revision_analyses
dani grant
2024-03-21
1 0. data prep
2 descriptives
mean(d$education, na.rm = T)## [1] 14.63202sd(d$education, na.rm = T)## [1] 2.622589mean(d$CRT, na.rm = T)## [1] 0.404966sd(d$CRT, na.rm = T)## [1] 0.3141821corr.test(af$bias.af, af$bias.as)## Call:corr.test(x = af$bias.af, y = af$bias.as)
## Correlation matrix
## [1] 0.93
## Sample Size
## [1] 23
## These are the unadjusted probability values.
## The probability values adjusted for multiple tests are in the p.adj object.
## [1] 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option## visualize media bias.z
ggplot(data = af, aes(x = mediaOutlet, y = bias.z, fill = country)) +
ggtitle("media bias standardized") +
geom_bar(stat = "identity", position = position_dodge()) +
geom_text(aes(label = mediaOutlet), vjust = 1.6, color = "black", position = position_dodge(0.9), size = 3) +
theme_minimal() +
coord_cartesian(ylim = c(-3, 3))## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_bar()`).## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_text()`).
2.1 1. Spring 2022 Correlation Table (Table 1)
library(apaTables)
corr <- data.frame(d$vaxxIntent.w1w2.z)
colnames(corr)[colnames(corr) == "d.vaxxIntent.w1w2.z"] <- "vaxxIntentions"
corr$trustSci <- d$trustSci.z
corr$Age <- d$age.z
corr$Education <- d$education.z
corr$Ethnicity <- d$white_1
corr$Ideology <- d$ideology.z
corr$CRT <- d$crt.z
corr$CMC.2020 <- d$bias.mean.1.15.z
corr$CMC.2022 <- d$bias.mean.3.20.z
corr$VMC.2020 <- d$bias.sd.w1w2.15.z
corr$VMC.2022 <- d$bias.sd.3.20.z
# create APA table
apa.cor.table(
corr,
filename = "Table1.doc",
table.number = 1,
show.conf.interval = FALSE,
show.sig.stars = TRUE,
landscape = TRUE
)## The ability to suppress reporting of reporting confidence intervals has been deprecated in this version.
## The function argument show.conf.interval will be removed in a later version.##
##
## Table 1
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2 3
## 1. vaxxIntentions -0.00 1.00
##
## 2. trustSci 0.00 1.00 .40**
## [.34, .45]
##
## 3. Age 0.27 0.93 .17** .06
## [.10, .23] [-.00, .13]
##
## 4. Education 0.12 0.91 .07* .13** -.00
## [.01, .13] [.07, .19] [-.07, .06]
##
## 5. Ideology 0.07 1.07 -.18** -.45** .13**
## [-.24, -.11] [-.50, -.40] [.07, .19]
##
## 6. CRT 0.00 1.00 .10** .14** .03
## [.04, .16] [.08, .20] [-.03, .10]
##
## 7. CMC.2020 0.00 1.00 -.21** -.32** .13**
## [-.27, -.14] [-.38, -.26] [.07, .20]
##
## 8. CMC.2022 0.00 1.00 -.20** -.51** -.03
## [-.26, -.13] [-.56, -.46] [-.09, .04]
##
## 9. VMC.2020 0.00 1.00 .23** .09** -.03
## [.17, .29] [.03, .15] [-.09, .04]
##
## 10. VMC.2022 -0.00 1.00 .19** -.03 -.10**
## [.13, .25] [-.09, .03] [-.17, -.04]
##
## 4 5 6 7 8 9
##
##
##
##
##
##
##
##
##
##
##
## -.06
## [-.12, .00]
##
## .21** .01
## [.15, .27] [-.06, .07]
##
## -.02 .49** .14**
## [-.08, .04] [.44, .54] [.08, .21]
##
## -.07* .53** .03 .66**
## [-.13, -.00] [.48, .57] [-.03, .09] [.62, .69]
##
## -.02 -.08* -.17** -.48** -.22**
## [-.08, .04] [-.14, -.02] [-.23, -.11] [-.52, -.43] [-.28, -.16]
##
## -.04 -.10** -.24** -.42** -.17** .61**
## [-.10, .03] [-.16, -.04] [-.30, -.18] [-.47, -.37] [-.23, -.11] [.56, .64]
##
##
## Note. M and SD are used to represent mean and standard deviation, respectively.
## Values in square brackets indicate the 95% confidence interval.
## The confidence interval is a plausible range of population correlations
## that could have caused the sample correlation (Cumming, 2014).
## * indicates p < .05. ** indicates p < .01.
## 2.2 2. Vaccination Behavior (Table 2A)
m.vaxx <- polr(vaxxBehavior ~ bias.mean.3.20.z * bias.sd.3.20.z +
(bias.mean.3.20.z + bias.sd.3.20.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z), data = d, Hess = TRUE)
tab_model(m.vaxx,
string.est = "OR",
dv.labels = "Standardized Vaccination Behavior",
pred.labels = c("1|2",
"2|3",
"Conservative Media Consumption (CMC)",
"Variability in Media Consumption (VMC)",
"Cognitive Reflection (CRT)",
"Ideology",
"Ethnicity",
"Age",
"Education",
"CMC x VMC",
"CMC x CRT",
"CMC x Ideology",
"CMC x Ethnicity",
"CMC x Age",
"CMC x Education",
"VMC x CRT",
"VMC x Ideology",
"VMC x Ethnicity",
"VMC x Age",
"VMC x Education"),
show.stat = T,
show.se = T,
string.se = "SE",
string.stat = "t",
digits = 2)| Standardized Vaccination Behavior | |||||
|---|---|---|---|---|---|
| Predictors | OR | SE | CI | t | p |
| 1|2 | 0.20 | 0.02 | 0.15 – 0.25 | -13.76 | <0.001 |
| 2|3 | 0.55 | 0.06 | 0.45 – 0.68 | -5.63 | <0.001 |
| Conservative Media Consumption (CMC) | 0.52 | 0.07 | 0.40 – 0.66 | -5.16 | <0.001 |
| Variability in Media Consumption (VMC) | 1.53 | 0.16 | 1.26 – 1.88 | 4.19 | <0.001 |
| Cognitive Reflection (CRT) | 1.22 | 0.11 | 1.03 – 1.45 | 2.28 | 0.023 |
| Ideology | 0.77 | 0.07 | 0.65 – 0.91 | -3.03 | 0.003 |
| Ethnicity | 0.91 | 0.16 | 0.64 – 1.29 | -0.50 | 0.617 |
| Age | 1.74 | 0.15 | 1.47 – 2.07 | 6.32 | <0.001 |
| Education | 1.35 | 0.12 | 1.14 – 1.61 | 3.43 | 0.001 |
| CMC x VMC | 1.47 | 0.20 | 1.13 – 1.92 | 2.91 | 0.004 |
| CMC x CRT | 1.01 | 0.09 | 0.85 – 1.19 | 0.07 | 0.944 |
| CMC x Ideology | 0.93 | 0.08 | 0.79 – 1.10 | -0.83 | 0.405 |
| CMC x Ethnicity | 0.82 | 0.17 | 0.55 – 1.22 | -0.99 | 0.325 |
| CMC x Age | 0.92 | 0.09 | 0.76 – 1.12 | -0.79 | 0.427 |
| CMC x Education | 0.95 | 0.10 | 0.78 – 1.16 | -0.54 | 0.586 |
| VMC x CRT | 1.05 | 0.10 | 0.88 – 1.27 | 0.57 | 0.571 |
| VMC x Ideology | 1.10 | 0.09 | 0.94 – 1.29 | 1.15 | 0.249 |
| VMC x Ethnicity | 0.82 | 0.14 | 0.58 – 1.14 | -1.18 | 0.237 |
| VMC x Age | 1.03 | 0.10 | 0.86 – 1.25 | 0.35 | 0.727 |
| VMC x Education | 0.93 | 0.07 | 0.80 – 1.07 | -0.94 | 0.346 |
| Observations | 909 | ||||
| R2 Nagelkerke | 0.416 | ||||
2.2.1 - CMC x VMC
d$hi.variety <- d$bias.sd.3.20.z - 1
d$low.variety <- d$bias.sd.3.20.z + 1
m.low <- polr(vaxxBehavior ~ (bias.mean.3.20.z * low.variety) +
(bias.mean.3.20.z + low.variety) *
(crt.z + ideology.z + white_.5 + age.z + education.z), data = d, Hess = TRUE)
