022.02804 -2.568
## Pr(>|t|)
## (Intercept) 9.89e-09 ***
## conditionLiberal \n Signal 0.0287 *
## SGen 1.36e-15 ***
## conditionLiberal \n Signal:SGen 0.0104 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS SGen
## cndtnLbrlSg -0.343
## SGen -0.566 0.506
## cndtnLSg:SG 0.353 -0.929 -0.6256.4.10 Pressured by peer companies
by_line(signal_gjg_long, SGen, peerPress, "Genuine", "", "Condition", "Pressured by peer companies")
mod_peerPress <- lmer(peerPress ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_peerPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: peerPress ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5556.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.10399 -0.55635 0.04393 0.58638 2.77146
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.87493 0.9354
## social_issue (Intercept) 0.01114 0.1055
## Residual 1.44115 1.2005
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 5.90671 0.13169 43.61206 44.855
## conditionLiberal \n Signal 0.12590 0.16988 1021.63469 0.741
## SGen -0.35596 0.02915 1425.32609 -12.210
## conditionLiberal \n Signal:SGen -0.05900 0.03889 1054.36225 -1.517
## Pr(>|t|)
## (Intercept) <2e-16 ***
## conditionLiberal \n Signal 0.459
## SGen <2e-16 ***
## conditionLiberal \n Signal:SGen 0.130
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS SGen
## cndtnLbrlSg -0.504
## SGen -0.816 0.515
## cndtnLSg:SG 0.516 -0.928 -0.6326.4.11 Pressured by public
by_line(signal_gjg_long, SGen, pubPress, "Genuine", "", "Condition", "Pressured by public")
## SIGNIFICANT ##
mod_pubPress <- lmer(pubPress ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_pubPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: pubPress ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5735.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.88195 -0.57408 0.04709 0.59508 2.76636
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.1998 1.0953
## social_issue (Intercept) 0.0631 0.2512
## Residual 1.4871 1.2195
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 5.30266 0.17860 10.83485 29.690
## conditionLiberal \n Signal 0.09926 0.17458 985.88206 0.569
## SGen -0.26485 0.03049 1379.33890 -8.685
## conditionLiberal \n Signal:SGen -0.03596 0.04002 1011.82312 -0.899
## Pr(>|t|)
## (Intercept) 9.97e-12 ***
## conditionLiberal \n Signal 0.570
## SGen < 2e-16 ***
## conditionLiberal \n Signal:SGen 0.369
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS SGen
## cndtnLbrlSg -0.378
## SGen -0.629 0.502
## cndtnLSg:SG 0.391 -0.929 -0.6216.4.12 Risky to NOT send signal
by_line(signal_gjg_long, SGen, riskInact, "Genuine", "", "Condition", "Risky NOT to signal")
mod_riskInact <- lmer(riskInact ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_riskInact)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: riskInact ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5874.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.51196 -0.62059 0.00991 0.60620 2.62139
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.9648 0.9822
## social_issue (Intercept) 0.1155 0.3399
## Residual 1.8363 1.3551
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.89013 0.21640 7.25269 17.976
## conditionLiberal \n Signal -0.05150 0.19068 1038.49228 -0.270
## SGen -0.02547 0.03246 1442.37955 -0.785
## conditionLiberal \n Signal:SGen 0.03165 0.04362 1074.70235 0.725
## Pr(>|t|)
## (Intercept) 2.79e-07 ***
## conditionLiberal \n Signal 0.787
## SGen 0.433
## conditionLiberal \n Signal:SGen 0.468
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS SGen
## cndtnLbrlSg -0.346
## SGen -0.553 0.520
## cndtnLSg:SG 0.352 -0.927 -0.6376.4.13 I like company
by_line(gjg_long, SGen, SLike, "Genuine", "", "Condition", "I like company")
#SIGNIFICANT#
