Repression Study 5 pilot analysis
Siwar Hasan-Aslih
2024-07-24
Summary: Consistent with our previous studies, police violence significantly decreases trust in the police. This effect persists even in the presence of protester violence, although the effect is smaller. This indicates that protester violence diminishes the negative impact of police violence on trust in the police. Similar to our previous findings, we do not observe any moderation by ideology. We find similar albeit weaker patterns for trust in the government and policy support.
#means
S5 %>%
group_by(condition) %>%
summarise_at(.vars = c("ViolentPolice_sc", "ViolentProtester_sc"), .funs = mean)## # A tibble: 4 × 3
## condition ViolentPolice_sc ViolentProtester_sc
## <fct> <dbl> <dbl>
## 1 control 8.01 8.44
## 2 police_violence 84.4 18.3
## 3 protester_violence 13.5 89.2
## 4 mutual_violence 64.8 73.9S5 %>%
group_by(condition) %>%
summarise_at(.vars = c("MoralPolice_sc", "MoralProtester_sc"), .funs = mean)## # A tibble: 4 × 3
## condition MoralPolice_sc MoralProtester_sc
## <fct> <dbl> <dbl>
## 1 control 88.8 83.0
## 2 police_violence 15.4 71.3
## 3 protester_violence 75.2 10.9
## 4 mutual_violence 34.7 24.4S5 %>%
group_by(condition) %>%
summarise_at(.vars = c("HarmfulPolice_sc", "HarmfulProtester_sc"), .funs = mean)## # A tibble: 4 × 3
## condition HarmfulPolice_sc HarmfulProtester_sc
## <fct> <dbl> <dbl>
## 1 control 8.06 9.97
## 2 police_violence 84.5 20.8
## 3 protester_violence 15.0 89.5
## 4 mutual_violence 67.5 75.9S5 %>%
group_by(condition) %>%
summarise_at(.vars = c("TrustPolice_sc", "TrustGov_sc"), .funs = mean)## # A tibble: 4 × 3
## condition TrustPolice_sc TrustGov_sc
## <fct> <dbl> <dbl>
## 1 control 71.4 58.3
## 2 police_violence 24.4 40.1
## 3 protester_violence 67.6 49.9
## 4 mutual_violence 43.4 45.8#effects on trust Consistent with our previous studies, police violence significantly decreases trust in the police. This effect persists even in the presence of protester violence, although the effect is reduced. This indicates that protester violence diminishes the negative impact of police violence on trust in the police. Similar to our previous findings, we do not observe any moderation by ideology. We find similar albeit weaker patterns for trust in the government and policy support. For trust in the local government, we find that also protester violence decreases trust.
summary(model <- lm(TrustPolice_sc ~ condD1*condD2*condD3*ideology + incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit))##
## Call:
## lm(formula = TrustPolice_sc ~ condD1 * condD2 * condD3 * ideology +
## incomeN + Race4 + age + educationN + gender_dum, data = S5,
## na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -82.72 -16.96 1.56 15.46 75.89
##
## Coefficients: (8 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 32.1905 10.2276 3.147 0.001801 **
## condD1 -49.2927 8.8576 -5.565 5.51e-08 ***
## condD2 -9.4385 9.6500 -0.978 0.328763
## condD3 -28.8767 8.5299 -3.385 0.000799 ***
## ideology 5.4482 1.4719 3.702 0.000252 ***
## incomeN 0.3718 0.4217 0.882 0.378603
## Race4Black 2.5504 4.7221 0.540 0.589504
## Race4Hispanic 1.9845 5.3041 0.374 