m.hi <- polr(vaxxBehavior ~ (bias.mean.3.20.z * hi.variety) +
(bias.mean.3.20.z + hi.variety) *
(crt.z + ideology.z + white_.5 + age.z + education.z), data = d, Hess = TRUE)
tab_model(m.low, m.vaxx, m.hi,
string.est = "OR",
title = "Outcome: Standardized Vaccination Behavior",
dv.labels = c("Low Variety","Mean", "High Variety"),
pred.labels = c("1|2",
"2|3",
"Conservative Media Consumption (CMC)",
"Variability in Media Consumption (VMC)",
"Cognitive Reflection (CRT)",
"Ideology",
"Ethnicity",
"Age",
"Education",
"CMC x VMC",
"CMC x CRT",
"CMC x Ideology",
"CMC x Ethnicity",
"CMC x Age",
"CMC x Education",
"VMC x CRT",
"VMC x Ideology",
"VMC x Ethnicity",
"VMC x Age",
"VMC x Education"),
show.stat = T,
show.se = T,
string.se = "SE",
string.stat = "t",
digits = 2)## Length of `pred.labels` does not equal number of predictors, no labelling applied.| Low Variety | Mean | High Variety | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | OR | SE | CI | t | p | OR | SE | CI | t | p | OR | SE | CI | t | p |
| 1|2 | 0.30 | 0.04 | 0.23 – 0.39 | -8.58 | <0.001 | 0.20 | 0.02 | 0.15 – 0.25 | -13.76 | <0.001 | 0.13 | 0.02 | 0.09 – 0.18 | -12.09 | <0.001 |
| 2|3 | 0.85 | 0.11 | 0.65 – 1.10 | -1.25 | 0.212 | 0.55 | 0.06 | 0.45 – 0.68 | -5.63 | <0.001 | 0.36 | 0.06 | 0.27 – 0.49 | -6.46 | <0.001 |
| bias.mean.3.20.z | 0.35 | 0.08 | 0.22 – 0.54 | -4.65 | <0.001 | 0.52 | 0.07 | 0.40 – 0.66 | -5.16 | <0.001 | 0.76 | 0.10 | 0.59 – 0.99 | -2.04 | 0.042 |
| low.variety | 1.53 | 0.16 | 1.26 – 1.88 | 4.19 | <0.001 | ||||||||||
| crt.z | 1.16 | 0.13 | 0.93 – 1.44 | 1.33 | 0.183 | 1.22 | 0.11 | 1.03 – 1.45 | 2.28 | 0.023 | 1.29 | 0.18 | 0.98 – 1.71 | 1.76 | 0.079 |
| ideology.z | 0.70 | 0.08 | 0.56 – 0.87 | -3.14 | 0.002 | 0.77 | 0.07 | 0.65 – 0.91 | -3.03 | 0.003 | 0.85 | 0.10 | 0.66 – 1.08 | -1.35 | 0.178 |
| white_.5 | 1.12 | 0.27 | 0.69 – 1.81 | 0.47 | 0.640 | 0.91 | 0.16 | 0.64 – 1.29 | -0.50 | 0.617 | 0.75 | 0.19 | 0.45 – 1.21 | -1.17 | 0.242 |
| age.z | 1.68 | 0.19 | 1.35 – 2.11 | 4.52 | <0.001 | 1.74 | 0.15 | 1.47 – 2.07 | 6.32 | <0.001 | 1.80 | 0.25 | 1.37 – 2.38 | 4.17 | <0.001 |
| education.z | 1.45 | 0.18 | 1.14 – 1.87 | 2.93 | 0.004 | 1.35 | 0.12 | 1.14 – 1.61 | 3.43 | 0.001 | 1.26 | 0.13 | 1.02 – 1.53 | 2.27 | 0.023 |
| bias.mean.3.20.z:low.variety | 1.47 | 0.20 | 1.13 – 1.92 | 2.91 | 0.004 | ||||||||||
| bias.mean.3.20.z:crt.z | 1.01 | 0.09 | 0.85 – 1.19 | 0.07 | 0.944 | 1.01 | 0.09 | 0.85 – 1.19 | 0.07 | 0.944 | 1.01 | 0.09 | 0.85 – 1.19 | 0.07 | 0.944 |
| bias.mean.3.20.z:ideology.z | 0.93 | 0.08 | 0.79 – 1.10 | -0.83 | 0.405 | 0.93 | 0.08 | 0.79 – 1.10 | -0.83 | 0.405 | 0.93 | 0.08 | 0.79 – 1.10 | -0.83 | 0.405 |
| bias.mean.3.20.z:white_.5 | 0.82 | 0.17 | 0.55 – 1.22 | -0.99 | 0.325 | 0.82 | 0.17 | 0.55 – 1.22 | -0.99 | 0.325 | 0.82 | 0.17 | 0.55 – 1.22 | -0.99 | 0.325 |
| bias.mean.3.20.z:age.z | 0.92 | 0.09 | 0.76 – 1.12 | -0.79 | 0.427 | 0.92 | 0.09 | 0.76 – 1.12 | -0.79 | 0.427 | 0.92 | 0.09 | 0.76 – 1.12 | -0.79 | 0.427 |
| bias.mean.3.20.z:education.z | 0.95 | 0.10 | 0.78 – 1.16 | -0.54 | 0.586 | 0.95 | 0.10 | 0.78 – 1.16 | -0.54 | 0.586 | 0.95 | 0.10 | 0.78 – 1.16 | -0.54 | 0.586 |
| low.variety:crt.z | 1.05 | 0.10 | 0.88 – 1.27 | 0.57 | 0.571 | ||||||||||
| low.variety:ideology.z | 1.10 | 0.09 | 0.94 – 1.29 | 1.15 | 0.249 | ||||||||||
| low.variety:white_.5 | 0.82 | 0.14 | 0.58 – 1.14 | -1.18 | 0.237 | ||||||||||
| low.variety:age.z | 1.03 | 0.10 | 0.86 – 1.25 | 0.35 | 0.727 | ||||||||||
| low.variety:education.z | 0.93 | 0.07 | 0.80 – 1.07 | -0.94 | 0.346 | ||||||||||
| bias.sd.3.20.z | 1.53 | 0.16 | 1.26 – 1.88 | 4.19 | <0.001 | ||||||||||
| bias.mean.3.20.z:bias.sd.3.20.z | 1.47 | 0.20 | 1.13 – 1.92 | 2.91 | 0.004 | ||||||||||
| bias.sd.3.20.z:crt.z | 1.05 | 0.10 | 0.88 – 1.27 | 0.57 | 0.571 | ||||||||||
| bias.sd.3.20.z:ideology.z | 1.10 | 0.09 | 0.94 – 1.29 | 1.15 | 0.249 | ||||||||||
| bias.sd.3.20.z:white_.5 | 0.82 | 0.14 | 0.58 – 1.14 | -1.18 | 0.237 | ||||||||||
| bias.sd.3.20.z:age.z | 1.03 | 0.10 | 0.86 – 1.25 | 0.35 | 0.727 | ||||||||||
| bias.sd.3.20.z:education.z | 0.93 | 0.07 | 0.80 – 1.07 | -0.94 | 0.346 | ||||||||||
| hi.variety | 1.53 | 0.16 | 1.26 – 1.88 | 4.19 | <0.001 | ||||||||||
| bias.mean.3.20.z:hi.variety | 1.47 | 0.20 | 1.13 – 1.92 | 2.91 | 0.004 | ||||||||||
| hi.variety:crt.z | 1.05 | 0.10 | 0.88 – 1.27 | 0.57 | 0.571 | ||||||||||
| hi.variety:ideology.z | 1.10 | 0.09 | 0.94 – 1.29 | 1.15 | 0.249 | ||||||||||
| hi.variety:white_.5 | 0.82 | 0.14 | 0.58 – 1.14 | -1.18 | 0.237 | ||||||||||
| hi.variety:age.z | 1.03 | 0.10 | 0.86 – 1.25 | 0.35 | 0.727 | ||||||||||
| hi.variety:education.z | 0.93 | 0.07 | 0.80 – 1.07 | -0.94 | 0.346 | ||||||||||
| Observations | 909 | 909 | 909 | ||||||||||||
| R2 Nagelkerke | 0.416 | 0.416 | 0.416 | ||||||||||||
## just a model to help make sense of the CMC x VMC interaction!
d$vaxx.num <- as.numeric(d$vaxxBehavior)
m.test <- lm(vaxx.num ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z), data = d)
interact_plot(m.test, bias.mean.3.20.z, bias.sd.3.20.z)
2.2.2 - Figure 1A
(Fig1A <- ggpredict(m.vaxx, terms = "bias.mean.3.20.z[-3, -2.5, -2, -1.5, -1, -.5, 0, .5, 1, 1.5, 2, 2.5, 3]") %>%
ggplot(mapping = aes(x = x, y = predicted, colour = response.level, fill = response.level)) +
geom_line(size = 1) +
scale_x_continuous(limits = c(-2, 2), breaks = c(-3:3)) +
scale_y_continuous(limits = c(0, 1), breaks = c(0, .1,.2,.3,.4,.5, .6, .7, .8, .9, 1)) +
labs(title = "Predicted Probabilities for Vaccination Behaviors",
x = "Standardized Conservative Media Consumption",
y = "Predicted Probability for Vaccination Behavior Choice") +
theme_minimal() +
theme(plot.title = element_text(size = 12)) + labs(colour = "Vaccination Behavior") +
geom_ribbon(aes(ymin = conf.low, ymax = conf.high), alpha = 0.2, colour = NA))## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: Removed 12 rows containing missing values or values outside the scale range