mod_SLike <- lmer(SLike ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SLike ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11007.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.6909 -0.5911 0.0355 0.6032 3.4124
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.33658 0.5802
## social_issue (Intercept) 0.05152 0.2270
## Residual 1.80141 1.3422
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 1.89612 0.16657 12.71273 11.383
## conditionConservative \n Signal -0.57253 0.16404 2615.02401 -3.490
## conditionLiberal \n Control 0.60397 0.18312 2663.75371 3.298
## conditionLiberal \n Signal -0.16272 0.18196 2672.56300 -0.894
## SGen 0.58340 0.03230 3002.66512 18.064
## conditionConservative \n Signal:SGen 0.11146 0.04220 2680.27695 2.641
## conditionLiberal \n Control:SGen -0.08955 0.04514 2708.95216 -1.984
## conditionLiberal \n Signal:SGen 0.03881 0.04323 2721.77777 0.898
## Pr(>|t|)
## (Intercept) 4.91e-08 ***
## conditionConservative \n Signal 0.000491 ***
## conditionLiberal \n Control 0.000986 ***
## conditionLiberal \n Signal 0.371251
## SGen < 2e-16 ***
## conditionConservative \n Signal:SGen 0.008313 **
## conditionLiberal \n Control:SGen 0.047388 *
## conditionLiberal \n Signal:SGen 0.369429
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS SGen cCS:SG cLC:SG
## cndtnCnsrvS -0.502
## cndtnLbrlCn -0.447 0.457
## cndtnLbrlSg -0.450 0.459 0.422
## SGen -0.660 0.631 0.561 0.565
## cndtnCSg:SG 0.478 -0.908 -0.433 -0.435 -0.724
## cndtnLCn:SG 0.446 -0.452 -0.923 -0.416 -0.676 0.516
## cndtnLSg:SG 0.468 -0.471 -0.431 -0.918 -0.709 0.538 0.5136.4.14 I trust company
by_line(gjg_long, SGen, STrust, "Genuine", "", "Condition", "I trust company")
mod_STrust <- lmer(STrust ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_STrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: STrust ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9923.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.8607 -0.5410 0.0119 0.5423 3.9839
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.45336 0.6733
## social_issue (Intercept) 0.02061 0.1435
## Residual 1.14869 1.0718
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 1.541e+00 1.243e-01 2.335e+01 12.398
## conditionConservative \n Signal -3.585e-01 1.325e-01 2.512e+03 -2.705
## conditionLiberal \n Control 3.358e-01 1.482e-01 2.552e+03 2.266
## conditionLiberal \n Signal -2.098e-01 1.473e-01 2.558e+03 -1.424
## SGen 6.312e-01 2.664e-02 2.900e+03 23.695
## conditionConservative \n Signal:SGen 5.286e-02 3.418e-02 2.559e+03 1.547
## conditionLiberal \n Control:SGen -7.518e-02 3.660e-02 2.583e+03 -2.054
## conditionLiberal \n Signal:SGen 2.682e-03 3.507e-02 2.592e+03 0.076
## Pr(>|t|)
## (Intercept) 9.32e-12 ***
## conditionConservative \n Signal 0.00688 **
## conditionLiberal \n Control 0.02356 *
## conditionLiberal \n Signal 0.15460
## SGen < 2e-16 ***
## conditionConservative \n Signal:SGen 0.12209
## conditionLiberal \n Control:SGen 0.04007 *
## conditionLiberal \n Signal:SGen 0.93906
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS SGen cCS:SG cLC:SG
## cndtnCnsrvS -0.544
## cndtnLbrlCn -0.480 0.457
## cndtnLbrlSg -0.484 0.459 0.425
## SGen -0.729 0.621 0.547 0.552
## cndtnCSg:SG 0.520 -0.910 -0.433 -0.435 -0.713
## cndtnLCn:SG 0.484 -0.453 -0.925 -0.420 -0.663 0.516
## cndtnLSg:SG 0.510 -0.472 -0.434 -0.920 -0.699 0.538 0.5166.4.15 I think company is competent
by_line(gjg_long, SGen, SComp, "Genuine", "", "Condition", "I think company is competent")
mod_SComp <- lmer(SComp ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SComp ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 10229.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.1409 -0.5099 0.0426 0.5702 3.7776
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.51985 0.7210
## social_issue (Intercept) 0.02359 0.1536
## Residual 1.26022 1.1226
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.62066 0.13142 22.36885 19.942