0.708545
## Race4Asian 1.4908 7.0717 0.211 0.833168
## Race4Other 26.7328 13.3142 2.008 0.045493 *
## age 0.3566 0.1044 3.417 0.000715 ***
## educationN -1.0787 1.6932 -0.637 0.524534
## gender_dum 4.6284 2.8865 1.603 0.109812
## condD1:condD2 NA NA NA NA
## condD1:condD3 NA NA NA NA
## condD2:condD3 NA NA NA NA
## condD1:ideology 0.6683 2.1177 0.316 0.752530
## condD2:ideology 1.1465 2.2289 0.514 0.607347
## condD3:ideology 0.1901 2.0064 0.095 0.924582
## condD1:condD2:condD3 NA NA NA NA
## condD1:condD2:ideology NA NA NA NA
## condD1:condD3:ideology NA NA NA NA
## condD2:condD3:ideology NA NA NA NA
## condD1:condD2:condD3:ideology NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 25.79 on 323 degrees of freedom
## Multiple R-squared: 0.4575, Adjusted R-squared: 0.4323
## F-statistic: 18.16 on 15 and 323 DF, p-value: < 2.2e-16summary(model <- lm(TrustPolice_sc ~ PoliceViolence.dum*ProtesterViolence.dum+ incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit))##
## Call:
## lm(formula = TrustPolice_sc ~ PoliceViolence.dum * ProtesterViolence.dum +
## incomeN + Race4 + age + educationN + gender_dum, data = S5,
## na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -73.220 -18.757 -0.933 19.719 60.952
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 55.6780 9.2791 6.000 5.22e-09
## PoliceViolence.dum -46.4196 4.3619 -10.642 < 2e-16
## ProtesterViolence.dum -2.4882 4.4644 -0.557 0.577677
## incomeN 1.0708 0.4432 2.416 0.016234
## Race4Black 0.5662 5.0407 0.112 0.910637
## Race4Hispanic -2.4244 5.6774 -0.427 0.669636
## Race4Asian -3.6087 7.5723 -0.477 0.633984
## Race4Other 18.9388 14.2897 1.325 0.185979
## age 0.3630 0.1124 3.230 0.001361
## educationN -3.2862 1.7969 -1.829 0.068340
## gender_dum 3.9132 3.1084 1.259 0.208959
## PoliceViolence.dum:ProtesterViolence.dum 21.4903 6.1741 3.481 0.000568
##
## (Intercept) ***
## PoliceViolence.dum ***
## ProtesterViolence.dum
## incomeN *
## Race4Black
## Race4Hispanic
## Race4Asian
## Race4Other
## age **
## educationN .
## gender_dum
## PoliceViolence.dum:ProtesterViolence.dum ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 27.83 on 327 degrees of freedom
## Multiple R-squared: 0.3608, Adjusted R-squared: 0.3393
## F-statistic: 16.78 on 11 and 327 DF, p-value: < 2.2e-16sim_slopes(model, pred = PoliceViolence.dum, modx = ProtesterViolence.dum)## JOHNSON-NEYMAN INTERVAL
##
## When ProtesterViolence.dum is OUTSIDE the interval [1.52, 4.36], the slope
## of PoliceViolence.dum is p < .05.
##
## Note: The range of observed values of ProtesterViolence.dum is [0.00, 1.00]
##
## SIMPLE SLOPES ANALYSIS
##
## Slope of PoliceViolence.dum when ProtesterViolence.dum = 0.00 (0):
##
## Est. S.E. t val. p
## -------- ------ -------- ------
## -46.42 4.36 -10.64 0.00
##
## Slope of PoliceViolence.dum when ProtesterViolence.dum = 1.00 (1):
##
## Est. S.E. t val. p
## -------- ------ -------- ------
## -24.93 4.34 -5.74 0.00summary(model <- lm(TrustPolice_sc ~ PoliceViolence.dum*ProtesterViolence.dum*MutualViolence.dum+ incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit)) #the mutual violence var is the interaction between police violence and protester violence##