## (`geom_line()`).
2.2.3 - Figure 1B
(Fig1B <- ggpredict(m.vaxx, terms = "bias.sd.3.20.z[-3, -2.5, -2, -1.5, -1, -.5, 0, .5, 1, 1.5, 2, 2.5, 3]") %>%
ggplot(mapping = aes(x = x, y = predicted, colour = response.level, fill = response.level)) +
geom_line(size = 1) +
scale_x_continuous(limits = c(-2, 2), breaks = c(-3:3)) +
scale_y_continuous(limits = c(0, 1), breaks = c(0, .1,.2,.3,.4,.5, .6, .7, .8, .9, 1)) +
labs(title = "Predicted Probabilities for Vaccination Behaviors",
x = "Standardized Variability in Media Consumption",
y = "Predicted Probability for Vaccination Behavior Choice") +
theme_minimal() +
theme(plot.title = element_text(size = 12)) + labs(colour = "Vaccination Behavior") +
geom_ribbon(aes(ymin = conf.low, ymax = conf.high), alpha = 0.2, colour = NA))## Warning: Removed 12 rows containing missing values or values outside the scale range
## (`geom_line()`).
2.3 3. Trust in Science (Table 2B)
m2.med <- lm(trustSci.z ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z), data = d)
tab_model(m2.med,
string.est = "Est",
dv.labels = "Standardized Trust in Science",
pred.labels = c("Intercept",
"Conservative Media Consumption (CMC)",
"Variability in Media Consumption (VMC)",
"Cognitive Reflection (CRT)",
"Ideology",
"Ethnicity",
"Age",
"Education",
"CMC x VMC",
"CMC x CRT",
"CMC x Ideology",
"CMC x Ethnicity",
"CMC x Age",
"CMC x Education",
"VMC x CRT",
"VMC x Ideology",
"VMC x Ethnicity",
"VMC x Age",
"VMC x Education"),
show.stat = T,
show.se = T,
string.se = "SE",
string.stat = "t",
digits = 2)| Standardized Trust in Science | |||||
|---|---|---|---|---|---|
| Predictors | Est | SE | CI | t | p |
| Intercept | 0.02 | 0.04 | -0.05 – 0.09 | 0.64 | 0.521 |
| Conservative Media Consumption (CMC) | -0.53 | 0.04 | -0.62 – -0.44 | -11.94 | <0.001 |
| Variability in Media Consumption (VMC) | -0.07 | 0.03 | -0.14 – -0.01 | -2.15 | 0.032 |
| Cognitive Reflection (CRT) | 0.10 | 0.03 | 0.04 – 0.16 | 3.40 | 0.001 |
| Ideology | -0.23 | 0.03 | -0.28 – -0.17 | -7.49 | <0.001 |
| Ethnicity | 0.19 | 0.06 | 0.07 – 0.32 | 3.05 | 0.002 |
| Age | 0.07 | 0.03 | 0.01 – 0.13 | 2.33 | 0.020 |
| Education | 0.06 | 0.03 | -0.00 – 0.12 | 1.89 | 0.059 |
| CMC x VMC | 0.21 | 0.04 | 0.12 – 0.30 | 4.76 | <0.001 |
| CMC x CRT | -0.01 | 0.03 | -0.07 – 0.04 | -0.46 | 0.646 |
| CMC x Ideology | -0.01 | 0.03 | -0.06 – 0.04 | -0.43 | 0.668 |
| CMC x Ethnicity | -0.08 | 0.06 | -0.20 – 0.05 | -1.23 | 0.218 |
| CMC x Age | 0.06 | 0.03 | -0.00 – 0.12 | 1.93 | 0.054 |
| CMC x Education | 0.02 | 0.04 | -0.05 – 0.09 | 0.66 | 0.508 |
| VMC x CRT | 0.03 | 0.03 | -0.04 – 0.09 | 0.85 | 0.396 |
| VMC x Ideology | 0.05 | 0.03 | -0.00 – 0.11 | 1.81 | 0.070 |
| VMC x Ethnicity | -0.08 | 0.06 | -0.20 – 0.04 | -1.33 | 0.182 |
| VMC x Age | 0.10 | 0.03 | 0.04 – 0.16 | 3.17 | 0.002 |
| VMC x Education | -0.04 | 0.02 | -0.09 – 0.00 | -1.77 | 0.077 |
| Observations | 908 | ||||
| R2 / R2 adjusted | 0.396 / 0.383 | ||||
round(etaSquared(m2.med),3)## eta.sq eta.sq.part
## bias.mean.3.20.z 0.112 0.156
## bias.sd.3.20.z 0.003 0.005
## crt.z 0.007 0.012
## ideology.z 0.038 0.060
## white_.5 0.007 0.011
## age.z 0.003 0.005
## education.z 0.002 0.003
## bias.mean.3.20.z:bias.sd.3.20.z 0.015 0.025
## bias.mean.3.20.z:crt.z 0.000 0.000
## bias.mean.3.20.z:ideology.z 0.000 0.000
## bias.mean.3.20.z:white_.5 0.001 0.002
## bias.mean.3.20.z:age.z 0.003 0.004
## bias.mean.3.20.z:education.z 0.000 0.000
## bias.sd.3.20.z:crt.z 0.000 0.001
## bias.sd.3.20.z:ideology.z 0.002 0.004
## bias.sd.3.20.z:white_.5 0.001 0.002
## bias.sd.3.20.z:age.z 0.007 0.011
## bias.sd.3.20.z:education.z 0.002 0.0042.3.1 - VMC x CMC
m2.low <- lm(trustSci.z ~ (bias.mean.3.20.z * low.variety) +
(bias.mean.3.20.z + low.variety) *
(crt.z + ideology.z + white_.5 + age.z + education.z), data = d)
m2.hi <- lm(trustSci.z ~ (bias.mean.3.20.z * hi.variety) +
(bias.mean.3.20.z + hi.variety) *
(crt.z + ideology.z + white_.5 + age.z + education.z), data = d)
tab_model(m2.low, m2.hi,
string.est = "Est",
dv.labels = "Standardized Trust in Science",
pred.labels = c("Intercept",
"Conservative Media Consumption (CMC)",
"Variability in Media Consumption (VMC)",
"Cognitive Reflection (CRT)",
"Ideology",
"Ethnicity",
"Age",
"Education",
"CMC x VMC",
"CMC x CRT",
"CMC x Ideology",
"CMC x Ethnicity",
"CMC x Age",
"CMC x Education",
"VMC x CRT",
"VMC x Ideology",
"VMC x Ethnicity",
"VMC x Age",
"VMC x Education"),
show.stat = T,
show.se = T,
string.se = "SE",
string.stat = "t",
digits = 2)## Length of `pred.labels` does not equal number of predictors, no labelling applied.| Standardized Trust in Science | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Est | SE | CI | t | p | Est | SE | CI | t | p |
| (Intercept) | 0.09 | 0.05 | 0.00 – 0.19 | 1.99 | 0.047 | -0.05 | 0.05 | -0.15 – 0.05 | -0.96 | 0.339 |
| bias.mean.3.20.z | -0.74 | 0.08 | -0.89 – -0.59 | -9.63 | <0.001 | -0.32 | 0.04 | -0.41 – -0.23 | -7.27 | <0.001 |
| low.variety | -0.07 | 0.03 | -0.14 – -0.01 | -2.15 | 0.032 | |||||
| crt.z | 0.07 | 0.04 | -0.01 – 0.15 | 1.80 | 0.073 | 0.13 | 0.05 | 0.04 – 0.22 | 2.73 | 0.006 |
| ideology.z | -0.28 | 0.04 | -0.36 – -0.20 | -6.76 | <0.001 | -0.17 | 0.04 | -0.26 – -0.09 | -4.24 | <0.001 |
| white_.5 | 0.27 | 0.09 | 0.10 – 0.45 | 3.05 | 0.002 | 0.11 | 0.08 | -0.05 – 0.28 | 1.35 | 0.176 |
| age.z | -0.03 | 0.04 | -0.11 – 0.05 | -0.71 | 0.478 | 0.17 | 0.04 | 0.08 – 0.26 | 3.74 | <0.001 |
| education.z | 0.10 | 0.04 | 0.02 – 0.19 | 2.33 | 0.020 | 0.02 | 0.04 | -0.05 – 0.08 | 0.44 | 0.658 |
| bias.mean.3.20.z:low.variety | 0.21 | 0.04 | 0.12 – 0.30 | 4.76 | <0.001 | |||||
| bias.mean.3.20.z:crt.z | -0.01 | 0.03 | -0.07 – 0.04 | -0.46 | 0.646 | -0.01 | 0.03 | -0.07 – 0.04 | -0.46 | 0.646 |
| bias.mean.3.20.z:ideology.z | -0.01 | 0.03 | -0.06 – 0.04 | -0.43 | 0.668 | -0.01 | 0.03 | -0.06 – 0.04 | -0.43 | 0.668 |
