1 Overview & Methodology

Study of third party judgments of donors motivated by a justice or generosity virtue
Data collected March 13th, 2023
N = 200
Respondents were psuedo-randomly asssigned (random assignment was fixed to be even across participants) to one of 2 conditions, which each contained 16 messages (shown in random order) about a donor donating to a local charity. Participant made a series of ratings (randomized) on each of the messages they were shown.
Survey took about 25 minutes on average for participants to complete

2 Key Findings

Participants show a small but significant anti-justice motive bias

3 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", "datawizard",
    "easyStats", "cowplot")

#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)

3.1 Load Data

# read in data files
setwd("~/Desktop")
gjg <-read.csv("/Users/mtrenfield17/Desktop/generosity_justice_pilot_RENAMED.csv")

3.2 Functions

plot_cooker <- function(dv, iv, Title, x_axis_labs, y_label, sample_size) {
  part1 <- ggviolin(gjg_wide, x = dv, y = iv, color = dv,
                    alpha = 0.1, fill = dv, xlab = "Motive",
                    trim = TRUE, ylab = y_label) +
    stat_summary(fun.data = "mean_cl_normal", geom = "crossbar", fatten = 1) +
    scale_y_continuous(breaks = c(1:7)) +
    labs(title = paste0(Title, " (n = ", sample_size, ")")) +
    scale_x_discrete(labels = x_axis_labs) +
    theme(panel.background = element_rect(fill = "transparent"), 
          legend.position = "right",  ## Consider “gray97” for fill
          plot.title = element_text(face = "bold", hjust = 0.5, size = 16), 
          plot.subtitle = element_text(hjust = 0.5),
          panel.grid.major.y = element_line(color='grey75'), 
          axis.text.x = element_text(face = "plain", size = 13, color = "black"),
          axis.text.y = element_text(face = "plain", size = 13, color = "black"),
          axis.title.y = element_text(face = "plain", size = 13, color = "black", 
                                       margin = margin(t = 0, r = 10, b = 0, l = 0)), ## lower X axis title
          panel.border = element_rect(color = "black", fill = NA, size = 1))
  ggpar(part1, legend = "none")
}

lizy_cooker <- function(dv, iv, Title, x_axis_labs, y_label, sample_size, coln, rown) {
  part1 <- ggviolin(gjg_wide, x = dv, y = iv, color = dv,
                    alpha = 0.1, fill = dv, xlab = "Motive",
                    trim = TRUE, ylab = y_label) +
    stat_summary(fun.data = "mean_cl_normal", geom = "crossbar", fatten = 1) +
    scale_y_continuous(breaks = c(1:7)) +
    labs(title = paste0(Title, " (n = ", sample_size, ")")) +
    theme(panel.background = element_rect(fill = "transparent"), 
          legend.position = "right",  ## Consider “gray97” for fill
          plot.title = element_text(face = "bold", hjust = 0.5, size = 16), 
          plot.subtitle = element_text(hjust = 0.5),
          panel.grid.major.y = element_line(color='grey75'), 
          axis.text.x = element_text(face = "plain", size = 13, color = "black"),
          axis.text.y = element_text(face = "plain", size = 13, color = "black"),
          axis.title.y = element_text(face = "plain", size = 13, color = "black", 
                                       margin = margin(t = 0, r = 10, b = 0, l = 0)), ## lower X axis title
          panel.border = element_rect(color = "black", fill = NA, size = 1)) +
  scale_color_discrete(name = "Condition") +
  facet_wrap(~ vignette, ncol = coln, nrow = rown, scales = "free", as.table = TRUE)
  ggpar(part1, legend = "none")
}

3.3 Reshaping data

#### filtering people who failed the attn check ####
filtered_gjg <- gjg %>% filter(attn_chk_DV == 1)
filtered_gjg$attn_PID <- seq_along(filtered_gjg$PID)

#### make dataset long ####
gjg_long<-filtered_gjg %>% gather(stim, resp, "just_BECMA_MC":"just_water_motive8")                         
gjg_long<-gjg_long %>%
  separate(stim, into= c("condition", "vignette", "DV"), sep="_")

## shift dataset back to wide format ##
gjg_wide <- spread(gjg_long, DV, resp)
gjg_wide <- gjg_wide %>% mutate_at(c("percep1","percep2","percep3","percep4","percep5",
 "selfMoral","selfPraiseworthy","selfFriend","agentMoral","agentPraiseworthy","agentFriend",
  "motive1", "motive2","motive3","motive4","motive5","motive6","motive7","motive8"), as.numeric)

#### rename DVs ####
names(gjg_wide)[names(gjg_wide) == 'percep1'] <-'p_approve'
names(gjg_wide)[names(gjg_wide) == 'percep2'] <-'p_similar'
names(gjg_wide)[names(gjg_wide) == 'percep3'] <-'p_genuine'
names(gjg_wide)[names(gjg_wide) == 'percep4'] <-'p_obligation'
names(gjg_wide)[names(gjg_wide) == 'percep5'] <-'p_beyond'

names(gjg_wide)[names(gjg_wide) == 'selfMoral'] <-'self_moral'
names(gjg_wide)[names(gjg_wide) == 'selfPraiseworthy'] <-'self_praiseworthy'
names(gjg_wide)[names(gjg_wide) == 'selfFriend'] <-'self_friend'
names(gjg_wide)[names(gjg_wide) == 'agentMoral'] <-'agent_moral'
names(gjg_wide)[names(gjg_wide) == 'agentPraiseworthy'] <-'agent_praiseworthy'
names(gjg_wide)[names(gjg_wide) == 'agentFriend'] <-'agent_friend'

names(gjg_wide)[names(gjg_wide) == 'motive1'] <-'m_reputation'
names(gjg_wide)[names(gjg_wide) == 'motive2'] <-'m_peers'
names(gjg_wide)[names(gjg_wide) == 'motive3'] <-'m_signal_important'
names(gjg_wide)[names(gjg_wide) == 'motive4'] <-'m_signal_right'
names(gjg_wide)[names(gjg_wide) == 'motive5'] <-'m_issue'
names(gjg_wide)[names(gjg_wide) == 'motive6'] <-'m_resources'
names(gjg_wide)[names(gjg_wide) == 'motive7'] <-'m_obligation'
names(gjg_wide)[names(gjg_wide) == 'motive8'] <-'m_beyond'