## Call:
## lm(formula = TrustPolice_sc ~ PoliceViolence.dum * ProtesterViolence.dum *
## MutualViolence.dum + incomeN + Race4 + age + educationN +
## gender_dum, data = S5, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -73.220 -18.757 -0.933 19.719 60.952
##
## Coefficients: (4 not defined because of singularities)
## Estimate Std. Error
## (Intercept) 55.6780 9.2791
## PoliceViolence.dum -46.4196 4.3619
## ProtesterViolence.dum -2.4882 4.4644
## MutualViolence.dum 21.4903 6.1741
## incomeN 1.0708 0.4432
## Race4Black 0.5662 5.0407
## Race4Hispanic -2.4244 5.6774
## Race4Asian -3.6087 7.5723
## Race4Other 18.9388 14.2897
## age 0.3630 0.1124
## educationN -3.2862 1.7969
## gender_dum 3.9132 3.1084
## PoliceViolence.dum:ProtesterViolence.dum NA NA
## PoliceViolence.dum:MutualViolence.dum NA NA
## ProtesterViolence.dum:MutualViolence.dum NA NA
## PoliceViolence.dum:ProtesterViolence.dum:MutualViolence.dum NA NA
## t value Pr(>|t|)
## (Intercept) 6.000 5.22e-09
## PoliceViolence.dum -10.642 < 2e-16
## ProtesterViolence.dum -0.557 0.577677
## MutualViolence.dum 3.481 0.000568
## incomeN 2.416 0.016234
## Race4Black 0.112 0.910637
## Race4Hispanic -0.427 0.669636
## Race4Asian -0.477 0.633984
## Race4Other 1.325 0.185979
## age 3.230 0.001361
## educationN -1.829 0.068340
## gender_dum 1.259 0.208959
## PoliceViolence.dum:ProtesterViolence.dum NA NA
## PoliceViolence.dum:MutualViolence.dum NA NA
## ProtesterViolence.dum:MutualViolence.dum NA NA
## PoliceViolence.dum:ProtesterViolence.dum:MutualViolence.dum NA NA
##
## (Intercept) ***
## PoliceViolence.dum ***
## ProtesterViolence.dum
## MutualViolence.dum ***
## incomeN *
## Race4Black
## Race4Hispanic
## Race4Asian
## Race4Other
## age **
## educationN .
## gender_dum
## PoliceViolence.dum:ProtesterViolence.dum
## PoliceViolence.dum:MutualViolence.dum
## ProtesterViolence.dum:MutualViolence.dum
## PoliceViolence.dum:ProtesterViolence.dum:MutualViolence.dum
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 27.83 on 327 degrees of freedom
## Multiple R-squared: 0.3608, Adjusted R-squared: 0.3393
## F-statistic: 16.78 on 11 and 327 DF, p-value: < 2.2e-16summary(model <- lm(TrustPolice_sc ~ PoliceViolence.dum*ProtesterViolence.dum*ideology+ incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit))##
## Call:
## lm(formula = TrustPolice_sc ~ PoliceViolence.dum * ProtesterViolence.dum *
## ideology + incomeN + Race4 + age + educationN + gender_dum,
## data = S5, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -82.72 -16.96 1.56 15.46 75.89
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 32.1905 10.2276 3.147
## PoliceViolence.dum -49.2927 8.8576 -5.565
## ProtesterViolence.dum -9.4385 9.6500 -0.978
## ideology 5.4482 1.4719 3.702
## incomeN 0.3718 0.4217 0.882
## Race4Black 2.5504 4.7221 0.540
## Race4Hispanic 1.9845 5.3041 0.374
## Race4Asian 1.4908 7.0717 0.211
## Race4Other 26.7328 13.3142 2.008
## age 0.3566 0.1044 3.417
## educationN -1.0787 1.6932 -0.637
## gender_dum 4.6284 2.8865 1.603
## PoliceViolence.dum:ProtesterViolence.dum 29.8546 12.9094 2.313
## PoliceViolence.dum:ideology 0.6683 2.1177 0.316
## ProtesterViolence.dum:ideology 1.1465 2.2289 0.514
## PoliceViolence.dum:ProtesterViolence.dum:ideology -1.6247 3.0301 -0.536
## Pr(>|t|)
## (Intercept) 0.001801 **
## PoliceViolence.dum 5.51e-08 ***
## ProtesterViolence.dum 0.328763
## ideology 0.000252 ***
## incomeN 0.378603
## Race4Black 0.589504
## Race4Hispanic 0.708545
## Race4Asian 0.833168
## Race4Other 0.045493 *
## age 0.000715 ***
## educationN 0.524534
## gender_dum 0.109812
## PoliceViolence.dum:ProtesterViolence.dum 0.021372 *
## PoliceViolence.dum:ideology 0.752530
## ProtesterViolence.dum:ideology 0.607347
## PoliceViolence.dum:ProtesterViolence.dum:ideology 0.592200
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 25.79 on 323 degrees of freedom
## Multiple R-squared: 0.4575, Adjusted R-squared: 0.4323
## F-statistic: 18.16 on 15 and 323 DF, p-value: < 2.2e-16ggplot(S5, aes(x = ProtesterViolence, y = TrustPolice_sc, fill = PoliceViolence, group = PoliceViolence)) +
stat_summary(fun = mean, geom = "bar", position = position_dodge(width = 0.8), width = 0.75) +
stat_summary(fun.data = mean_cl_boot, geom = "errorbar", colour = "grey",
position = position_dodge(width = 0.8), width = 0.2) +
scale_y_continuous(limits = c(0, 100)) +
theme_bw() +
scale_fill_manual(values = c("grey","#80b1d3")) +
labs(x = "",
y = "Score",
title = "Effects on trust in the police") +
theme(
plot.title = element_text(hjust = 0.5, size = 14),
plot.subtitle = element_text(hjust = 0.5),
plot.caption = element_text(hjust = 0.5, face = "italic")
) 
summary(model <- lm(TrustGov_sc ~ condD1*condD2*condD3*ideology, S5, na.action=na.omit))##