## conditionConservative \n Signal -0.50299 0.13890 2514.92923 -3.621
## conditionLiberal \n Control 0.31778 0.15537 2554.24630 2.045
## conditionLiberal \n Signal -0.24586 0.15445 2559.63664 -1.592
## SGen 0.53650 0.02796 2895.38518 19.188
## conditionConservative \n Signal:SGen 0.08739 0.03583 2561.08696 2.439
## conditionLiberal \n Control:SGen -0.07380 0.03837 2583.66667 -1.923
## conditionLiberal \n Signal:SGen 0.02559 0.03677 2592.60541 0.696
## Pr(>|t|)
## (Intercept) 9.73e-16 ***
## conditionConservative \n Signal 0.000299 ***
## conditionLiberal \n Control 0.040932 *
## conditionLiberal \n Signal 0.111556
## SGen < 2e-16 ***
## conditionConservative \n Signal:SGen 0.014798 *
## conditionLiberal \n Control:SGen 0.054542 .
## conditionLiberal \n Signal:SGen 0.486481
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS SGen cCS:SG cLC:SG
## cndtnCnsrvS -0.539
## cndtnLbrlCn -0.476 0.457
## cndtnLbrlSg -0.480 0.459 0.425
## SGen -0.724 0.621 0.546 0.551
## cndtnCSg:SG 0.516 -0.910 -0.433 -0.435 -0.712
## cndtnLCn:SG 0.480 -0.453 -0.925 -0.421 -0.662 0.516
## cndtnLSg:SG 0.506 -0.472 -0.435 -0.920 -0.698 0.538 0.5166.4.16 Others like company
by_line(gjg_long, SGen, OLike, "Genuine", "", "Condition", "Others like company")
mod_OLike <- lmer(OLike ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OLike ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9357.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.6369 -0.4502 0.0991 0.5595 3.2286
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.4073 0.6382
## social_issue (Intercept) 0.0124 0.1113
## Residual 0.9419 0.9705
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.41527 0.10794 34.76073 40.905
## conditionConservative \n Signal -0.28847 0.12017 2510.81246 -2.401
## conditionLiberal \n Control 0.33977 0.13443 2549.61300 2.528
## conditionLiberal \n Signal 0.20827 0.13364 2554.48781 1.558
## SGen 0.21516 0.02422 2887.72513 8.883
## conditionConservative \n Signal:SGen 0.06904 0.03100 2555.70978 2.227
## conditionLiberal \n Control:SGen -0.04209 0.03320 2578.04084 -1.268
## conditionLiberal \n Signal:SGen -0.01739 0.03182 2586.44314 -0.546
## Pr(>|t|)
## (Intercept) <2e-16 ***
## conditionConservative \n Signal 0.0164 *
## conditionLiberal \n Control 0.0115 *
## conditionLiberal \n Signal 0.1193
## SGen <2e-16 ***
## conditionConservative \n Signal:SGen 0.0260 *
## conditionLiberal \n Control:SGen 0.2051
## conditionLiberal \n Signal:SGen 0.5848
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS SGen cCS:SG cLC:SG
## cndtnCnsrvS -0.568
## cndtnLbrlCn -0.501 0.457
## cndtnLbrlSg -0.505 0.459 0.425
## SGen -0.764 0.620 0.545 0.550
## cndtnCSg:SG 0.544 -0.910 -0.433 -0.435 -0.712
## cndtnLCn:SG 0.505 -0.453 -0.925 -0.421 -0.662 0.516
## cndtnLSg:SG 0.533 -0.472 -0.435 -0.920 -0.697 0.538 0.5166.4.17 Others trust company
by_line(gjg_long, SGen, OTrust, "Genuine", "", "Condition", "Others trust company")
mod_OTrust <- lmer(OTrust ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OTrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OTrust ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9417.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.0481 -0.4691 0.0739 0.5492 2.9697
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.469086 0.68490
## social_issue (Intercept) 0.009684 0.09841
## Residual 0.938234 0.96862
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.90749 0.10540 49.04918 37.074
## conditionConservative \n Signal -0.27519 0.12019 2491.12975 -2.290
## conditionLiberal \n Control 0.09752 0.13450 2527.95978 0.725
## conditionLiberal \n Signal 0.14618 0.13373 2532.07220 1.093
## SGen 0.27502 0.02433 2859.04169 11.304
## conditionConservative \n Signal:SGen 0.04094 0.03102 2532.51478 1.320
## conditionLiberal \n Control:SGen -0.01760 0.03323 2553.56049 -0.530
## conditionLiberal \n Signal:SGen -0.04100 0.03185 2561.11117 -1.287
## Pr(>|t|)
## (Intercept) <2e-16 ***
## conditionConservative \n Signal 0.0221 *
## conditionLiberal \n Control 0.4685
## conditionLiberal \n Signal 0.2744
## SGen <2e-16 ***
## conditionConservative \n Signal:SGen 0.1870
## conditionLiberal \n Control:SGen 0.5963
## conditionLiberal \n Signal:SGen 0.1981
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS SGen cCS:SG cLC:SG
## cndtnCnsrvS -0.582
## cndtnLbrlCn -0.512 0.457
## cndtnLbrlSg -0.517 0.459 0.426
## SGen -0.786 0.618 0.542 0.548
## cndtnCSg:SG 0.557 -0.911 -0.433 -0.435 -0.709
## cndtnLCn:SG 0.517 -0.453 -0.926 -0.422 -0.659 0.516
## cndtnLSg:SG 0.546 -0.472 -0.435 -0.920 -0.695 0.538 0.5166.4.18 Others think company is competent
by_line(gjg_long, SGen, OComp, "Genuine", "", "Condition", "Others think company is competent")
mod_OComp <- lmer(OComp ~ condition*SGen + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OComp ~ condition * SGen + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9555.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2155 -0.4548 0.0885 0.5607 2.8709
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.46833 0.6843
## social_issue (Intercept) 0.02507 0.1583
## Residual 0.98958 0.9948
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.95337 0.12396 16.26101 31.892