| bias.mean.3.20.z:white_.5 | -0.08 | 0.06 | -0.20 – 0.05 | -1.23 | 0.218 | -0.08 | 0.06 | -0.20 – 0.05 | -1.23 | 0.218 |
| bias.mean.3.20.z:age.z | 0.06 | 0.03 | -0.00 – 0.12 | 1.93 | 0.054 | 0.06 | 0.03 | -0.00 – 0.12 | 1.93 | 0.054 |
| bias.mean.3.20.z:education.z | 0.02 | 0.04 | -0.05 – 0.09 | 0.66 | 0.508 | 0.02 | 0.04 | -0.05 – 0.09 | 0.66 | 0.508 |
| low.variety:crt.z | 0.03 | 0.03 | -0.04 – 0.09 | 0.85 | 0.396 | |||||
| low.variety:ideology.z | 0.05 | 0.03 | -0.00 – 0.11 | 1.81 | 0.070 | |||||
| low.variety:white_.5 | -0.08 | 0.06 | -0.20 – 0.04 | -1.33 | 0.182 | |||||
| low.variety:age.z | 0.10 | 0.03 | 0.04 – 0.16 | 3.17 | 0.002 | |||||
| low.variety:education.z | -0.04 | 0.02 | -0.09 – 0.00 | -1.77 | 0.077 | |||||
| hi.variety | -0.07 | 0.03 | -0.14 – -0.01 | -2.15 | 0.032 | |||||
| bias.mean.3.20.z:hi.variety | 0.21 | 0.04 | 0.12 – 0.30 | 4.76 | <0.001 | |||||
| hi.variety:crt.z | 0.03 | 0.03 | -0.04 – 0.09 | 0.85 | 0.396 | |||||
| hi.variety:ideology.z | 0.05 | 0.03 | -0.00 – 0.11 | 1.81 | 0.070 | |||||
| hi.variety:white_.5 | -0.08 | 0.06 | -0.20 – 0.04 | -1.33 | 0.182 | |||||
| hi.variety:age.z | 0.10 | 0.03 | 0.04 – 0.16 | 3.17 | 0.002 | |||||
| hi.variety:education.z | -0.04 | 0.02 | -0.09 – 0.00 | -1.77 | 0.077 | |||||
| Observations | 908 | 908 | ||||||||
| R2 / R2 adjusted | 0.396 / 0.383 | 0.396 / 0.383 | ||||||||
2.3.2 - Figure 2
#create plot
(p2 <- plot_model(m2.med, type = "pred", terms = c("bias.mean.3.20.z", "bias.sd.3.20.z [-1, 0, 1]")) +
ggtitle("") +
ylab("") +
xlab("Conservative Media Consumption") +
xlim(-2, 2) +
ylim(-3, 2) +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.line = element_line(colour = "black"),
legend.position = c(0.8, 0.8),
legend.background = element_rect(fill = "white", color = "white"),
legend.title = element_blank()) +
scale_color_manual( labels = c("Low (-1 SD)", "Mean", "High (+1 SD)"),
values = c("blue", "purple", "red")) +
scale_fill_manual(values = c("blue", "purple", "red")) +
scale_y_continuous(breaks = c(-2.993, -1.775, -0.558, 0.660, 1.878),
limits = c(-3.193, 2.2),
labels = c("Strongly distrust",
"Moderately distrust",
"Neither trust nor distrust",
"Moderately trust",
"Strongly trust"))
)## Scale for y is already present.
## Adding another scale for y, which will replace the existing scale.## Warning: A numeric `legend.position` argument in `theme()` was deprecated in ggplot2
## 3.5.0.
## ℹ Please use the `legend.position.inside` argument of `theme()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Scale for colour is already present.
## Adding another scale for colour, which will replace the existing scale.
## Scale for y is already present.
## Adding another scale for y, which will replace the existing scale.## Warning: Removed 9 rows containing missing values or values outside the scale range
## (`geom_line()`).
2.4 4. Long - Vaccination Behavior (Table 3)
m.vaxx.long <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.w1w2.15.z * bias.sd.w1w2.15.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + bias.mean.w1w2.15.z + bias.sd.w1w2.15.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z) +
vaxxIntent.w1w2.z,
data = d, Hess = TRUE)
tab_model(m.vaxx.long,
string.est = "OR",
dv.labels = "Standardized Vaccination Behavior",
pred.labels = c("1|2",
"2|3",
"Conservative Media Consumption 2022 (CMC 2022)",
"Variability in Media Consumption 2022 (VMC 2022)",
"Conservative Media Consumption 2020 (CMC 2020)",
"Variability in Media Consumption 2020 (VMC 2020)",
"Cognitive Reflection (CRT)",
"Ideology",
"Ethnicity",
"Age",
"Education",
"Vaccination Intention 2020",
"CMC 2022 x VMC22",
"CMC 2020 x VMC20",
"CMC 2022 x CRT",
"CMC 2022 x Ideology",
"CMC 2022 x Ethnicity",
"CMC 2022 x Age",
"CMC 2022 x Education",
"VMC 2022 x CRT",
"VMC 2022 x Ideology",
"VMC 2022 x Ethnicity",
"VMC 2022 x Age",
"VMC 2022 x Education",
"CMC 2020 x CRT",
"CMC 2020 x Ideology",
"CMC 2020 x Ethnicity",
"CMC 2020 x Age",
"CMC 2020 x Education",
"VMC 2020 x CRT",
"VMC 2020 x Ideology",
"VMC 2020 x Ethnicity",
"VMC 2020 x Age",
"VMC 2020 x Education"),
show.stat = T,
show.se = T,
string.se = "SE",
string.stat = "t",
digits = 2)| Standardized Vaccination Behavior | |||||
|---|---|---|---|---|---|
| Predictors | OR | SE | CI | t | p |
| 1|2 | 0.11 | 0.02 | 0.08 – 0.15 | -14.28 | <0.001 |
| 2|3 | 0.44 | 0.06 | 0.34 – 0.56 | -6.38 | <0.001 |
| Conservative Media Consumption 2022 (CMC 2022) | 0.56 | 0.10 | 0.39 – 0.78 | -3.34 | 0.001 |
| Variability in Media Consumption 2022 (VMC 2022) | 1.52 | 0.21 | 1.16 – 2.00 | 3.01 | 0.003 |
| Conservative Media Consumption 2020 (CMC 2020) | 0.89 | 0.18 | 0.60 – 1.32 | -0.59 | 0.552 |
| Variability in Media Consumption 2020 (VMC 2020) | 0.78 | 0.11 | 0.59 – 1.02 | -1.78 | 0.076 |
| Cognitive Reflection (CRT) | 1.07 | 0.10 | 0.89 – 1.30 | 0.74 | 0.460 |
| Ideology | 0.83 | 0.08 | 0.68 – 1.00 | -1.97 | 0.049 |
| Ethnicity | 0.79 | 0.16 | 0.54 – 1.16 | -1.19 | 0.234 |
| Age | 1.55 | 0.15 | 1.28 – 1.87 | 4.50 | <0.001 |
| Education | 1.35 | 0.13 | 1.12 – 1.62 | 3.14 | 0.002 |
| Vaccination Intention 2020 | 3.02 | 0.27 | 2.53 – 3.62 | 12.13 | <0.001 |
| CMC 2022 x VMC22 | 1.29 | 0.20 | 0.94 – 1.75 | 1.60 | 0.111 |
| CMC 2020 x VMC20 | 1.39 | 0.15 | 1.13 – 1.71 | 3.14 | 0.002 |
| CMC 2022 x CRT | 0.85 | 0.11 | 0.65 – 1.10 | -1.27 | 0.206 |
| CMC 2022 x Ideology | 0.97 | 0.12 | 0.75 – 1.25 | -0.27 | 0.785 |
| CMC 2022 x Ethnicity | 1.60 | 0.48 | 0.89 – 2.88 | 1.58 | 0.115 |
| CMC 2022 x Age | 0.67 | 0.10 | 0.50 – 0.89 | -2.76 | 0.006 |
| CMC 2022 x Education | 0.99 | 0.15 | 0.75 – 1.33 | -0.05 | 0.957 |
| VMC 2022 x CRT | 1.06 | 0.13 | 0.83 – 1.36 | 0.46 | 0.647 |
| VMC 2022 x Ideology | 0.83 | 0.10 | 0.64 – 1.06 | -1.51 | 0.130 |
| VMC 2022 x Ethnicity | 0.84 | 0.20 | 0.52 – 1.34 | -0.74 | 0.462 |
| VMC 2022 x Age | 1.04 | 0.13 | 0.81 – 1.35 | 0.34 | 0.736 |
| VMC 2022 x Education | 0.88 | 0.11 | 0.69 – 1.11 | -1.03 | 0.305 |