## Call:
## lm(formula = TrustGov_sc ~ condD1 * condD2 * condD3 * ideology,
## data = S5, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -54.419 -19.725 3.185 17.579 54.578
##
## Coefficients: (8 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 47.4533 6.0362 7.861 5.4e-14 ***
## condD1 -14.7323 8.6589 -1.701 0.0898 .
## condD2 6.5975 9.4759 0.696 0.4868
## condD3 -2.8467 8.3614 -0.340 0.7337
## ideology 2.9110 1.4425 2.018 0.0444 *
## condD1:condD2 NA NA NA NA
## condD1:condD3 NA NA NA NA
## condD2:condD3 NA NA NA NA
## condD1:ideology -0.8991 2.0901 -0.430 0.6674
## condD2:ideology -3.9503 2.2048 -1.792 0.0741 .
## condD3:ideology -2.5960 1.9807 -1.311 0.1909
## condD1:condD2:condD3 NA NA NA NA
## condD1:condD2:ideology NA NA NA NA
## condD1:condD3:ideology NA NA NA NA
## condD2:condD3:ideology NA NA NA NA
## condD1:condD2:condD3:ideology NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 25.61 on 331 degrees of freedom
## Multiple R-squared: 0.08103, Adjusted R-squared: 0.06159
## F-statistic: 4.169 on 7 and 331 DF, p-value: 0.0002042summary(model <- lm(TrustGov_sc ~ PoliceViolence.dum*ProtesterViolence.dum+ incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit))##
## Call:
## lm(formula = TrustGov_sc ~ PoliceViolence.dum * ProtesterViolence.dum +
## incomeN + Race4 + age + educationN + gender_dum, data = S5,
## na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -60.365 -17.528 1.437 18.307 61.163
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 38.7398 8.4915 4.562 7.17e-06
## PoliceViolence.dum -18.5136 3.9917 -4.638 5.09e-06
## ProtesterViolence.dum -8.6119 4.0855 -2.108 0.03580
## incomeN 0.7017 0.4056 1.730 0.08456
## Race4Black 3.7636 4.6128 0.816 0.41515
## Race4Hispanic 0.3456 5.1955 0.067 0.94700
## Race4Asian -1.2193 6.9296 -0.176 0.86043
## Race4Other 4.6494 13.0768 0.356 0.72241
## age 0.3166 0.1028 3.078 0.00226
## educationN -0.3031 1.6444 -0.184 0.85386
## gender_dum 0.2069 2.8445 0.073 0.94205
## PoliceViolence.dum:ProtesterViolence.dum 14.6345 5.6501 2.590 0.01002
##
## (Intercept) ***
## PoliceViolence.dum ***
## ProtesterViolence.dum *
## incomeN .
## Race4Black
## Race4Hispanic
## Race4Asian
## Race4Other
## age **
## educationN
## gender_dum
## PoliceViolence.dum:ProtesterViolence.dum *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 25.46 on 327 degrees of freedom
## Multiple R-squared: 0.1027, Adjusted R-squared: 0.07249
## F-statistic: 3.401 on 11 and 327 DF, p-value: 0.0001754sim_slopes(model, pred = PoliceViolence.dum, modx = ProtesterViolence.dum)## JOHNSON-NEYMAN INTERVAL