## Rename Vignettes
gjg_wide <- gjg_wide %>%
  mutate(vignette = case_when(
    vignette == "water" ~ "Clean Water Action",
    vignette == "bread" ~ "Project Bread",
    vignette == "child" ~ "Friends of the Children",
    vignette == "health" ~ "Healthcare Without Walls",
    vignette == "bread" ~ "Project Bread",
    vignette == "child" ~ "Friends of the Children",
    vignette == "ace" ~ "Alternatives for Community and Environment",
    vignette == "dcc" ~ "Dorchester Community care",
    vignette == "crayon" ~ "Cradles to Crayons",
    vignette == "raft" ~ "RAFT",
    vignette == "lit" ~ "Adult Literacy Initiative",
    vignette == "rosie" ~ "Rosie’s Place",
    vignette == "dudley" ~ "Dudley Street Neighborhood Initiative",
    vignette == "table" ~ "My Brother’s Table",
    vignette == "food" ~ "The Food Project",
    vignette == "home" ~ "Heading Home",
    vignette == "ethos" ~ "Ethos",
    vignette == "becma" ~ "BECMA",
    TRUE ~ vignette  # if none of the above conditions are met, keep the original value
  ))

## Rename Conditions
gjg_wide <- gjg_wide %>%
  mutate(condition = case_when(
    condition == "just" ~ "Justice",
    condition == "gen" ~ "Generosity",
    TRUE ~ condition  # if none of the above conditions are met, keep the original value
  ))

4 Attention Check

gjg %>%
  group_by(attn_chk_DV) %>%
  dplyr::summarise(n = n()) %>%
  mutate(freq = n / sum(n))

There was a 36% attention check failure rate.

5 Demographics

# Subset your data frame to include only the demographic columns
demo_gjg <- gjg[, c("age", "gender", "race", "income", "education", "employment", "political_overall", "political_social", "political_economic", "sexual_orientation", "english", "married", "relationship", "religiosity", "god", "faith", "services", "region")]

# Age
mean(gjg$age, na.rm=TRUE)

## [1] 39.535

sd(gjg$age, na.rm=TRUE)

## [1] 14.00319

# Loop through each demographic column and calculate frequency counts
freq_tables <- list()
for (col in names(demo_gjg)) {
  if (is.character(demo_gjg[[col]])) {
    freq_tables[[col]] <- as.data.frame(table(demo_gjg[[col]]))
  }
}