| CMC 2020 x CRT | 1.35 | 0.21 | 1.00 – 1.82 | 1.97 | 0.049 |
| CMC 2020 x Ideology | 1.02 | 0.15 | 0.77 – 1.35 | 0.12 | 0.902 |
| CMC 2020 x Ethnicity | 0.44 | 0.15 | 0.22 – 0.86 | -2.39 | 0.017 |
| CMC 2020 x Age | 1.20 | 0.18 | 0.89 – 1.63 | 1.22 | 0.225 |
| CMC 2020 x Education | 0.90 | 0.14 | 0.66 – 1.23 | -0.64 | 0.524 |
| VMC 2020 x CRT | 1.12 | 0.13 | 0.90 – 1.41 | 1.02 | 0.310 |
| VMC 2020 x Ideology | 1.35 | 0.16 | 1.08 – 1.71 | 2.57 | 0.010 |
| VMC 2020 x Ethnicity | 0.54 | 0.15 | 0.31 – 0.91 | -2.30 | 0.022 |
| VMC 2020 x Age | 1.09 | 0.13 | 0.87 – 1.39 | 0.75 | 0.454 |
| VMC 2020 x Education | 0.99 | 0.12 | 0.79 – 1.25 | -0.04 | 0.966 |
| Observations | 909 | ||||
| R2 Nagelkerke | 0.570 | ||||
2.5 5. Robustness checks - correlation table
d$vaxxBehavior.num <- as.numeric(d$vaxxBehavior)
corr <- data.frame(d$vaxxBehavior.num)
names(corr)## [1] "d.vaxxBehavior.num"colnames(corr)[colnames(corr) == "d.vaxxBehavior.num"] <- "vaxxBehavior"
corr$trustSci <- d$trustSci
corr$analytic <- d$analytic.mean.3.12
corr$affect <- d$affect.mean.3.12
corr$threat <- d$threat.mean.3.12
corr$negEmo <- d$negEmo.mean.3.12
corr$posEmo <- d$posEmo.mean.3.12
corr$clout <- d$clout.mean.3.12
corr$reliab <- d$rel.mean.3.19
corr$cons.media <- d$bias.mean.3.20
corr$variety <- d$bias.sd.3.20
corr2 <- corr_coef(corr, use = "pairwise.complete.obs")## Warning: Missing values in the data. Option 'pairwise.complete.obs' used to
## compute correlation with all complete pairs of observations.plot(corr2)
# to report in manuscript
cor.test(d$bias.mean.3.20, d$negEmo.mean.3.12)##
## Pearson's product-moment correlation
##
## data: d$bias.mean.3.20 and d$negEmo.mean.3.12
## t = -8.523, df = 990, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.3185147 -0.2025084
## sample estimates:
## cor
## -0.2614555cor.test(d$bias.mean.3.20, d$posEmo.mean.3.12)##
## Pearson's product-moment correlation
##
## data: d$bias.mean.3.20 and d$posEmo.mean.3.12
## t = -3.399, df = 990, p-value = 0.0007032
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.16852006 -0.04546525
## sample estimates:
## cor
## -0.107404cor.test(d$bias.mean.3.20, d$clout.mean.3.12)##
## Pearson's product-moment correlation
##
## data: d$bias.mean.3.20 and d$clout.mean.3.12
## t = -12.04, df = 990, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.4105061 -0.3018677
## sample estimates:
## cor
## -0.3573952cor.test(d$bias.mean.3.20, d$analytic.mean.3.12)##
## Pearson's product-moment correlation
##
## data: d$bias.mean.3.20 and d$analytic.mean.3.12
## t = -2.0947, df = 990, p-value = 0.03645
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.128139455 -0.004201302
## sample estimates:
## cor
## -0.06642659cor.test(d$bias.mean.3.20, d$rel.mean.3.19)##
## Pearson's product-moment correlation
##
## data: d$bias.mean.3.20 and d$rel.mean.3.19
## t = -51.316, df = 990, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.8686583 -0.8345493
## sample estimates:
## cor
## -0.8525088cor.test(d$bias.sd.3.20, d$rel.mean.3.19)##
## Pearson's product-moment correlation
##
## data: d$bias.sd.3.20 and d$rel.mean.3.19
## t = 2.7017, df = 990, p-value = 0.007017
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.02343212 0.14700987
## sample estimates:
## cor
## 0.085550012.6 6. Robust check - Vaccination behavior (Supplemental Table 3)
m.analytic <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * analytic.mean.3.12.z) +
(bias.sd.3.20.z * analytic.mean.3.12.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + analytic.mean.3.12.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
m.threat <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * threat.mean.3.12.z) +
(threat.mean.3.12.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + threat.mean.3.12.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
m.posEmo <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * posEmo.mean.3.12.z) +
(posEmo.mean.3.12.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + posEmo.mean.3.12.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
m.negEmo <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * negEmo.mean.3.12.z) +
(negEmo.mean.3.12.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + negEmo.mean.3.12.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
m.affect <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * affect.mean.3.12.z) +
(affect.mean.3.12.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + affect.mean.3.12.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
m.clout <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * clout.mean.3.12.z) +
(clout.mean.3.12.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + clout.mean.3.12.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
m.authentic <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * authentic.mean.3.12.z) +
(authentic.mean.3.12.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + authentic.mean.3.12.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
m.reliability <- polr(vaxxBehavior ~ (bias.mean.3.20.z * bias.sd.3.20.z) +
(bias.mean.3.20.z * rel.mean.3.19.z) +
(rel.mean.3.19.z * bias.sd.3.20.z) +
(bias.mean.3.20.z + bias.sd.3.20.z + rel.mean.3.19.z) *
(crt.z + ideology.z + white_.5 + age.z + education.z),
data = d, Hess = TRUE)
tab_model(m.affect, m.analytic, m.authentic, m.clout, m.posEmo, m.negEmo, m.threat, m.reliability,
dv.labels = c("affect", "analytic", "authentic", "clout",
"positive emotion", "negative emotion", "threat", "reliability"),
title = "Outcome: Vaccination Behavior",
pred.labels = c("Intercept"),
string.est = "Est",
show.stat = F,
show.se = F,
show.ci = F,
string.stat = "t",
digits = 2)## Length of `pred.labels` does not equal number of predictors, no labelling applied.| affect | analytic | authentic | clout | positive emotion | negative emotion | threat | reliability | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Est | p | Est | p | Est | p | Est | p | Est | p | Est | p | Est | p | Est | p |