##
## When ProtesterViolence.dum is OUTSIDE the interval [0.82, 3.79], the slope
## of PoliceViolence.dum is p < .05.
##
## Note: The range of observed values of ProtesterViolence.dum is [0.00, 1.00]
##
## SIMPLE SLOPES ANALYSIS
##
## Slope of PoliceViolence.dum when ProtesterViolence.dum = 0.00 (0):
##
## Est. S.E. t val. p
## -------- ------ -------- ------
## -18.51 3.99 -4.64 0.00
##
## Slope of PoliceViolence.dum when ProtesterViolence.dum = 1.00 (1):
##
## Est. S.E. t val. p
## ------- ------ -------- ------
## -3.88 3.97 -0.98 0.33summary(model <- lm(TrustGov_sc ~ PoliceViolence.dum*ProtesterViolence.dum*ideology + incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit))##
## Call:
## lm(formula = TrustGov_sc ~ PoliceViolence.dum * ProtesterViolence.dum *
## ideology + incomeN + Race4 + age + educationN + gender_dum,
## data = S5, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -57.508 -18.567 2.239 18.290 56.133
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 29.3946 10.0866 2.914
## PoliceViolence.dum -15.3293 8.7355 -1.755
## ProtesterViolence.dum 5.3301 9.5169 0.560
## ideology 2.5430 1.4516 1.752
## incomeN 0.5746 0.4159 1.382
## Race4Black 3.3916 4.6569 0.728
## Race4Hispanic 1.1056 5.2310 0.211
## Race4Asian -1.2980 6.9742 -0.186
## Race4Other 7.0558 13.1306 0.537
## age 0.3062 0.1029 2.975
## educationN 0.0769 1.6698 0.046
## gender_dum 0.1541 2.8467 0.054
## PoliceViolence.dum:ProtesterViolence.dum 6.6962 12.7313 0.526
## PoliceViolence.dum:ideology -0.8608 2.0885 -0.412
## ProtesterViolence.dum:ideology -3.6701 2.1982 -1.670
## PoliceViolence.dum:ProtesterViolence.dum:ideology 2.0471 2.9883 0.685
## Pr(>|t|)
## (Intercept) 0.00381 **
## PoliceViolence.dum 0.08024 .
## ProtesterViolence.dum 0.57582
## ideology 0.08074 .
## incomeN 0.16804
## Race4Black 0.46696
## Race4Hispanic 0.83274
## Race4Asian 0.85247
## Race4Other 0.59139
## age 0.00315 **
## educationN 0.96330
## gender_dum 0.95687
## PoliceViolence.dum:ProtesterViolence.dum 0.59928
## PoliceViolence.dum:ideology 0.68051
## ProtesterViolence.dum:ideology 0.09596 .
## PoliceViolence.dum:ProtesterViolence.dum:ideology 0.49380
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 25.44 on 323 degrees of freedom
## Multiple R-squared: 0.1155, Adjusted R-squared: 0.07439
## F-statistic: 2.811 on 15 and 323 DF, p-value: 0.0003924sim_slopes(model, pred = ProtesterViolence.dum, modx = ideology)## JOHNSON-NEYMAN INTERVAL
##
## The Johnson-Neyman interval could not be found. Is the p value for your
## interaction term below the specified alpha?
##
## SIMPLE SLOPES ANALYSIS
##
## Slope of ProtesterViolence.dum when ideology = 1.906236 (- 1 SD):
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 3.77 4.02 0.94 0.35
##
## Slope of ProtesterViolence.dum when ideology = 3.790560 (Mean):
##
## Est. S.E. t val. p
## ------- ------ -------- ------
## -1.16 2.82 -0.41 0.68
##
## Slope of ProtesterViolence.dum when ideology = 5.674885 (+ 1 SD):
##
## Est. S.E. t val. p
## ------- ------ -------- ------
## -6.10 3.97 -1.53 0.13ggplot(S5, aes(x = ProtesterViolence, y = TrustGov_sc, fill = PoliceViolence, group = PoliceViolence)) +
stat_summary(fun = mean, geom = "bar", position = position_dodge(width = 0.8), width = 0.75) +
stat_summary(fun.data = mean_cl_boot, geom = "errorbar", colour = "grey",
position = position_dodge(width = 0.8), width = 0.2) +
scale_y_continuous(limits = c(0, 100)) +
theme_bw() +
scale_fill_manual(values = c("grey","#80b1d3")) +
labs(x = "",
y = "Score",
title = "Effects on trust in the local government") +
theme(
plot.title = element_text(hjust = 0.5, size = 14),
plot.subtitle = element_text(hjust = 0.5),
plot.caption = element_text(hjust = 0.5, face = "italic")
) 
summary(model <- lm(PolicySupport ~ condD1*condD2*condD3*ideology, S5, na.action=na.omit))##
