<- final_data |> filter (condition %in% c (2 , 5 , 8 , 11 ))#support for candidate |> ggplot (aes (x = support_election)) + geom_bar () + facet_wrap (~ politician_gender + politician_party)|> ggplot (aes (x = support_election_lumped)) + geom_bar () + facet_wrap (~ politician_gender + politician_party)#recognition of antidemocratic behavior |> ggplot (aes (x = threaten_country)) + geom_bar () + facet_wrap (~ politician_gender + politician_party)|> ggplot (aes (x = threaten_country_lumped)) + geom_bar () + facet_wrap (~ politician_gender + politician_party)#Opinion on bill |> ggplot (aes (x = opinion_bill)) + geom_bar () + facet_wrap (~ politician_gender + politician_party)|> ggplot (aes (x = opinion_bill_lumped)) + geom_bar () + facet_wrap (~ politician_gender + politician_party)<- media_censorship_data |> group_by (politician_party, politician_gender) |> summarize (mean_support_for_politician = mean (support_election, na.rm = TRUE ),sd_support_for_politician = sd (support_election, na.rm = TRUE ),mean_antidemocratic_recognition = mean (threaten_country, na.rm = TRUE ),sd_antidemocratic_recognition = sd (threaten_country, na.rm = TRUE ),mean_support_for_bill = mean (opinion_bill, na.rm = TRUE ),sd_support_for_bill = sd (opinion_bill, na.rm = TRUE ),n = n (),.groups = "drop" ) |> print ()
# A tibble: 4 × 9
politician_party politician_gender mean_support_for_politician
<fct> <fct> <dbl>
1 Democrat Male Politician 3.79
2 Democrat Female Politician 4.05
3 Republican Male Politician 3.54
4 Republican Female Politician 3.37
# ℹ 6 more variables: sd_support_for_politician <dbl>,
# mean_antidemocratic_recognition <dbl>, sd_antidemocratic_recognition <dbl>,
# mean_support_for_bill <dbl>, sd_support_for_bill <dbl>, n <int>
Hypothesis 2: this effect will be more pronounced among outparty voters than inparty voters
H2a: Overall effect
#simple model <- lm (support_election ~ politician_gender * inparty_outparty, data = media_censorship_data)summary (media_h2)
Call:
lm(formula = support_election ~ politician_gender * inparty_outparty,
data = media_censorship_data)
Residuals:
Min 1Q Median 3Q Max
-3.8983 -1.0050 0.1017 1.1017 4.0000
Coefficients:
Estimate Std. Error
(Intercept) 3.000000 0.119181
politician_genderFemale Politician 0.005025 0.167272
inparty_outpartyInparty 1.704000 0.190093
politician_genderFemale Politician:inparty_outpartyInparty 0.189280 0.270450
t value Pr(>|t|)
(Intercept) 25.172 <2e-16 ***
politician_genderFemale Politician 0.030 0.976
inparty_outpartyInparty 8.964 <2e-16 ***
politician_genderFemale Politician:inparty_outpartyInparty 0.700 0.484
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.656 on 631 degrees of freedom
Multiple R-squared: 0.2194, Adjusted R-squared: 0.2156
F-statistic: 59.1 on 3 and 631 DF, p-value: < 2.2e-16
plot_model (media_h2, terms = c ("inparty_outparty" , "politician_gender" ),type= "pred" )#include covariates <- lm (support_election ~ politician_gender * inparty_outparty + survey_partyid + respondent_gender, data = media_censorship_data)summary (media_h2_covariates)
Call:
lm(formula = support_election ~ politician_gender * inparty_outparty +
survey_partyid + respondent_gender, data = media_censorship_data)
Residuals:
Min 1Q Median 3Q Max
-3.9188 -1.3777 0.1189 1.1290 4.1290
Coefficients:
Estimate Std. Error
(Intercept) 3.44936 0.20061
politician_genderFemale Politician 0.01012 0.16466
inparty_outpartyInparty 1.73455 0.18727
survey_partyid -0.14459 0.03545
respondent_genderFemale Respondent 0.31427 0.12940
politician_genderFemale Politician:inparty_outpartyInparty 0.15858 0.26635
t value Pr(>|t|)
(Intercept) 17.194 < 2e-16 ***
politician_genderFemale Politician 0.061 0.9510
inparty_outpartyInparty 9.262 < 2e-16 ***
survey_partyid -4.078 5.12e-05 ***
respondent_genderFemale Respondent 2.429 0.0154 *
politician_genderFemale Politician:inparty_outpartyInparty 0.595 0.5518
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.63 on 629 degrees of freedom
Multiple R-squared: 0.246, Adjusted R-squared: 0.24
F-statistic: 41.04 on 5 and 629 DF, p-value: < 2.2e-16
plot_model (media_h2_covariates, terms = c ("inparty_outparty" , "politician_gender" ),type= "pred" )#compare this to next chunk - is it needed?