| 1|2 | 0.19 | <0.001 | 0.20 | <0.001 | 0.19 | <0.001 | 0.20 | <0.001 | 0.19 | <0.001 | 0.19 | <0.001 | 0.20 | <0.001 | 0.19 | <0.001 |
| 2|3 | 0.55 | <0.001 | 0.57 | <0.001 | 0.55 | <0.001 | 0.57 | <0.001 | 0.56 | <0.001 | 0.55 | <0.001 | 0.57 | <0.001 | 0.54 | <0.001 |
| bias.mean.3.20.z | 0.50 | <0.001 | 0.51 | <0.001 | 0.52 | <0.001 | 0.52 | <0.001 | 0.51 | <0.001 | 0.50 | <0.001 | 0.50 | <0.001 | 0.73 | 0.122 |
| bias.sd.3.20.z | 1.56 | <0.001 | 1.47 | 0.001 | 1.53 | <0.001 | 1.54 | <0.001 | 1.50 | <0.001 | 1.57 | <0.001 | 1.55 | <0.001 | 1.63 | <0.001 |
| affect.mean.3.12.z | 0.92 | 0.427 | ||||||||||||||
| crt.z | 1.24 | 0.016 | 1.24 | 0.014 | 1.23 | 0.020 | 1.24 | 0.014 | 1.24 | 0.013 | 1.23 | 0.020 | 1.23 | 0.017 | 1.23 | 0.019 |
| ideology.z | 0.77 | 0.003 | 0.76 | 0.002 | 0.76 | 0.001 | 0.76 | 0.002 | 0.77 | 0.003 | 0.76 | 0.002 | 0.77 | 0.002 | 0.76 | 0.002 |
| white_.5 | 0.94 | 0.728 | 0.90 | 0.565 | 0.93 | 0.701 | 0.92 | 0.655 | 0.93 | 0.663 | 0.94 | 0.710 | 0.94 | 0.722 | 0.91 | 0.590 |
| age.z | 1.77 | <0.001 | 1.77 | <0.001 | 1.76 | <0.001 | 1.77 | <0.001 | 1.78 | <0.001 | 1.77 | <0.001 | 1.75 | <0.001 | 1.75 | <0.001 |
| education.z | 1.35 | 0.001 | 1.36 | 0.001 | 1.36 | 0.001 | 1.36 | 0.001 | 1.36 | 0.001 | 1.35 | 0.001 | 1.35 | 0.001 | 1.35 | 0.001 |
| bias.mean.3.20.z:bias.sd.3.20.z | 1.53 | 0.002 | 1.48 | 0.005 | 1.45 | 0.010 | 1.48 | 0.006 | 1.53 | 0.002 | 1.53 | 0.002 | 1.45 | 0.008 | 1.93 | 0.008 |
| bias.mean.3.20.z:affect.mean.3.12.z | 1.14 | 0.170 | ||||||||||||||
| bias.sd.3.20.z:affect.mean.3.12.z | 1.03 | 0.798 | ||||||||||||||
| bias.mean.3.20.z:crt.z | 1.04 | 0.703 | 1.03 | 0.721 | 1.02 | 0.822 | 1.03 | 0.779 | 1.05 | 0.596 | 1.01 | 0.890 | 1.02 | 0.804 | 1.07 | 0.714 |
| bias.mean.3.20.z:ideology.z | 0.90 | 0.253 | 0.90 | 0.249 | 0.88 | 0.187 | 0.93 | 0.416 | 0.90 | 0.221 | 0.91 | 0.311 | 0.92 | 0.324 | 1.06 | 0.736 |
| bias.mean.3.20.z:white_.5 | 0.84 | 0.418 | 0.80 | 0.288 | 0.94 | 0.796 | 0.81 | 0.343 | 0.80 | 0.284 | 0.87 | 0.516 | 0.82 | 0.331 | 0.80 | 0.540 |
| bias.mean.3.20.z:age.z | 0.98 | 0.833 | 0.87 | 0.186 | 0.95 | 0.652 | 0.99 | 0.919 | 0.95 | 0.619 | 0.97 | 0.787 | 0.90 | 0.291 | 1.03 | 0.859 |
| bias.mean.3.20.z:education.z | 0.94 | 0.561 | 0.94 | 0.544 | 0.91 | 0.403 | 0.94 | 0.573 | 0.95 | 0.648 | 0.93 | 0.549 | 0.92 | 0.423 | 1.05 | 0.789 |
| bias.sd.3.20.z:crt.z | 1.07 | 0.490 | 1.05 | 0.593 | 1.05 | 0.577 | 1.05 | 0.574 | 1.07 | 0.489 | 1.06 | 0.520 | 1.07 | 0.478 | 1.05 | 0.604 |
| bias.sd.3.20.z:ideology.z | 1.08 | 0.339 | 1.08 | 0.328 | 1.07 | 0.389 | 1.08 | 0.323 | 1.08 | 0.342 | 1.09 | 0.316 | 1.08 | 0.365 | 1.10 | 0.265 |
| bias.sd.3.20.z:white_.5 | 0.82 | 0.261 | 0.82 | 0.245 | 0.85 | 0.350 | 0.81 | 0.239 | 0.82 | 0.251 | 0.82 | 0.244 | 0.81 | 0.233 | 0.80 | 0.215 |
| bias.sd.3.20.z:age.z | 1.06 | 0.525 | 0.97 | 0.782 | 1.06 | 0.538 | 1.03 | 0.747 | 1.06 | 0.556 | 1.06 | 0.565 | 0.98 | 0.807 | 1.06 | 0.546 |
| bias.sd.3.20.z:education.z | 0.93 | 0.313 | 0.93 | 0.331 | 0.92 | 0.287 | 0.93 | 0.339 | 0.93 | 0.305 | 0.93 | 0.310 | 0.92 | 0.294 | 0.95 | 0.506 |
| affect.mean.3.12.z:crt.z | 0.99 | 0.872 | ||||||||||||||
| affect.mean.3.12.z:ideology.z | 0.89 | 0.177 | ||||||||||||||
| affect.mean.3.12.z:white_.5 | 1.20 | 0.348 | ||||||||||||||
| affect.mean.3.12.z:age.z | 1.25 | 0.019 | ||||||||||||||
| affect.mean.3.12.z:education.z | 0.94 | 0.552 | ||||||||||||||
| analytic.mean.3.12.z | 1.03 | 0.780 | ||||||||||||||
| bias.mean.3.20.z:analytic.mean.3.12.z | 0.88 | 0.162 | ||||||||||||||
| bias.sd.3.20.z:analytic.mean.3.12.z | 0.98 | 0.868 | ||||||||||||||
| analytic.mean.3.12.z:crt.z | 1.00 | 0.972 | ||||||||||||||
| analytic.mean.3.12.z:ideology.z | 1.03 | 0.736 | ||||||||||||||
| analytic.mean.3.12.z:white_.5 | 1.03 | 0.869 | ||||||||||||||
| analytic.mean.3.12.z:age.z | 0.76 | 0.005 | ||||||||||||||
| analytic.mean.3.12.z:education.z | 1.04 | 0.677 | ||||||||||||||
| authentic.mean.3.12.z | 0.99 | 0.942 | ||||||||||||||
| bias.mean.3.20.z:authentic.mean.3.12.z | 0.96 | 0.569 | ||||||||||||||
| bias.sd.3.20.z:authentic.mean.3.12.z | 1.07 | 0.564 | ||||||||||||||
| authentic.mean.3.12.z:crt.z | 0.98 | 0.830 | ||||||||||||||
| authentic.mean.3.12.z:ideology.z | 1.13 | 0.195 | ||||||||||||||
| authentic.mean.3.12.z:white_.5 | 0.83 | 0.390 | ||||||||||||||
| authentic.mean.3.12.z:age.z | 0.94 | 0.581 | ||||||||||||||
| authentic.mean.3.12.z:education.z | 1.12 | 0.374 | ||||||||||||||
| clout.mean.3.12.z | 1.00 | 0.967 | ||||||||||||||
| bias.mean.3.20.z:clout.mean.3.12.z | 1.09 | 0.343 | ||||||||||||||
| bias.sd.3.20.z:clout.mean.3.12.z | 1.03 | 0.814 | ||||||||||||||
| clout.mean.3.12.z:crt.z | 0.99 | 0.937 | ||||||||||||||
| clout.mean.3.12.z:ideology.z | 0.96 | 0.663 | ||||||||||||||
| clout.mean.3.12.z:white_.5 | 1.03 | 0.888 | ||||||||||||||
| clout.mean.3.12.z:age.z | 1.28 | 0.023 | ||||||||||||||
| clout.mean.3.12.z:education.z | 0.98 | 0.845 | ||||||||||||||
| posEmo.mean.3.12.z | 0.94 | 0.552 | ||||||||||||||
| bias.mean.3.20.z:posEmo.mean.3.12.z | 1.17 | 0.080 | ||||||||||||||
| bias.sd.3.20.z:posEmo.mean.3.12.z | 0.95 | 0.618 | ||||||||||||||
| posEmo.mean.3.12.z:crt.z | 1.01 | 0.896 | ||||||||||||||
| posEmo.mean.3.12.z:ideology.z | 0.90 | 0.191 | ||||||||||||||
| posEmo.mean.3.12.z:white_.5 | 1.08 | 0.667 | ||||||||||||||
| posEmo.mean.3.12.z:age.z | 1.28 | 0.010 | ||||||||||||||
| posEmo.mean.3.12.z:education.z | 0.93 | 0.407 | ||||||||||||||
| negEmo.mean.3.12.z | 0.93 | 0.455 | ||||||||||||||
| bias.mean.3.20.z:negEmo.mean.3.12.z | 1.09 | 0.389 | ||||||||||||||
| bias.sd.3.20.z:negEmo.mean.3.12.z | 1.10 | 0.413 | ||||||||||||||
| negEmo.mean.3.12.z:crt.z | 0.96 | 0.659 | ||||||||||||||
| negEmo.mean.3.12.z:ideology.z | 0.89 | 0.207 | ||||||||||||||