## Call:
## lm(formula = PolicySupport ~ condD1 * condD2 * condD3 * ideology,
## data = S5, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -69.859 -12.151 0.703 11.100 52.168
##
## Coefficients: (8 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 65.4501 4.4439 14.728 < 2e-16 ***
## condD1 11.3832 6.3747 1.786 0.0751 .
## condD2 5.6895 6.9762 0.816 0.4153
## condD3 11.0098 6.1557 1.789 0.0746 .
## ideology -5.2022 1.0619 -4.899 1.51e-06 ***
## condD1:condD2 NA NA NA NA
## condD1:condD3 NA NA NA NA
## condD2:condD3 NA NA NA NA
## condD1:ideology 0.8806 1.5387 0.572 0.5675
## condD2:ideology -0.3789 1.6232 -0.233 0.8156
## condD3:ideology -0.8983 1.4582 -0.616 0.5383
## condD1:condD2:condD3 NA NA NA NA
## condD1:condD2:ideology NA NA NA NA
## condD1:condD3:ideology NA NA NA NA
## condD2:condD3:ideology NA NA NA NA
## condD1:condD2:condD3:ideology NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 18.86 on 331 degrees of freedom
## Multiple R-squared: 0.2782, Adjusted R-squared: 0.2629
## F-statistic: 18.22 on 7 and 331 DF, p-value: < 2.2e-16summary(model <- lm(PolicySupport ~ PoliceViolence.dum*ProtesterViolence.dum+ incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit))##
## Call:
## lm(formula = PolicySupport ~ PoliceViolence.dum * ProtesterViolence.dum +
## incomeN + Race4 + age + educationN + gender_dum, data = S5,
## na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -60.871 -12.033 -1.008 13.777 52.619
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 52.73144 6.95385 7.583 3.53e-13
## PoliceViolence.dum 14.75555 3.26888 4.514 8.89e-06
## ProtesterViolence.dum 2.31621 3.34569 0.692 0.48924
## incomeN -1.01775 0.33213 -3.064 0.00236
## Race4Black 1.33943 3.77753 0.355 0.72313
## Race4Hispanic 5.48397 4.25470 1.289 0.19834
## Race4Asian 1.05003 5.67475 0.185 0.85332
## Race4Other -0.60256 10.70882 -0.056 0.95516
## age -0.22014 0.08421 -2.614 0.00936
## educationN 2.92898 1.34662 2.175 0.03034
## gender_dum 0.48754 2.32943 0.209 0.83435
## PoliceViolence.dum:ProtesterViolence.dum -9.87734 4.62694 -2.135 0.03352
##
## (Intercept) ***
## PoliceViolence.dum ***
## ProtesterViolence.dum
## incomeN **
## Race4Black
## Race4Hispanic
## Race4Asian
## Race4Other
## age **
## educationN *
## gender_dum
## PoliceViolence.dum:ProtesterViolence.dum *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 20.85 on 327 degrees of freedom
## Multiple R-squared: 0.1279, Adjusted R-squared: 0.09858
## F-statistic: 4.36 on 11 and 327 DF, p-value: 4.191e-06sim_slopes(model, pred = PoliceViolence.dum, modx = ProtesterViolence.dum)## JOHNSON-NEYMAN INTERVAL