## conditionConservative \n Signal -0.24326 0.12334 2498.51739 -1.972
## conditionLiberal \n Control 0.25817 0.13802 2535.50455 1.871
## conditionLiberal \n Signal 0.09834 0.13721 2540.54080 0.717
## SGen 0.28297 0.02493 2869.51973 11.350
## conditionConservative \n Signal:SGen 0.04206 0.03183 2541.11346 1.321
## conditionLiberal \n Control:SGen -0.04329 0.03410 2562.08397 -1.270
## conditionLiberal \n Signal:SGen -0.01170 0.03267 2570.50669 -0.358
## Pr(>|t|)
## (Intercept) 4.29e-16 ***
## conditionConservative \n Signal 0.0487 *
## conditionLiberal \n Control 0.0615 .
## conditionLiberal \n Signal 0.4736
## SGen < 2e-16 ***
## conditionConservative \n Signal:SGen 0.1865
## conditionLiberal \n Control:SGen 0.2043
## conditionLiberal \n Signal:SGen 0.7202
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS SGen cCS:SG cLC:SG
## cndtnCnsrvS -0.508
## cndtnLbrlCn -0.447 0.457
## cndtnLbrlSg -0.451 0.459 0.426
## SGen -0.685 0.619 0.543 0.549
## cndtnCSg:SG 0.486 -0.911 -0.433 -0.435 -0.710
## cndtnLCn:SG 0.452 -0.453 -0.926 -0.421 -0.660 0.516
## cndtnLSg:SG 0.476 -0.472 -0.435 -0.920 -0.696 0.538 0.5166.5 Surprise Line
6.5.1 Static Norm
by_line(gjg_long, surprise, staticNorm, "surprise", "static norm", "Condition", "Percent of support for issue")
6.5.2 Dynamic Norm (Look into)
by_line(gjg_long, surprise, dyNorm, "surprise", "dynamic norm", "Condition", "Change in support for issue")
## SIGNIFICANT ##
mod_dyNorm <- lmer(dyNorm ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_dyNorm)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: dyNorm ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9607.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7561 -0.4485 0.0599 0.5538 4.0879
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.83020 0.9112
## social_issue (Intercept) 0.03644 0.1909
## Residual 0.88914 0.9429
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 4.955e+00 1.263e-01 8.620e+00
## conditionConservative \n Signal 1.560e-01 1.149e-01 2.495e+03
## conditionLiberal \n Control 9.418e-02 9.924e-02 2.438e+03
## conditionLiberal \n Signal 1.426e-01 1.017e-01 2.465e+03
## surprise -1.479e-02 2.289e-02 2.652e+03
## conditionConservative \n Signal:surprise 2.123e-02 2.903e-02 2.539e+03
## conditionLiberal \n Control:surprise -3.943e-03 3.252e-02 2.480e+03
## conditionLiberal \n Signal:surprise 1.312e-03 3.084e-02 2.512e+03
## t value Pr(>|t|)
## (Intercept) 39.230 5.1e-11 ***
## conditionConservative \n Signal 1.357 0.175
## conditionLiberal \n Control 0.949 0.343
## conditionLiberal \n Signal 1.403 0.161
## surprise -0.646 0.518
## conditionConservative \n Signal:surprise 0.731 0.465
## conditionLiberal \n Control:surprise -0.121 0.904
## conditionLiberal \n Signal:surprise 0.043 0.966
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS surprs cndCS: cndLC:
## cndtnCnsrvS -0.369
## cndtnLbrlCn -0.425 0.459
## cndtnLbrlSg -0.423 0.456 0.527
## surprise -0.537 0.539 0.619 0.620
## cndtnCSgnl: 0.398 -0.890 -0.481 -0.480 -0.741
## cndtnLCntr: 0.334 -0.365 -0.869 -0.422 -0.622 0.488
## cndtnLSgnl: 0.369 -0.396 -0.459 -0.881 -0.687 0.533 0.4706.5.3 Issue is important
by_line(gjg_long, surprise, SImport, "surprise", "issue importance", "Condition", "I think cause is important")
6.5.4 Issue is relatively important
by_line(gjg_long, surprise, SRelImport, "surprise", "issue relative importance", "Condition", "I think cause is important relative to other causes")
6.5.5 Message motivates others
by_line(gjg_long, surprise, OMotivate, "surprise", "", "Condition", "Message motivates others to act")
6.5.6 Genuine
by_line(gjg_long, surprise, SGen, "surprise", "", "Condition", "I think the company is genuine")
6.5.7 Reputation motive
by_line(signal_gjg_long, surprise, Rep, "surprise", "", "Condition", "Reputation motive")
mod_Rep <- lmer(Rep ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Rep)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Rep ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5400.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.4365 -0.3992 0.1159 0.6072 2.3004
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.68850 0.8298
## social_issue (Intercept) 0.02808 0.1676
## Residual 1.36473 1.1682
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 5.01330 0.14686 21.38348 34.136
## conditionLiberal \n Signal 0.04984 0.14458 1181.70117 0.345
## surprise 0.07839 0.02531 1407.77568 3.098
## conditionLiberal \n Signal:surprise -0.02501 0.03701 1260.96416 -0.676
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionLiberal \n Signal 0.73038