# 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 gender :
##                        Var1 Freq
## 1                              1
## 2                       Man  100
## 3 Nonbinary person or Other    4
## 4                     Woman   96
## 
## Table of frequencies for race :
##                                                               Var1 Freq
## 1                                                                     1
## 2                                                            Asian   19
## 3                                                      Asian,White    2
## 4                                        Black or African American   20
## 5                                  Black or African American,White    2
## 6                                              Hispanic/Latino/a/x   10
## 7                            Indigenous American or Alaskan Native    2
## 8                      Indigenous American or Alaskan Native,White    3
## 9  Indigenous American or Alaskan Native,White,Hispanic/Latino/a/x    1
## 10                       Native Hawaiian or Other Pacific Islander    1
## 11                                                           White  133
## 12                                       White,Hispanic/Latino/a/x    7
## 
## Table of frequencies for income :
##                    Var1 Freq
## 1                          2
## 2             < $10,000   11
## 3             >$150,000   14
## 4    $10,000 to $19,999   20
## 5  $100,000 to $149,999   32
## 6    $20,000 to $29,999   15
## 7    $30,000 to $39,999   23
## 8    $40,000 to $49,999   17
## 9    $50,000 to $74,999   38
## 10   $75,000 to $99,999   29
## 
## Table of frequencies for education :
##                                                                                Var1
## 1                                                                                  
## 2                                                    Associate Degree (e.g. AA, AS)
## 3                                                   Bachelor's Degree (e.g. BA, BS)
## 4                                       High school degree or equivalent (e.g. GED)
## 5                                                   Less than a high school diploma
## 6 Postgraduate Degree (e.g. Master's Degree, Professional Degree, Doctorate Degree)
## 7                                                           Some college, no degree
##   Freq
## 1    2
## 2   17
## 3   67
## 4   31
## 5    2
## 6   32
## 7   50
## 
## Table of frequencies for employment :
##                                             Var1 Freq
## 1                                                   2
## 2   Employed full time (30 hours or more a week)   90
## 3     Employed part time (up to 29 hours a week)   27
## 4                                      Homemaker   11
## 5                                        Retired   12
## 6                                  Self-employed   19
## 7                                        Student   12
## 8                                 Unable to work    7
## 9      Unemployed and currently looking for work   16
## 10 Unemployed and not currently looking for work    5
## 
## Table of frequencies for political_overall :
##             Var1 Freq
## 1                   1
## 2       Democrat   96
## 3    Independent   63
## 4     Republican   34
## 5 Something else    7
## 
## Table of frequencies for political_social :
##                    Var1 Freq
## 1                          2
## 2          Conservative   16
## 3               Liberal   51
## 4              Moderate   32
## 5 Somewhat conservative   18
## 6      Somewhat liberal   32
## 7     Very conservative    7
## 8          Very liberal   43
## 
## Table of frequencies for political_economic :
##                    Var1 Freq
## 1                          3
## 2          Conservative   19
## 3               Liberal   41
## 4              Moderate   37
## 5 Somewhat conservative   33
## 6      Somewhat liberal   23
## 7     Very conservative    9
## 8          Very liberal   36
## 
## Table of frequencies for sexual_orientation :
##                                          Var1 Freq
## 1                                                1
## 2                                     Asexual    2
## 3                         Asexual,Questioning    1
## 4                                    Bisexual   17
## 5  Bisexual,Pansexual,Straight (heterosexual)    1
## 6            Bisexual,Straight (heterosexual)    1
## 7                                         Gay    6
## 8                                     Lesbian    5
## 9                               Lesbian,Queer    1
## 10                                  Pansexual    1
## 11                            Pansexual,Queer    1
## 12                      Pansexual,Questioning    1
## 13                     Prefer not to disclose    1
## 14                    Straight (heterosexual)  162
## 
## Table of frequencies for english :
##      Var1 Freq
## 1            1
## 2 English  194
## 3   Other    6
## 
## Table of frequencies for married :
##                        Var1 Freq
## 1    No, never been married  110
## 2 Yes, and am still married   67
## 3    Yes, have been widowed    3
## 4        Yes, have divorced   18
## 5       Yes, have separated    3
## 
## Table of frequencies for relationship :
##                                          Var1 Freq
## 1                  In a long term partnership   41
## 2 In a marriage or legal domestic partnership   68
## 3       Single/not in a long term partnership   92
## 
## Table of frequencies for religiosity :
##                   Var1 Freq
## 1                         3
## 2 Moderately religious   36
## 3 Not at all religious   89
## 4   Slightly religious   43
## 5       Very religious   30
## 
## Table of frequencies for god :
##    Var1 Freq
## 1    No   66
## 2 Other   22
## 3   Yes  113
## 
## Table of frequencies for faith :
##                              Var1 Freq
## 1 Atheist (do not believe in God)   53
## 2                        Buddhist    1
## 3                       Christian   99
## 4                          Jewish    3
## 5                          Muslim    2
## 6                           Other   31
## 7          Prefer not to disclose   12
## 
## Table of frequencies for services :
##                    Var1 Freq
## 1                          1
## 2 A few times in a year   25
## 3 More than once a week    6
## 4                 Never   93
## 5           Once a week   15
## 6 Once or twice a month    9
## 7                Seldom   52
## 
## Table of frequencies for region :
##       Var1 Freq
## 1    Rural   25
## 2 Suburban  117
## 3    Urban   59

6 Correlations: Testing relationships among ratings

Here are the question wordings for the various ratings:

Perceptions of the donor (1 = Strongly Disagree, 7 = Strongly Agree)

I approve of the donor’s motivation for donating.
I think I am similar to the donor
I think the donor is genuine.
I think the donor fulfilled his obligation.
I think the donor went above and beyond.
To what extent is this message intended for a broad audience?

Contrast between first and third party beliefs about the donor (1 = Strongly Disagree, 7 = Strongly Agree)

I think the donor is moral.
I think the donor is praiseworthy.
I would like the donor as a friend.
The donor thinks he is moral.
The donor thinks he is praiseworthy
The donor would like me as a friend.

Beliefs about the donor’s motive (1 = Strongly Disagree, 7 = Strongly Agree)

The donor was motivated to donate because…

… he believed it would improve his reputation?
… he believed his peers would think more highly of him?
… he wanted to signal to others that it is important?
… he wanted to signal to others that it is the right thing to do?
… he wanted to help address the issue at hand?
… he wanted to provide resources to those who need them?
… he felt like he needed to fulfill an obligation?
… he wanted to go above and beyond?

DVs <- gjg_wide[c("p_approve","p_similar","p_genuine","p_obligation","p_beyond",
                 "self_moral","self_praiseworthy","self_friend","agent_moral","agent_praiseworthy",
                 "agent_friend","m_reputation","m_peers","m_signal_important","m_signal_right","m_issue",
                 "m_resources","m_obligation","m_beyond")]
results <- correlation::correlation(DVs)
results %>%
  summary(redundant = T) %>%
  plot() + #show_data = "points"
  see::theme_modern() +
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
  scale_fill_gradient2(low = "orange", high = hcl(240, 100, 50), mid = "white", midpoint = 0, limits = c(-1, 1))

The ratings are weakly to moderately positively correlated with the exception of reputation signaling motive measures, which tend to be negatively correlated perceptions of the donor and belief that the donor was motived solely by the impact of the donation on the cause/recipients.