| negEmo.mean.3.12.z:white_.5 | 1.26 | 0.239 | ||||||||||||||
| negEmo.mean.3.12.z:age.z | 1.20 | 0.053 | ||||||||||||||
| negEmo.mean.3.12.z:education.z | 0.97 | 0.795 | ||||||||||||||
| threat.mean.3.12.z | 1.06 | 0.571 | ||||||||||||||
| bias.mean.3.20.z:threat.mean.3.12.z | 0.89 | 0.220 | ||||||||||||||
| bias.sd.3.20.z:threat.mean.3.12.z | 0.88 | 0.246 | ||||||||||||||
| threat.mean.3.12.z:crt.z | 1.07 | 0.433 | ||||||||||||||
| threat.mean.3.12.z:ideology.z | 1.02 | 0.834 | ||||||||||||||
| threat.mean.3.12.z:white_.5 | 0.97 | 0.872 | ||||||||||||||
| threat.mean.3.12.z:age.z | 0.76 | 0.003 | ||||||||||||||
| threat.mean.3.12.z:education.z | 0.99 | 0.884 | ||||||||||||||
| rel.mean.3.19.z | 1.50 | 0.036 | ||||||||||||||
| bias.mean.3.20.z:rel.mean.3.19.z | 1.03 | 0.711 | ||||||||||||||
| bias.sd.3.20.z:rel.mean.3.19.z | 1.38 | 0.164 | ||||||||||||||
| rel.mean.3.19.z:crt.z | 1.09 | 0.640 | ||||||||||||||
| rel.mean.3.19.z:ideology.z | 1.12 | 0.518 | ||||||||||||||
| rel.mean.3.19.z:white_.5 | 0.90 | 0.771 | ||||||||||||||
| rel.mean.3.19.z:age.z | 1.12 | 0.529 | ||||||||||||||
| rel.mean.3.19.z:education.z | 1.12 | 0.518 | ||||||||||||||
| Observations | 909 | 909 | 909 | 909 | 909 | 909 | 909 | 909 | ||||||||
| R2 Nagelkerke | 0.424 | 0.424 | 0.420 | 0.421 | 0.426 | 0.421 | 0.425 | 0.425 | ||||||||
2.7 7. US vs. UK Samples
cor.test(dUK$ideology.z, dUK$bias.sd.z)##
## Pearson's product-moment correlation
##
## data: dUK$ideology.z and dUK$bias.sd.z
## t = 0.67006, df = 1500, p-value = 0.5029
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.03331049 0.06781878
## sample estimates:
## cor
## 0.01729839cor.test(dUK$vaxxIntentions.z, dUK$bias.sd.z)##
## Pearson's product-moment correlation
##
## data: dUK$vaxxIntentions.z and dUK$bias.sd.z
## t = 2.0983, df = 1500, p-value = 0.03605
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.003527728 0.104391894
## sample estimates:
## cor
## 0.05409781cor.test(dUK$vaxxIntentions.z, dUK$bias.mean.z)##
## Pearson's product-moment correlation
##
## data: dUK$vaxxIntentions.z and dUK$bias.mean.z
## t = -4.7414, df = 1500, p-value = 2.324e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.17104469 -0.07137521
## sample estimates:
## cor
## -0.1215162mean(as.numeric(dUK$age), na.rm = T) #35.35## Warning in mean(as.numeric(dUK$age), na.rm = T): NAs introduced by coercion## [1] 35.35425sd(as.numeric(dUK$age), na.rm = T) #13.35## Warning in is.data.frame(x): NAs introduced by coercion## [1] 13.34589mean(as.numeric(dUS$age), na.rm = T) #48.23## [1] 48.22771sd(as.numeric(dUS$age), na.rm = T) #15.55## [1] 15.551552.8 8. Vaccine Intentions (Supplemental Table 4)
m1 <- lm(vaxxIntentions.z ~
(bias.mean.z * bias.sd.z * USvUK) +
(bias.mean.z + bias.sd.z + USvUK) *
(ideology.z + age.z + education.z), data = d2)
m1.us <- lm(vaxxIntentions.z ~
(bias.mean.z * bias.sd.z * US_0) +
(bias.mean.z + bias.sd.z + US_0) *
(ideology.z + age.z + education.z), data = d2)
m1.uk <- lm(vaxxIntentions.z ~
(bias.mean.z * bias.sd.z * UK_0) +
(bias.mean.z + bias.sd.z + UK_0) *
(ideology.z + age.z + education.z), data = d2)
tab_model(m1, m1.us, m1.uk,
dv.labels = c("Country (US = -.5, UK = .5)", "United States (US = 0, UK = 1)", "United Kingdom (US = 1, UK = 0)"),
title = "Outcome: Vaccine Intention",
pred.labels = c("Intercept",
"Conservative Media Consumption (CMC)",
"Variability in Media Consumption (VMC)",
"Country",
"Ideology",
"Age",
"Education",
"CMC x VMC",
"CMC x Country",
"VMC x Country",
"CMC x Ideology",
"CMC x Age",
"CMC x Education",
"VMC x Ideology",
"VMC x Age",
"VMC x Education",
"Country x Ideology",
"Country x Age",
"Country x Education",
"CMC x VMC x Country",
"US",
"CMC x US",
"VMC x US",
"US x Ideology",
"US x Age",
"US x Education",
"CMC x VMC x US",
"UK",
"CMC x UK",
"VMC x UK",
"UK x Ideology",
"UK x Age",
"UK x Education",
"CMC x VMC x UK"
),
string.est = "Est",
show.stat = T,
show.se = T,
show.ci = F,
string.se = "SE",
string.stat = "t",
digits = 2)| Country (US = -.5, UK = .5) | United States (US = 0, UK = 1) | United Kingdom (US = 1, UK = 0) | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Est | SE | t | p | Est | SE | t | p | Est | SE | t | p |
| Intercept | 0.02 | 0.02 | 1.06 | 0.291 | 0.03 | 0.02 | 1.44 | 0.151 | 0.01 | 0.03 | 0.24 | 0.807 |
| Conservative Media Consumption (CMC) | -0.16 | 0.03 | -6.00 | <0.001 | -0.21 | 0.03 | -7.33 | <0.001 | -0.11 | 0.04 | -2.45 | 0.014 |
| Variability in Media Consumption (VMC) | 0.06 | 0.02 | 3.14 | 0.002 | 0.04 | 0.02 | 1.96 | 0.050 | 0.07 | 0.03 | 2.49 | 0.013 |
| Country | -0.02 | 0.03 | -0.73 | 0.465 | ||||||||
| Ideology | -0.13 | 0.02 | -7.84 | <0.001 | -0.15 | 0.02 | -7.50 | <0.001 | -0.12 | 0.03 | -4.25 | <0.001 |
| Age | 0.10 | 0.02 | 6.16 | <0.001 | 0.17 | 0.02 | 9.72 | <0.001 | 0.02 | 0.03 | 0.75 | 0.454 |
| Education | 0.04 | 0.02 | 2.33 | 0.020 | 0.09 | 0.02 | 4.93 | <0.001 | -0.02 | 0.03 | -0.69 | 0.489 |
| CMC x VMC | 0.02 | 0.02 | 0.76 | 0.445 | 0.06 | 0.02 | 3.10 | 0.002 | -0.03 | 0.04 | -0.67 | 0.504 |
| CMC x Country | 0.10 | 0.05 | 1.89 | 0.059 | ||||||||
| VMC x Country | 0.03 | 0.04 | 0.78 | 0.437 | ||||||||
| CMC x Ideology | 0.01 | 0.01 | 0.69 | 0.489 | 0.01 | 0.01 | 0.69 | 0.489 | 0.01 | 0.01 | 0.69 | 0.489 |
| CMC x Age | 0.05 | 0.02 | 3.40 | 0.001 | 0.05 | 0.02 | 3.40 | 0.001 | 0.05 | 0.02 | 3.40 | 0.001 |
| CMC x Education | 0.01 | 0.01 | 0.87 | 0.386 | 0.01 | 0.01 | 0.87 | 0.386 | 0.01 | 0.01 | 0.87 | 0.386 |
| VMC x Ideology | 0.08 | 0.02 | 4.96 | <0.001 | 0.08 | 0.02 | 4.96 | <0.001 | 0.08 | 0.02 | 4.96 | <0.001 |
| VMC x Age | -0.00 | 0.02 | -0.20 | 0.839 | -0.00 | 0.02 | -0.20 | 0.839 | -0.00 | 0.02 | -0.20 | 0.839 |
| VMC x Education | -0.03 | 0.01 | -2.21 | 0.027 | -0.03 | 0.01 | -2.21 | 0.027 | -0.03 | 0.01 | -2.21 | 0.027 |
| Country x Ideology | 0.03 | 0.03 | 1.01 | 0.311 | ||||||||
| Country x Age | -0.16 | 0.03 | -4.98 | <0.001 | ||||||||