## surprise 0.00199 **
## conditionLiberal \n Signal:surprise 0.49935
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS surprs
## cndtnLbrlSg -0.615
## surprise -0.742 0.716
## cndtnLSgnl: 0.469 -0.889 -0.6326.5.8 Profit motive
by_line(signal_gjg_long, surprise, Profit, "surprise", "", "Condition", "Profit motive")
mod_Profit <- lmer(Profit ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_Profit)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Profit ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5664.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.8738 -0.4728 0.1008 0.5871 2.2050
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.00013 1.0001
## social_issue (Intercept) 0.03622 0.1903
## Residual 1.50561 1.2270
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.63125 0.16158 18.85272 28.662
## conditionLiberal \n Signal -0.03023 0.15432 1138.19978 -0.196
## surprise 0.08305 0.02727 1361.43771 3.045
## conditionLiberal \n Signal:surprise 0.01143 0.03961 1206.45332 0.289
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionLiberal \n Signal 0.84473
## surprise 0.00237 **
## conditionLiberal \n Signal:surprise 0.77301
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS surprs
## cndtnLbrlSg -0.599
## surprise -0.727 0.717
## cndtnLSgnl: 0.456 -0.892 -0.6286.5.9 Noisy minority
by_line(signal_gjg_long, surprise, noisyMin, "surprise", "", "Condition", "Motive to cater to noisy minority")
## SIGNIFICANT ##
mod_noisyMin <- lmer(noisyMin ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_noisyMin)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: noisyMin ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5954
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.93785 -0.54689 0.02711 0.58527 2.67693
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.39086 1.1793
## social_issue (Intercept) 0.07583 0.2754
## Residual 1.71000 1.3077
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.97383 0.19826 10.98187 20.043
## conditionLiberal \n Signal -0.18978 0.16650 1103.50842 -1.140
## surprise 0.11290 0.02966 1327.51667 3.806
## conditionLiberal \n Signal:surprise 0.03702 0.04282 1163.03410 0.865
## Pr(>|t|)
## (Intercept) 5.35e-10 ***
## conditionLiberal \n Signal 0.254602
## surprise 0.000148 ***
## conditionLiberal \n Signal:surprise 0.387482
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS surprs
## cndtnLbrlSg -0.529
## surprise -0.644 0.717
## cndtnLSgnl: 0.402 -0.893 -0.6246.5.10 Pressured by peer companies
by_line(signal_gjg_long, surprise, peerPress, "surprise", "", "Condition", "Pressured by peer companies")
mod_peerPress <- lmer(peerPress ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_peerPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: peerPress ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5784
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.95814 -0.56950 0.05072 0.62115 2.62773
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.083760 1.04104
## social_issue (Intercept) 0.007382 0.08592
## Residual 1.631192 1.27718
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 4.006e+00 1.417e-01 8.981e+01 28.270
## conditionLiberal \n Signal -1.788e-01 1.601e-01 1.118e+03 -1.116
## surprise 1.367e-01 2.815e-02 1.108e+03 4.855
## conditionLiberal \n Signal:surprise -9.948e-04 4.115e-02 1.199e+03 -0.024
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## conditionLiberal \n Signal 0.264
## surprise 1.38e-06 ***
## conditionLiberal \n Signal:surprise 0.981
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS surprs
## cndtnLbrlSg -0.705
## surprise -0.856 0.715
## cndtnLSgnl: 0.536 -0.891 -0.6266.5.11 Pressured by public
by_line(signal_gjg_long, surprise, pubPress, "surprise", "", "Condition", "Pressured by public")
## SIGNIFICANT ##
mod_pubPress <- lmer(pubPress ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_pubPress)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: pubPress ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5835.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.98878 -0.62048 0.03853 0.60896 2.84585
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.19390 1.0927
## social_issue (Intercept) 0.07368 0.2714
## Residual 1.63573 1.2790
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.81622 0.19338 10.91481 19.734