7 factor analysis

corr_DVs = cor(DVs, 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 =  0.88
## MSA for each item = 
##          p_approve          p_similar          p_genuine       p_obligation 
##               0.94               0.88               0.94               0.95 
##           p_beyond         self_moral  self_praiseworthy        self_friend 
##               0.89               0.93               0.92               0.92 
##        agent_moral agent_praiseworthy       agent_friend       m_reputation 
##               0.73               0.73               0.86               0.68 
##            m_peers m_signal_important     m_signal_right            m_issue 
##               0.68               0.81               0.82               0.90 
##        m_resources       m_obligation           m_beyond 
##               0.90               0.93               0.87

cortest.bartlett(corr_DVs) #tests correlations between variables

## $chisq
## [1] 966.7685
## 
## $p.value
## [1] 3.092928e-111
## 
## $df
## [1] 171

ev<-eigen(cor(corr_DVs)) #gets eigenvalues (variance explained by each component)
ev$values

##  [1] 1.037409e+01 2.430630e+00 1.632689e+00 1.270013e+00 9.861088e-01
##  [6] 8.617383e-01 3.577198e-01 2.305413e-01 1.921516e-01 1.477668e-01
## [11] 1.171956e-01 1.077976e-01 8.820732e-02 5.915502e-02 5.061735e-02
## [16] 4.129114e-02 3.357023e-02 1.871365e-02 1.535846e-16

scree(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 =  2  and the number of components =  NA

dat_fa <- na.omit(DVs)

7.1 4 factors

fit.4 <- factanal(na.omit(dat_fa),factors=4, n.obs=3215, rotation="promax", scores = "regression")
print(fit.4, digits = 2, cutoff = .4, sort = TRUE)

## 
## Call:
## factanal(x = na.omit(dat_fa), factors = 4, n.obs = 3215, scores = "regression",     rotation = "promax")
## 
## Uniquenesses:
##          p_approve          p_similar          p_genuine       p_obligation 
##               0.34               0.48               0.26               0.44 
##           p_beyond         self_moral  self_praiseworthy        self_friend 
##               0.55               0.31               0.36               0.28 
##        agent_moral agent_praiseworthy       agent_friend       m_reputation 
##               0.81               0.74               0.22               0.21 
##            m_peers m_signal_important     m_signal_right            m_issue 
##               0.21               0.31               0.28               0.56 
##        m_resources       m_obligation           m_beyond 
##               0.62               0.74               0.76 
## 
## Loadings:
##                    Factor1 Factor2 Factor3 Factor4
## p_approve           0.86                          
## p_genuine           0.89                          
## p_obligation        0.62                          
## p_beyond            0.72                          
## self_moral          0.78                          
## self_praiseworthy   0.77                          
## m_issue             0.65                          
## m_resources         0.64                          
## m_reputation                0.89                  
## m_peers                     0.89                  
## p_similar                           0.60          
## self_friend                         0.59          
## agent_friend                        0.92          
## m_signal_important                          0.87  
## m_signal_right                              0.87  
## agent_moral                                       
## agent_praiseworthy          0.46                  
## m_obligation                                      
## m_beyond            0.47                          
## 
##                Factor1 Factor2 Factor3 Factor4
## SS loadings       5.01    2.09    1.71    1.63
## Proportion Var    0.26    0.11    0.09    0.09
## Cumulative Var    0.26    0.37    0.46    0.55
## 
## Factor Correlations:
##         Factor1 Factor2 Factor3 Factor4
## Factor1   1.000  -0.067   -0.58   -0.54
## Factor2  -0.067   1.000    0.22    0.40
## Factor3  -0.578   0.224    1.00    0.31
## Factor4  -0.537   0.401    0.31    1.00
## 
## Test of the hypothesis that 4 factors are sufficient.
## The chi square statistic is 2434.45 on 101 degrees of freedom.
## The p-value is 0

7.2 5 factors

fit.5 <- factanal(na.omit(dat_fa),factors=5, n.obs=3215, rotation="promax", scores = "regression")
print(fit.5, digits = 2, cutoff = .4, sort = TRUE)

## 
## Call:
## factanal(x = na.omit(dat_fa), factors = 5, n.obs = 3215, scores = "regression",     rotation = "promax")
## 
## Uniquenesses:
##          p_approve          p_similar          p_genuine       p_obligation 
##               0.32               0.43               0.26               0.44 
##           p_beyond         self_moral  self_praiseworthy        self_friend 
##               0.56               0.29               0.36               0.28 
##        agent_moral agent_praiseworthy       agent_friend       m_reputation 
##               0.41               0.44               0.23               0.22 
##            m_peers m_signal_important     m_signal_right            m_issue 
##               0.18               0.32               0.27               0.53 
##        m_resources       m_obligation           m_beyond 
##               0.60               0.74               0.76 
## 
## Loadings:
##                    Factor1 Factor2 Factor3 Factor4 Factor5
## p_approve           0.88                                  
## p_genuine           0.88                                  
## p_obligation        0.59                                  
## p_beyond            0.70                                  
## self_moral          0.74                                  
## self_praiseworthy   0.75                                  
## m_issue             0.69                                  
## m_resources         0.67                                  
## m_reputation                0.87                          
## m_peers                     0.91                          
## m_signal_important                  0.88                  
## m_signal_right                      0.89                  
## p_similar                                   0.66          
## self_friend                                 0.58          
## agent_friend                                0.89          
## agent_moral                                         0.78  
## agent_praiseworthy                                  0.69  
## m_obligation                                              
## m_beyond            0.46                                  
## 
##                Factor1 Factor2 Factor3 Factor4 Factor5
## SS loadings       4.89    1.75    1.68    1.64    1.24
## Proportion Var    0.26    0.09    0.09    0.09    0.07
## Cumulative Var    0.26    0.35    0.44    0.52    0.59
## 
## Factor Correlations:
##         Factor1 Factor2 Factor3 Factor4 Factor5
## Factor1    1.00  -0.040  -0.570    0.52   -0.21
## Factor2   -0.04   1.000  -0.069    0.41   -0.42
## Factor3   -0.57  -0.069   1.000   -0.31    0.31
## Factor4    0.52   0.409  -0.315    1.00   -0.28
## Factor5   -0.21  -0.419   0.313   -0.28    1.00
## 
## Test of the hypothesis that 5 factors are sufficient.
## The chi square statistic is 1579.1 on 86 degrees of freedom.
## The p-value is 4.67e-273