H2b: Split to look at just Democratic candidates, then just Republican
#################repeated for just democratic candidate ############### <- media_censorship_data |> filter (politician_party == "Democrat" )<- lm (support_election ~ politician_gender * inparty_outparty, data = dem_politician_media_data)summary (media_h2a)
Call:
lm(formula = support_election ~ politician_gender * inparty_outparty,
data = dem_politician_media_data)
Residuals:
Min 1Q Median 3Q Max
-3.8529 -1.4444 0.3699 1.1471 3.8889
Coefficients:
Estimate Std. Error
(Intercept) 3.1111 0.1767
politician_genderFemale Politician 0.3333 0.2499
inparty_outpartyInparty 1.5190 0.2640
politician_genderFemale Politician:inparty_outpartyInparty -0.1105 0.3772
t value Pr(>|t|)
(Intercept) 17.608 < 2e-16 ***
politician_genderFemale Politician 1.334 0.183
inparty_outpartyInparty 5.753 2.06e-08 ***
politician_genderFemale Politician:inparty_outpartyInparty -0.293 0.770
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.676 on 317 degrees of freedom
Multiple R-squared: 0.1644, Adjusted R-squared: 0.1565
F-statistic: 20.79 on 3 and 317 DF, p-value: 2.538e-12
plot_model (media_h2a, terms = c ("inparty_outparty" , "politician_gender" ),type= "pred" )#####################just republican candidate ################## <- media_censorship_data |> filter (politician_party == "Republican" )<- lm (support_election ~ politician_gender * inparty_outparty, data = rep_politician_media_data)summary (media_h2b)
Call:
lm(formula = support_election ~ politician_gender * inparty_outparty,
data = rep_politician_media_data)
Residuals:
Min 1Q Median 3Q Max
-3.960 -1.642 0.040 1.192 4.358
Coefficients:
Estimate Std. Error
(Intercept) 2.9029 0.1587
politician_genderFemale Politician -0.2607 0.2213
inparty_outpartyInparty 1.9048 0.2740
politician_genderFemale Politician:inparty_outpartyInparty 0.4130 0.3882
t value Pr(>|t|)
(Intercept) 18.293 < 2e-16 ***
politician_genderFemale Politician -1.178 0.240
inparty_outpartyInparty 6.952 2.13e-11 ***
politician_genderFemale Politician:inparty_outpartyInparty 1.064 0.288
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.611 on 310 degrees of freedom
Multiple R-squared: 0.2794, Adjusted R-squared: 0.2725
F-statistic: 40.07 on 3 and 310 DF, p-value: < 2.2e-16
plot_model (media_h2b, terms = c ("inparty_outparty" , "politician_gender" ),type= "pred" )
For dems, both out and inparty voters see higher effects for female candidates
for Reps, outparty decreases, but inparty increases (albeit not significantly)