## conditionLiberal \n Signal -0.14280 0.16182 1121.82175 -0.882
## surprise 0.11856 0.02872 1351.74829 4.129
## conditionLiberal \n Signal:surprise 0.02558 0.04157 1185.77503 0.615
## Pr(>|t|)
## (Intercept) 6.92e-10 ***
## conditionLiberal \n Signal 0.378
## surprise 3.87e-05 ***
## conditionLiberal \n Signal:surprise 0.538
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS surprs
## cndtnLbrlSg -0.527
## surprise -0.640 0.717
## cndtnLSgnl: 0.401 -0.892 -0.6266.5.12 Risky to NOT send signal
by_line(signal_gjg_long, surprise, riskInact, "surprise", "", "Condition", "Risky NOT to signal")
mod_riskInact <- lmer(riskInact ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_riskInact)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: riskInact ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 5872.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.41796 -0.62013 0.02981 0.61062 2.51460
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.9742 0.9870
## social_issue (Intercept) 0.1117 0.3342
## Residual 1.8274 1.3518
## Number of obs: 1538, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 3.88836 0.21839 7.98408 17.805
## conditionLiberal \n Signal 0.11626 0.16796 1171.44739 0.692
## surprise -0.02139 0.02949 1412.91957 -0.725
## conditionLiberal \n Signal:surprise -0.02750 0.04301 1248.12121 -0.639
## Pr(>|t|)
## (Intercept) 1.04e-07 ***
## conditionLiberal \n Signal 0.489
## surprise 0.468
## conditionLiberal \n Signal:surprise 0.523
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtLS surprs
## cndtnLbrlSg -0.482
## surprise -0.582 0.717
## cndtnLSgnl: 0.367 -0.890 -0.6326.5.13 I like company
by_line(gjg_long, surprise, SLike, "surprise", "", "Condition", "I like company")
#SIGNIFICANT#
mod_SLike <- lmer(SLike ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SLike ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 12034.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.0445 -0.6414 0.1051 0.6362 2.7599
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.90013 0.9488
## social_issue (Intercept) 0.03961 0.1990
## Residual 2.28637 1.5121
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 4.01221 0.15863 16.58228
## conditionConservative \n Signal 0.52353 0.18104 2630.43473
## conditionLiberal \n Control 0.63345 0.15715 2535.41547
## conditionLiberal \n Signal 0.65136 0.16057 2581.40846
## surprise -0.04378 0.03556 2846.75346
## conditionConservative \n Signal:surprise -0.10757 0.04555 2702.89392
## conditionLiberal \n Control:surprise -0.01269 0.05130 2610.75026
## conditionLiberal \n Signal:surprise -0.02733 0.04850 2663.40145
## t value Pr(>|t|)
## (Intercept) 25.293 1.11e-14 ***
## conditionConservative \n Signal 2.892 0.00386 **
## conditionLiberal \n Control 4.031 5.72e-05 ***
## conditionLiberal \n Signal 4.057 5.13e-05 ***
## surprise -1.231 0.21838
## conditionConservative \n Signal:surprise -2.362 0.01826 *
## conditionLiberal \n Control:surprise -0.247 0.80467
## conditionLiberal \n Signal:surprise -0.563 0.57321
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS surprs cndCS: cndLC:
## cndtnCnsrvS -0.465
## cndtnLbrlCn -0.534 0.462
## cndtnLbrlSg -0.531 0.458 0.527
## surprise -0.665 0.544 0.624 0.623
## cndtnCSgnl: 0.495 -0.887 -0.482 -0.479 -0.745
## cndtnLCntr: 0.422 -0.367 -0.866 -0.421 -0.634 0.493
## cndtnLSgnl: 0.461 -0.396 -0.457 -0.877 -0.694 0.535 0.4716.5.14 I trust company
by_line(gjg_long, surprise, STrust, "surprise", "", "Condition", "I trust company")
mod_STrust <- lmer(STrust ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_STrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: STrust ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11323.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3944 -0.5558 0.0500 0.5522 3.5233
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.213971 1.10180
## social_issue (Intercept) 0.007729 0.08792
## Residual 1.627655 1.27580
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.812e+00 1.179e-01 8.967e+01
## conditionConservative \n Signal 5.376e-01 1.548e-01 2.524e+03
## conditionLiberal \n Control 4.983e-01 1.339e-01 2.456e+03
## conditionLiberal \n Signal 4.023e-01 1.370e-01 2.489e+03
## surprise -4.092e-02 3.070e-02 2.679e+03
## conditionConservative \n Signal:surprise -1.091e-01 3.908e-02 2.575e+03
## conditionLiberal \n Control:surprise -2.978e-02 4.384e-02 2.506e+03
## conditionLiberal \n Signal:surprise 4.682e-03 4.153e-02 2.545e+03
## t value Pr(>|t|)
## (Intercept) 32.319 < 2e-16 ***
## conditionConservative \n Signal 3.473 0.000524 ***
## conditionLiberal \n Control 3.722 0.000202 ***
## conditionLiberal \n Signal 2.936 0.003354 **
## surprise -1.333 0.182669
## conditionConservative \n Signal:surprise -2.791 0.005291 **
## conditionLiberal \n Control:surprise -0.679 0.497010
## conditionLiberal \n Signal:surprise 0.113 0.910245
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS surprs cndCS: cndLC:
## cndtnCnsrvS -0.534
## cndtnLbrlCn -0.613 0.460
## cndtnLbrlSg -0.610 0.457 0.527
## surprise -0.772 0.542 0.621 0.621
## cndtnCSgnl: 0.574 -0.890 -0.481 -0.480 -0.743
## cndtnLCntr: 0.483 -0.366 -0.868 -0.422 -0.626 0.489
## cndtnLSgnl: 0.531 -0.397 -0.459 -0.880 -0.689 0.534 0.4706.5.15 I think company is competent
by_line(gjg_long, surprise, SComp, "surprise", "", "Condition", "I think company is competent")
mod_SComp <- lmer(SComp ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_SComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: SComp ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 11279.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.4450 -0.4539 0.1098 0.5743 3.1404
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 1.014316 1.00713
## social_issue (Intercept) 0.009734 0.09866
## Residual 1.664304 1.29008
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 4.68707 0.11946 65.86684
## conditionConservative \n Signal 0.34905 0.15592 2561.29721
## conditionLiberal \n Control 0.38981 0.13499 2484.79573
## conditionLiberal \n Signal 0.17102 0.13810 2522.02980
## surprise -0.08089 0.03083 2738.96070
## conditionConservative \n Signal:surprise -0.06303 0.03932 2618.60683
## conditionLiberal \n Control:surprise -0.02527 0.04416 2542.33376
## conditionLiberal \n Signal:surprise 0.07435 0.04181 2585.50021
## t value Pr(>|t|)
## (Intercept) 39.235 < 2e-16 ***
## conditionConservative \n Signal 2.239 0.02527 *
## conditionLiberal \n Control 2.888 0.00392 **
## conditionLiberal \n Signal 1.238 0.21568
## surprise -2.624 0.00874 **
## conditionConservative \n Signal:surprise -1.603 0.10906
## conditionLiberal \n Control:surprise -0.572 0.56732
## conditionLiberal \n Signal:surprise 1.778 0.07550 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS surprs cndCS: cndLC:
## cndtnCnsrvS -0.532
## cndtnLbrlCn -0.610 0.460
## cndtnLbrlSg -0.607 0.457 0.527
## surprise -0.765 0.543 0.622 0.621
## cndtnCSgnl: 0.569 -0.889 -0.481 -0.480 -0.744
## cndtnLCntr: 0.481 -0.366 -0.868 -0.422 -0.628 0.490
## cndtnLSgnl: 0.528 -0.397 -0.458 -0.879 -0.690 0.534 0.4706.5.16 Others like company
by_line(gjg_long, surprise, OLike, "surprise", "", "Condition", "Others like company")
mod_OLike <- lmer(OLike ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OLike)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OLike ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9595.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7236 -0.4240 0.1257 0.5595 2.7352
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.480650 0.69329
## social_issue (Intercept) 0.004616 0.06794
## Residual 1.001597 1.00080
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 5.37030 0.08954 83.63520
## conditionConservative \n Signal 0.02019 0.12033 2602.86342
## conditionLiberal \n Control 0.44238 0.10434 2515.85983
## conditionLiberal \n Signal 0.18501 0.10666 2558.29884
## surprise -0.07502 0.02369 2789.86823
## conditionConservative \n Signal:surprise 0.02470 0.03031 2667.56271
## conditionLiberal \n Control:surprise -0.07167 0.03410 2582.49289
## conditionLiberal \n Signal:surprise 0.05225 0.03225 2631.51683
## t value Pr(>|t|)
## (Intercept) 59.979 < 2e-16 ***
## conditionConservative \n Signal 0.168 0.86677
## conditionLiberal \n Control 4.240 2.32e-05 ***
## conditionLiberal \n Signal 1.735 0.08294 .
## surprise -3.166 0.00156 **
## conditionConservative \n Signal:surprise 0.815 0.41518
## conditionLiberal \n Control:surprise -2.102 0.03566 *
## conditionLiberal \n Signal:surprise 1.620 0.10538
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS surprs cndCS: cndLC:
## cndtnCnsrvS -0.548
## cndtnLbrlCn -0.629 0.461
## cndtnLbrlSg -0.625 0.458 0.527
## surprise -0.785 0.545 0.624 0.622
## cndtnCSgnl: 0.585 -0.888 -0.481 -0.480 -0.745
## cndtnLCntr: 0.496 -0.367 -0.867 -0.422 -0.632 0.492
## cndtnLSgnl: 0.543 -0.397 -0.458 -0.878 -0.692 0.535 0.4716.5.17 Others trust company
by_line(gjg_long, surprise, OTrust, "surprise", "", "Condition", "Others trust company")
mod_OTrust <- lmer(OTrust ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OTrust)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OTrust ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9793.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.4521 -0.4320 0.0920 0.5421 3.1943