7.3 6 factors

fit.6 <- factanal(na.omit(dat_fa),factors=6, n.obs=3215, rotation="promax", scores = "regression")
print(fit.6, digits = 2, cutoff = .4, sort = TRUE)

## 
## Call:
## factanal(x = na.omit(dat_fa), factors = 6, n.obs = 3215, scores = "regression",     rotation = "promax")
## 
## Uniquenesses:
##          p_approve          p_similar          p_genuine       p_obligation 
##               0.29               0.42               0.26               0.43 
##           p_beyond         self_moral  self_praiseworthy        self_friend 
##               0.00               0.28               0.36               0.28 
##        agent_moral agent_praiseworthy       agent_friend       m_reputation 
##               0.40               0.45               0.23               0.22 
##            m_peers m_signal_important     m_signal_right            m_issue 
##               0.17               0.31               0.28               0.53 
##        m_resources       m_obligation           m_beyond 
##               0.60               0.74               0.65 
## 
## Loadings:
##                    Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## p_approve           0.97                                          
## p_genuine           0.87                                          
## self_moral          0.78                                          
## self_praiseworthy   0.67                                          
## m_issue             0.67                                          
## m_resources         0.71                                          
## m_signal_important          0.91                                  
## m_signal_right              0.90                                  
## p_similar                           0.70                          
## self_friend                         0.60                          
## agent_friend                        0.92                          
## m_reputation                                0.87                  
## m_peers                                     0.92                  
## p_beyond                                            1.04          
## m_beyond                                            0.50          
## agent_moral                                                 0.79  
## agent_praiseworthy                                          0.68  
## p_obligation        0.44                                          
## m_obligation                                                      
## 
##                Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## SS loadings       4.15    1.78    1.77    1.75    1.41    1.25
## Proportion Var    0.22    0.09    0.09    0.09    0.07    0.07
## Cumulative Var    0.22    0.31    0.41    0.50    0.57    0.64
## 
## Factor Correlations:
##         Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## Factor1   1.000   0.449  -0.099   -0.45   -0.65    0.27
## Factor2   0.449   1.000  -0.053   -0.36   -0.60    0.33
## Factor3  -0.099  -0.053   1.000    0.38   -0.12   -0.40
## Factor4  -0.445  -0.360   0.382    1.00    0.53   -0.29
## Factor5  -0.651  -0.597  -0.123    0.53    1.00   -0.20
## Factor6   0.274   0.335  -0.397   -0.29   -0.20    1.00
## 
## Test of the hypothesis that 6 factors are sufficient.
## The chi square statistic is 994.1 on 72 degrees of freedom.
## The p-value is 3.36e-162

8 Plots

8.1 Perception Plots

percep_plot_list <- list(plot_cooker("condition", "p_approve", "I approve of donors motivation for donating", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "p_similar", "I think I am similar to the donor", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "p_genuine", "I think the donor is genuine", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "p_obligation", "I think the donor fulfilled his obligation", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "p_beyond", "I think the donor went above and beyond", c("Justice", "Generosity"), "Participant agreement", 129))

percep_plot_arranged <- ggarrange(plotlist = percep_plot_list, ncol = 2, nrow = 3)

overall_percep_title <- ggdraw() + 
  draw_label("Perception DVs", fontface = "bold")

plot_grid(overall_percep_title, percep_plot_arranged, ncol = 1, rel_heights = c(0.1, 0.9))

8.2 Contrast Plots

contrast_plot_list <- list(plot_cooker("condition", "self_moral", "I think the donor is moral", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "self_praiseworthy", "I think the donor is praiseworthy", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "self_friend", "I would like the donor as a friend", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "agent_moral", "The donor thinks he is moral", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "agent_praiseworthy", "The donor thinks he is praiseworthy", c("Justice", "Generosity"), "Participant agreement", 129),
                         plot_cooker("condition", "agent_friend", "The donor would like me as a friend", c("Justice", "Generosity"), "Participant agreement", 129))

contrast_plot_arranged <- ggarrange(plotlist = contrast_plot_list, ncol = 2, nrow = 3)

overall_contrast_title <- ggdraw() + 
  draw_label("Contrast DVs", fontface = "bold")

plot_grid(overall_contrast_title, contrast_plot_arranged, ncol = 1, rel_heights = c(0.1, 0.9))

8.3 Motive Plots

motive_plot_list <- list(plot_cooker("condition", "m_reputation", "Reputation Motive", c("Justice", "Generosity"), "Potential motive", 129),
plot_cooker("condition", "m_peers", "Peer Motive", c("Justice", "Generosity"), "Potential motive", 129),
plot_cooker("condition", "m_signal_important", "Signal Importance", c("Justice", "Generosity"), "Potential motive", 129),
plot_cooker("condition", "m_signal_right", "Signal Right Thing to Do", c("Justice", "Generosity"), "Potential motive", 129),
plot_cooker("condition", "m_issue", "Address the issue", c("Justice", "Generosity"), "Potential motive", 129),
plot_cooker("condition", "m_resources", "Provide resources", c("Justice", "Generosity"), "Potential motive", 129),
plot_cooker("condition", "m_obligation", "Fulfill an obligation", c("Justice", "Generosity"), "Potential motive", 129), 
plot_cooker("condition", "m_beyond", "To go above and beyond?", c("Justice", "Generosity"), "Potential motive", 129))

motive_plot_arranged <- ggarrange(plotlist = motive_plot_list, ncol = 3, nrow = 3)

overall_motive_title <- ggdraw() + 
  draw_label("Motive DVs", fontface = "bold")

plot_grid(overall_motive_title, motive_plot_arranged, ncol = 1, rel_heights = c(0.1, 0.9))