##
## When ProtesterViolence.dum is OUTSIDE the interval [0.90, 13.25], the slope
## of PoliceViolence.dum is p < .05.
##
## Note: The range of observed values of ProtesterViolence.dum is [0.00, 1.00]
##
## SIMPLE SLOPES ANALYSIS
##
## Slope of PoliceViolence.dum when ProtesterViolence.dum = 0.00 (0):
##
## Est. S.E. t val. p
## ------- ------ -------- ------
## 14.76 3.27 4.51 0.00
##
## Slope of PoliceViolence.dum when ProtesterViolence.dum = 1.00 (1):
##
## Est. S.E. t val. p
## ------ ------ -------- ------
## 4.88 3.25 1.50 0.13summary(model <- lm(PolicySupport ~ PoliceViolence.dum*ProtesterViolence.dum*ideology+ incomeN + Race4 + age + educationN + gender_dum, S5, na.action=na.omit))##
## Call:
## lm(formula = PolicySupport ~ PoliceViolence.dum * ProtesterViolence.dum *
## ideology + incomeN + Race4 + age + educationN + gender_dum,
## data = S5, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -72.721 -11.416 0.356 11.012 51.928
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 73.7234 7.4179 9.939
## PoliceViolence.dum 12.0253 6.4243 1.872
## ProtesterViolence.dum 6.7507 6.9990 0.965
## ideology -4.8483 1.0675 -4.542
## incomeN -0.4372 0.3059 -1.429
## Race4Black -0.6423 3.4248 -0.188
## Race4Hispanic 2.0530 3.8470 0.534
## Race4Asian -3.8201 5.1290 -0.745
## Race4Other -6.5683 9.6566 -0.680
## age -0.2131 0.0757 -2.815
## educationN 1.0266 1.2280 0.836
## gender_dum -0.2418 2.0935 -0.116
## PoliceViolence.dum:ProtesterViolence.dum -6.8517 9.3630 -0.732
## PoliceViolence.dum:ideology 0.8353 1.5359 0.544
## ProtesterViolence.dum:ideology -0.5925 1.6166 -0.367
## PoliceViolence.dum:ProtesterViolence.dum:ideology -1.3329 2.1977 -0.607
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PoliceViolence.dum 0.06213 .
## ProtesterViolence.dum 0.33550
## ideology 7.89e-06 ***
## incomeN 0.15384
## Race4Black 0.85136
## Race4Hispanic 0.59393
## Race4Asian 0.45693
## Race4Other 0.49687
## age 0.00517 **
## educationN 0.40379
## gender_dum 0.90811
## PoliceViolence.dum:ProtesterViolence.dum 0.46483
## PoliceViolence.dum:ideology 0.58695
## ProtesterViolence.dum:ideology 0.71421
## PoliceViolence.dum:ProtesterViolence.dum:ideology 0.54460
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 18.71 on 323 degrees of freedom
## Multiple R-squared: 0.3067, Adjusted R-squared: 0.2745
## F-statistic: 9.526 on 15 and 323 DF, p-value: < 2.2e-16ggplot(S5, aes(x = ProtesterViolence, y = PolicySupport, fill = PoliceViolence, group = PoliceViolence)) +
stat_summary(fun = mean, geom = "bar", position = position_dodge(width = 0.8), width = 0.75) +
stat_summary(fun.data = mean_cl_boot, geom = "errorbar", colour = "grey",
position = position_dodge(width = 0.8), width = 0.2) +
scale_y_continuous(limits = c(0, 100)) +
theme_bw() +
scale_fill_manual(values = c("grey","#80b1d3")) +
labs(x = "",
y = "Score",
title = "Effects on support for police reforms") +
theme(
plot.title = element_text(hjust = 0.5, size = 14),
plot.subtitle = element_text(hjust = 0.5),
plot.caption = element_text(hjust = 0.5, face = "italic")
) 
#plot trust in the police
S5_long <- S5 %>%
pivot_longer(cols = c(TrustGov_sc, TrustPolice_sc, MoralPolice_sc, HarmfulPolice_sc, PolicySupport),
names_to = "DV", values_to = "value")
S5_long$DV <- factor(S5_long$DV, levels = c("HarmfulPolice_sc", "MoralPolice_sc", "TrustPolice_sc", "TrustGov_sc", "PolicySupport"))
# Plotting
p_trustpol <- ggplot(S5_long, aes(x = DV, y = value, fill = condition)) +
stat_summary(fun = mean, geom = "bar", position = position_dodge(width = 0.8), width = 0.75) +
stat_summary(fun.data = mean_cl_boot, geom = "errorbar", colour = "grey",
position = position_dodge(width = 0.8), width = 0.2) +
scale_y_continuous(limits = c(0, 100)) +
theme_bw() +
scale_fill_manual(values = c("#ffffb3","#80b1d3", "#8dd3c7", "#fb8072")) +
labs(x = "Condition",
y = "Score",
title = "Effects on dependent variables") +
theme(
plot.title = element_text(hjust = 0.5, size = 14),
plot.subtitle = element_text(hjust = 0.5),
plot.caption = element_text(hjust = 0.5, face = "italic")
)
# Print the plot
print(p_trustpol)
#violin plot with ideology