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.61194 0.78227
## social_issue (Intercept) 0.00349 0.05908
## Residual 1.03049 1.01513
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 4.97469 0.09035 126.41982
## conditionConservative \n Signal -0.03233 0.12261 2567.58965
## conditionLiberal \n Control 0.27087 0.10618 2489.74023
## conditionLiberal \n Signal 0.08975 0.10860 2527.78500
## surprise -0.04412 0.02422 2725.19285
## conditionConservative \n Signal:surprise 0.01023 0.03092 2625.37924
## conditionLiberal \n Control:surprise -0.03603 0.03473 2548.04415
## conditionLiberal \n Signal:surprise 0.04950 0.03288 2592.15845
## t value Pr(>|t|)
## (Intercept) 55.060 <2e-16 ***
## conditionConservative \n Signal -0.264 0.7920
## conditionLiberal \n Control 2.551 0.0108 *
## conditionLiberal \n Signal 0.826 0.4086
## surprise -1.822 0.0685 .
## conditionConservative \n Signal:surprise 0.331 0.7409
## conditionLiberal \n Control:surprise -1.037 0.2996
## conditionLiberal \n Signal:surprise 1.506 0.1323
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS surprs cndCS: cndLC:
## cndtnCnsrvS -0.553
## cndtnLbrlCn -0.634 0.461
## cndtnLbrlSg -0.630 0.458 0.527
## surprise -0.795 0.544 0.623 0.621
## cndtnCSgnl: 0.592 -0.889 -0.481 -0.480 -0.745
## cndtnLCntr: 0.500 -0.366 -0.867 -0.422 -0.629 0.491
## cndtnLSgnl: 0.549 -0.397 -0.458 -0.879 -0.691 0.534 0.4716.5.18 Others think company is competent
by_line(gjg_long, surprise, OComp, "surprise", "", "Condition", "Others think company is competent")
mod_OComp <- lmer(OComp ~ condition*surprise + (1 | PID) + (1 | social_issue), data = gjg_long)
summary(mod_OComp)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OComp ~ condition * surprise + (1 | PID) + (1 | social_issue)
## Data: gjg_long
##
## REML criterion at convergence: 9932.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.1360 -0.4255 0.0986 0.5651 3.2590
##
## Random effects:
## Groups Name Variance Std.Dev.
## PID (Intercept) 0.61156 0.7820
## social_issue (Intercept) 0.01491 0.1221
## Residual 1.08720 1.0427
## Number of obs: 3076, groups: PID, 769; social_issue, 4
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 5.03950 0.10663 23.00778
## conditionConservative \n Signal 0.12926 0.12583 2575.15937
## conditionLiberal \n Control 0.42029 0.10898 2495.86919
## conditionLiberal \n Signal 0.19461 0.11147 2534.32916
## surprise -0.04139 0.02486 2769.70132
## conditionConservative \n Signal:surprise -0.01925 0.03172 2635.22855
## conditionLiberal \n Control:surprise -0.07195 0.03564 2556.36908
## conditionLiberal \n Signal:surprise 0.04385 0.03374 2600.80897
## t value Pr(>|t|)
## (Intercept) 47.263 < 2e-16 ***
## conditionConservative \n Signal 1.027 0.304418
## conditionLiberal \n Control 3.857 0.000118 ***
## conditionLiberal \n Signal 1.746 0.080964 .
## surprise -1.665 0.096075 .
## conditionConservative \n Signal:surprise -0.607 0.543961
## conditionLiberal \n Control:surprise -2.019 0.043610 *
## conditionLiberal \n Signal:surprise 1.300 0.193793
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) cndtCS cndtLC cndtLS surprs cndCS: cndLC:
## cndtnCnsrvS -0.480
## cndtnLbrlCn -0.552 0.460
## cndtnLbrlSg -0.549 0.457 0.527
## surprise -0.691 0.542 0.622 0.622
## cndtnCSgnl: 0.514 -0.889 -0.481 -0.480 -0.744
## cndtnLCntr: 0.435 -0.366 -0.867 -0.422 -0.629 0.491
## cndtnLSgnl: 0.478 -0.397 -0.458 -0.879 -0.691 0.534 0.470
6.6 Social Issue Facet
6.6.1 Static Norm
6.6.2 Dynamic Norm
6.6.3 Issue is important
6.6.4 Issue is relatively important
6.6.5 Message motivates others
6.6.6 Surprise
6.6.7 Company is genuine
6.6.8 Reputation motive
6.6.9 Profit motive
6.6.10 Noisy minority
6.6.11 Pressured by peer companies
6.6.12 Pressured by public
6.6.13 Risky to NOT send signal
6.6.14 I like company
6.6.15 I trust company
6.6.16 I think company is competent
6.6.17 Others like company
6.6.18 Others trust company
6.6.19 Others think company is competent