8.4 Plots by Vignette

8.4.1 Perception

lizy_cooker("condition", "p_approve", "I approve of donors motivation for donating", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "p_similar", "I think I am similar to the donor", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "p_genuine", "I think the donor is genuine", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "p_obligation", "I think the donor fulfilled his obligation", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "p_beyond", "I think the donor went above and beyond", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

### Contrast

lizy_cooker("condition", "self_moral", "I think the donor is moral", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "self_praiseworthy", "I think the donor is praiseworthy", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "self_friend", "I would like the donor as a friend", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "agent_moral", "The donor thinks he is moral", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "agent_praiseworthy", "The donor thinks he is praiseworthy", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

lizy_cooker("condition", "agent_friend", "The donor would like me as a friend", c("Justice", "Generosity"), "Participant agreement", 129, 4, 4)

### Motive

lizy_cooker("condition", "m_reputation", "Reputation Motive", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

lizy_cooker("condition", "m_peers", "Peer Motive", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

lizy_cooker("condition", "m_signal_important", "Signal Importance", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

lizy_cooker("condition", "m_signal_right", "Signal Right Thing to Do", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

lizy_cooker("condition", "m_issue", "Address the issue", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

lizy_cooker("condition", "m_resources", "Provide resources", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

lizy_cooker("condition", "m_obligation", "Fulfill an obligation", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

lizy_cooker("condition", "m_beyond", "To go above and beyond?", c("Justice", "Generosity"), "Potential motive", 129, 4, 4)

9 Inferential Stats

9.1 Perception DVs

9.1.1 Condition main effect

mod_p_approve <- lmer(p_approve ~ condition + (1 + condition | PID) + (1 + condition | vignette), data = gjg_wide)
summary(mod_p_approve)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: p_approve ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 5064.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -6.5844 -0.2815  0.0551  0.3961  5.0361 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.59602  0.7720        
##           conditionJustice 0.54512  0.7383   -0.28
##  vignette (Intercept)      0.01991  0.1411        
##           conditionJustice 0.02194  0.1481   -1.00
##  Residual                  0.50558  0.7110        
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                  Estimate Std. Error       df t value Pr(>|t|)    
## (Intercept)       6.05898    0.07972 89.42484  76.005   <2e-16 ***
## conditionJustice -0.17628    0.08110 67.61513  -2.174   0.0332 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.470
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_p_similar <- lmer(p_similar ~ condition + (1 + condition | PID) + (1 + condition | vignette), data = gjg_wide)
summary(mod_p_similar)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: p_similar ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 5641.2
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -5.1149 -0.3580  0.0153  0.4117  4.4251 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      1.250367 1.11820       
##           conditionJustice 0.526793 0.72581  -0.41
##  vignette (Intercept)      0.012433 0.11150       
##           conditionJustice 0.004985 0.07061  -0.33
##  Residual                  0.663830 0.81476       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        4.86014    0.10542 126.57854  46.103   <2e-16 ***
## conditionJustice  -0.07592    0.07538  78.95985  -1.007    0.317    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.423

mod_p_genuine <- lmer(p_genuine ~ condition + (1 + condition | PID) + (1 + condition | vignette), data = gjg_wide)
summary(mod_p_genuine)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: p_genuine ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4764.9
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -6.8118 -0.3741  0.0335  0.4629  4.7161 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.602826 0.77642       
##           conditionJustice 0.246195 0.49618  -0.29
##  vignette (Intercept)      0.009726 0.09862       
##           conditionJustice 0.003063 0.05535  -1.00
##  Residual                  0.448983 0.67006       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.84607    0.07561 110.17081   77.32   <2e-16 ***
## conditionJustice  -0.06761    0.05450  79.43139   -1.24    0.218    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.398
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_p_obligation <- lmer(p_obligation ~ condition + (1 + condition | PID) + (1 + condition | vignette), data = gjg_wide)
summary(mod_p_obligation)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: p_obligation ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4649.8
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -7.9013 -0.3780  0.0190  0.4391  3.9266 
## 
## Random effects:
##  Groups   Name             Variance  Std.Dev.  Corr 
##  PID      (Intercept)      8.014e-01 0.8952064      
##           conditionJustice 1.501e-01 0.3874725 -0.17
##  vignette (Intercept)      4.642e-03 0.0681348      
##           conditionJustice 8.787e-07 0.0009374 -1.00
##  Residual                  4.219e-01 0.6495346      
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.74364    0.08313 127.51931  69.088   <2e-16 ***
## conditionJustice  -0.08225    0.04452 124.30576  -1.847   0.0671 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.234
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_p_beyond <- lmer(p_beyond ~ condition + (1 + condition | PID) + (1 + condition | vignette), data = gjg_wide)
summary(mod_p_beyond)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: p_beyond ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 5331.9
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -6.2951 -0.3841  0.0318  0.4347  5.5098 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      1.012825 1.00639       
##           conditionJustice 0.178728 0.42276  -0.09
##  vignette (Intercept)      0.004861 0.06972       
##           conditionJustice 0.001802 0.04245  -1.00
##  Residual                  0.595563 0.77173       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.51695    0.09345 122.73051  59.038   <2e-16 ***
## conditionJustice  -0.10687    0.05150  80.78332  -2.075   0.0412 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.223
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

9.2 contrast

mod_self_moral<-lmer(self_moral~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_self_moral)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: self_moral ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4354.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -7.3600 -0.2916  0.0407  0.4244  4.3736 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.671315 0.81934       
##           conditionJustice 0.087293 0.29545  -0.11
##  vignette (Intercept)      0.010052 0.10026       
##           conditionJustice 0.003902 0.06246  -1.00
##  Residual                  0.370705 0.60886       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.75877    0.07869 117.91667  73.186   <2e-16 ***
## conditionJustice  -0.03749    0.04049  41.17797  -0.926     0.36    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.298
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_self_praiseworthy<-lmer(self_praiseworthy~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_self_praiseworthy)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: self_praiseworthy ~ condition + (1 + condition | PID) + (1 +  
##     condition | vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4780.1
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -6.3692 -0.2779  0.0327  0.3718  5.0766 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.906549 0.95213       
##           conditionJustice 0.159643 0.39955  -0.22
##  vignette (Intercept)      0.002478 0.04978       
##           conditionJustice 0.001727 0.04156  -1.00
##  Residual                  0.450322 0.67106       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.68202    0.08729 126.35197   65.10   <2e-16 ***
## conditionJustice  -0.08994    0.04710  68.88380   -1.91   0.0604 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.297
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_self_friend<-lmer(self_friend~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_self_friend)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: self_friend ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4848.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -5.8941 -0.3107  0.0136  0.3837  3.8076 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      1.024492 1.01217       
##           conditionJustice 0.338579 0.58188  -0.32
##  vignette (Intercept)      0.007886 0.08880       
##           conditionJustice 0.001992 0.04463  -1.00
##  Residual                  0.447369 0.66886       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.32822    0.09417 129.28948  56.580   <2e-16 ***
## conditionJustice  -0.08294    0.06014 109.54869  -1.379    0.171    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.382
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_agent_moral<-lmer(agent_moral~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_agent_moral)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: agent_moral ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4937.4
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -5.4844 -0.3864  0.0230  0.4482  5.9608 
## 
## Random effects:
##  Groups   Name             Variance  Std.Dev. Corr 
##  PID      (Intercept)      0.7895778 0.88858       
##           conditionJustice 0.0450159 0.21217  -0.04
##  vignette (Intercept)      0.0010376 0.03221       
##           conditionJustice 0.0003437 0.01854  -1.00
##  Residual                  0.5108656 0.71475       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.47476    0.08174 123.63410  66.982   <2e-16 ***
## conditionJustice  -0.02706    0.03689  86.54935  -0.734    0.465    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.198
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_agent_praiseworthy<-lmer(agent_praiseworthy~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_agent_praiseworthy)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: agent_praiseworthy ~ condition + (1 + condition | PID) + (1 +  
##     condition | vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 5799
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -4.5979 -0.4176 -0.0379  0.3614  4.9067 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      1.028983 1.01439       
##           conditionJustice 0.099619 0.31562  -0.10
##  vignette (Intercept)      0.006097 0.07808       
##           conditionJustice 0.004765 0.06903  -1.00
##  Residual                  0.776622 0.88126       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                    Estimate Std. Error         df t value Pr(>|t|)    
## (Intercept)       4.923e+00  9.545e-02  1.217e+02  51.583   <2e-16 ***
## conditionJustice -5.530e-05  5.075e-02  3.877e+01  -0.001    0.999    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.279
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_agent_friend<-lmer(agent_friend~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_agent_friend)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: agent_friend ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4810
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -4.5898 -0.2929  0.0037  0.3867  4.8660 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      1.130472 1.06324       
##           conditionJustice 0.300757 0.54841  -0.31
##  vignette (Intercept)      0.004765 0.06903       
##           conditionJustice 0.004806 0.06933  -1.00
##  Residual                  0.438739 0.66237       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        5.01063    0.09740 129.13853  51.445   <2e-16 ***
## conditionJustice  -0.06780    0.05901  78.71171  -1.149    0.254    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.368
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

9.3 motive

mod_m_reputation<-lmer(m_reputation~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_reputation)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_reputation ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 5071.2
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -4.4370 -0.3933 -0.0259  0.4115  3.7794 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.748581 0.8652        
##           conditionJustice 0.217514 0.4664   -0.29
##  vignette (Intercept)      0.011432 0.1069        
##           conditionJustice 0.007191 0.0848   -0.68
##  Residual                  0.523526 0.7236        
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        2.84757    0.08382 118.12164  33.974   <2e-16 ***
## conditionJustice   0.06386    0.05613  45.92557   1.138    0.261    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.384

mod_m_peers<-lmer(m_peers~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_peers)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_peers ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 5117.1
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -4.0906 -0.4002 -0.0285  0.3632  3.9586 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.694496 0.83336       
##           conditionJustice 0.207525 0.45555  -0.23
##  vignette (Intercept)      0.001753 0.04187       
##           conditionJustice 0.009503 0.09748  -0.81
##  Residual                  0.542255 0.73638       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)      2.893e+00  7.758e-02 1.208e+02  37.284   <2e-16 ***
## conditionJustice 7.625e-03  5.704e-02 4.232e+01   0.134    0.894    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.320

mod_m_signal_important<-lmer(m_signal_important~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_signal_important)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_signal_important ~ condition + (1 + condition | PID) + (1 +  
##     condition | vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4533.8
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -4.5574 -0.3648  0.0476  0.5462  2.6226 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.525350 0.72481       
##           conditionJustice 0.109686 0.33119  -0.24
##  vignette (Intercept)      0.005267 0.07257       
##           conditionJustice 0.007827 0.08847  -1.00
##  Residual                  0.414198 0.64358       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        3.79754    0.06930 119.25642   54.80   <2e-16 ***
## conditionJustice   0.11527    0.04628  36.41697    2.49   0.0175 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.388
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_m_signal_right<-lmer(m_signal_right~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_signal_right)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_signal_right ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4482.1
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -4.9592 -0.4310  0.0359  0.4726  3.2967 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.509467 0.71377       
##           conditionJustice 0.082227 0.28675  -0.21
##  vignette (Intercept)      0.003961 0.06294       
##           conditionJustice 0.005279 0.07266  -0.94
##  Residual                  0.407343 0.63823       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        3.78393    0.06776 119.67366   55.84  < 2e-16 ***
## conditionJustice   0.14923    0.04192  29.21401    3.56  0.00129 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.351

mod_m_issue<-lmer(m_issue~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_issue)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_issue ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 3642.1
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -6.4651 -0.3272  0.0742  0.4313  3.4386 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.286830 0.53556       
##           conditionJustice 0.153345 0.39159  -0.49
##  vignette (Intercept)      0.001334 0.03653       
##           conditionJustice 0.004663 0.06829  -1.00
##  Residual                  0.267165 0.51688       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        4.38563    0.05065 119.69132  86.580   <2e-16 ***
## conditionJustice   0.02035    0.04470  57.69638   0.455    0.651    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.534
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_m_resources<-lmer(m_resources~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_resources)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_resources ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 3949.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -5.8414 -0.3737  0.0695  0.5135  2.8731 
## 
## Random effects:
##  Groups   Name             Variance  Std.Dev. Corr 
##  PID      (Intercept)      0.2216543 0.470802      
##           conditionJustice 0.1597120 0.399640 -0.31
##  vignette (Intercept)      0.0181819 0.134840      
##           conditionJustice 0.0000622 0.007887 -1.00
##  Residual                  0.3123059 0.558843      
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        4.46302    0.05619  55.30740  79.426   <2e-16 ***
## conditionJustice  -0.05886    0.04299 124.95666  -1.369    0.173    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.340
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_m_obligation<-lmer(m_obligation~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_obligation)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_obligation ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4848.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -4.9507 -0.4299  0.0651  0.5125  3.9409 
## 
## Random effects:
##  Groups   Name             Variance  Std.Dev.  Corr 
##  PID      (Intercept)      4.733e-01 0.6880008      
##           conditionJustice 1.294e-01 0.3596822 -0.15
##  vignette (Intercept)      2.933e-08 0.0001712      
##           conditionJustice 8.244e-08 0.0002871 -1.00
##  Residual                  4.913e-01 0.7009626      
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        3.79264    0.06439 128.00718  58.905  < 2e-16 ***
## conditionJustice   0.14050    0.04422 127.92768   3.178  0.00186 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.270
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')

mod_m_beyond<-lmer(m_beyond~condition + (1 + condition | PID) + (1 + condition | vignette), data=gjg_wide)
summary(mod_m_beyond)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: m_beyond ~ condition + (1 + condition | PID) + (1 + condition |  
##     vignette)
##    Data: gjg_wide
## 
## REML criterion at convergence: 4502.7
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -5.2059 -0.4196  0.0522  0.5137  4.7178 
## 
## Random effects:
##  Groups   Name             Variance Std.Dev. Corr 
##  PID      (Intercept)      0.379123 0.61573       
##           conditionJustice 0.063612 0.25221  0.18 
##  vignette (Intercept)      0.005261 0.07253       
##           conditionJustice 0.008305 0.09113  -0.87
##  Residual                  0.419004 0.64731       
## Number of obs: 2064, groups:  PID, 129; vignette, 16
## 
## Fixed effects:
##                   Estimate Std. Error        df t value Pr(>|t|)    
## (Intercept)        3.94562    0.06061 107.20788  65.096  < 2e-16 ***
## conditionJustice  -0.13447    0.04271  23.89320  -3.148  0.00437 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr)
## conditnJstc -0.213

# ggplot(gjg_wide, aes(x = condition, y = p_approve, color = condition)) +
#   geom_point(stat="summary", fun="mean", size = 2) +
#   facet_wrap(~attn_PID, nrow = 10) +
#   scale_x_discrete(labels = NULL)
# 
# ggplot(TEST_gjg_long, aes(x = condition, y = resp, group = attn_PID)) +
#   geom_line()
# TEST_gjg_long <- gjg_long %>% filter(DV == "percep1")
# 
# view(gjg)
# 
# ?geom_line
# 
# justice_cols <- gjg[, startsWith(names(gjg), "just")]
# gjg <- gjg %>% mutate(avg_Generous = colMeans(as.numeric(justice_cols)))
# 
# # select columns that start with "just"
# justice_cols <- gjg[, startsWith(names(gjg), "just")]
# 
# # convert the columns to a numeric matrix
# justice_cols_numeric <- as.matrix(justice_cols)
# 
# # calculate the column means and add them as a new column to the gjg data frame
# gjg <- gjg %>% mutate(avg_Generous = colMeans(justice_cols_numeric, na.rm = TRUE))
# 
# # calculate the column means
# means <- colMeans(selected_cols)
# 
# 
# library(dplyr)
# 
# # select columns that start with "just"
# justice_cols <- gjg[, startsWith(names(gjg), "just")]
# 
# # convert all columns to numeric
# justice_cols <- justice_cols %>% mutate_all(as.numeric)
# 
# # replace the original columns with the new numeric columns in the gjg data frame
# gjg[, startsWith(names(gjg), "just")] <- justice_cols

Generosity Vs Justice Pilot 1

Marcus + Lizy

3/20/2023