| Country x Education | -0.11 | 0.03 | -3.44 | 0.001 | ||||||||
| CMC x VMC x Country | -0.08 | 0.04 | -1.98 | 0.048 | ||||||||
| US | -0.02 | 0.03 | -0.73 | 0.465 | ||||||||
| CMC x US | 0.10 | 0.05 | 1.89 | 0.059 | ||||||||
| VMC x US | 0.03 | 0.04 | 0.78 | 0.437 | ||||||||
| US x Ideology | 0.03 | 0.03 | 1.01 | 0.311 | ||||||||
| US x Age | -0.16 | 0.03 | -4.98 | <0.001 | ||||||||
| US x Education | -0.11 | 0.03 | -3.44 | 0.001 | ||||||||
| CMC x VMC x US | -0.08 | 0.04 | -1.98 | 0.048 | ||||||||
| UK | 0.02 | 0.03 | 0.73 | 0.465 | ||||||||
| CMC x UK | -0.10 | 0.05 | -1.89 | 0.059 | ||||||||
| VMC x UK | -0.03 | 0.04 | -0.78 | 0.437 | ||||||||
| UK x Ideology | -0.03 | 0.03 | -1.01 | 0.311 | ||||||||
| UK x Age | 0.16 | 0.03 | 4.98 | <0.001 | ||||||||
| UK x Education | 0.11 | 0.03 | 3.44 | 0.001 | ||||||||
| CMC x VMC x UK | 0.08 | 0.04 | 1.98 | 0.048 | ||||||||
| Observations | 4460 | 4460 | 4460 | |||||||||
| R2 / R2 adjusted | 0.100 / 0.097 | 0.100 / 0.097 | 0.100 / 0.097 | |||||||||
round(etaSquared(m1),3)## eta.sq eta.sq.part
## bias.mean.z 0.012 0.013
## bias.sd.z 0.004 0.005
## USvUK 0.000 0.000
## ideology.z 0.014 0.016
## age.z 0.015 0.016
## education.z 0.002 0.002
## bias.mean.z:bias.sd.z 0.001 0.001
## bias.mean.z:USvUK 0.000 0.000
## bias.sd.z:USvUK 0.000 0.000
## bias.mean.z:ideology.z 0.000 0.000
## bias.mean.z:age.z 0.002 0.003
## bias.mean.z:education.z 0.000 0.000
## bias.sd.z:ideology.z 0.005 0.006
## bias.sd.z:age.z 0.000 0.000
## bias.sd.z:education.z 0.001 0.001
## USvUK:ideology.z 0.000 0.000
## USvUK:age.z 0.005 0.006
## USvUK:education.z 0.002 0.003
## bias.mean.z:bias.sd.z:USvUK 0.001 0.0012.9 9. Robust check - UK Corr Table
corr <- data.frame(dUK$vaxxIntentions)
colnames(corr)[colnames(corr) == "dUK.vaxxIntentions"] <- "vaxxIntent"
corr$analytic <- dUK$analytic.mean
corr$affect <- dUK$affect.mean
corr$threat <- dUK$threat.mean
corr$negEmo <- dUK$negEmo.mean
corr$posEmo <- dUK$posEmo.mean
corr$clout <- dUK$clout.mean
corr$reliab <- dUK$rel.mean
corr$bias.mean <- dUK$bias.mean
corr$bias.sd <- dUK$bias.sd
corr$exp.sum <- dUK$exp.sum
corr2 <- corr_coef(corr, use = "pairwise.complete.obs")## Warning: Missing values in the data. Option 'pairwise.complete.obs' used to
## compute correlation with all complete pairs of observations.plot(corr2)
2.10 10. Robust check - US Corr Table
corr <- data.frame(dUS$vaxxIntentions)
colnames(corr)[colnames(corr) == "dUS.vaxxIntentions"] <- "vaxxIntent"
corr$analytic <- dUS$analytic.mean
corr$affect <- dUS$affect.mean
corr$threat <- dUS$threat.mean
corr$negEmo <- dUS$negEmo.mean
corr$posEmo <- dUS$posEmo.mean
corr$clout <- dUS$clout.mean
corr$reliab <- dUS$rel.mean
corr$bias.mean <- dUS$bias.mean
corr$bias.sd <- dUS$bias.sd
corr$exp.sum <- dUS$exp.sum
corr2 <- corr_coef(corr, use = "pairwise.complete.obs")## Warning: Missing values in the data. Option 'pairwise.complete.obs' used to
## compute correlation with all complete pairs of observations.plot(corr2)
2.11 11. Robust check - Vaccine intentions
m.analytic <- lm(vaxxIntentions.z ~ (bias.mean.z * bias.sd.z) +
(bias.mean.z * analytic.mean.z) +
(analytic.mean.z * bias.sd.z) +
(bias.mean.z + bias.sd.z + analytic.mean.z) *
(UK_0 + ideology.z + age.z + education.z),
data = d2)
m.threat <- lm(vaxxIntentions.z ~ (bias.mean.z * bias.sd.z) +
(bias.mean.z * threat.mean.z) +
(threat.mean.z * bias.sd.z) +
(bias.mean.z + bias.sd.z + threat.mean.z) *
(UK_0 + ideology.z + age.z + education.z),
data = d2)
m.posEmo <- lm(vaxxIntentions.z ~ (bias.mean.z * bias.sd.z) +
(bias.mean.z * posEmo.mean.z) +
(posEmo.mean.z * bias.sd.z) +
(bias.mean.z + bias.sd.z + posEmo.mean.z) *
(UK_0 + ideology.z + age.z + education.z),
data = d2)
m.negEmo <- lm(vaxxIntentions.z ~ (bias.mean.z * bias.sd.z) +
(bias.mean.z * negEmo.mean.z) +
(negEmo.mean.z * bias.sd.z) +
(bias.mean.z + bias.sd.z + negEmo.mean.z) *
(UK_0 + ideology.z + age.z + education.z),
data = d2)
m.affect <- lm(vaxxIntentions.z ~ (bias.mean.z * bias.sd.z) +
(bias.mean.z * affect.mean.z) +
(affect.mean.z * bias.sd.z) +
(bias.mean.z + bias.sd.z + affect.mean.z) *
(UK_0 + ideology.z + age.z + education.z),
data = d2)
m.clout <- lm(vaxxIntentions.z ~ (bias.mean.z * bias.sd.z) +
(bias.mean.z * clout.mean.z) +
(clout.mean.z * bias.sd.z) +
(bias.mean.z + bias.sd.z + clout.mean.z) *
(UK_0 + ideology.z + age.z + education.z),
data = d2)
m.authentic <- lm(vaxxIntentions.z ~ (bias.mean.z * bias.sd.z) +
(bias.mean.z * authentic.mean.z) +
(authentic.mean.z * bias.sd.z) +
(bias.mean.z + bias.sd.z + authentic.mean.z) *
(UK_0 + ideology.z + age.z + education.z),
data = d2)
tab_model(m.affect, m.analytic, m.authentic, m.clout, m.posEmo, m.negEmo, m.threat,
dv.labels = c("affect",
"analytic",
"authentic",
"clout",
"positive emotion",
"negative emotion",
"threat",
"reliability"),
title = "Outcome: Vaccination Behavior",
string.est = "Est",
show.stat = F,
show.se = F,
show.ci = F,
string.stat = "t",
digits = 2)| affect | analytic | authentic | clout | positive emotion | negative emotion | threat | reliability | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Est | p | Est | p | Est | p | Est | p | Est | p | Est | p | Est | p |
| (Intercept) | -0.03 | 0.277 | -0.01 | 0.713 | -0.01 | 0.767 | -0.03 | 0.316 | -0.03 | 0.223 | -0.02 | 0.520 | -0.02 | 0.565 |
| bias mean z | 0.04 | 0.403 | -0.20 | <0.001 | -0.19 | <0.001 | -0.16 | <0.001 | -0.10 | 0.041 | -0.12 | <0.001 | -0.23 | <0.001 |
| bias sd z | -0.04 | 0.242 | 0.11 | <0.001 | 0.07 | 0.006 | 0.10 | <0.001 | 0.02 | 0.644 | 0.13 | <0.001 | 0.10 | 0.007 |
| affect mean z | -0.21 | <0.001 | ||||||||||||
| UK 0 | 0.06 | 0.087 | 0.03 | 0.348 | 0.04 | 0.287 | 0.05 | 0.166 | 0.06 | 0.108 | 0.04 | 0.265 | 0.05 | 0.170 |
| ideology z | -0.15 | <0.001 | -0.15 | <0.001 | -0.15 | <0.001 | -0.14 | <0.001 | -0.15 | <0.001 | -0.14 | <0.001 | -0.15 | <0.001 |
| age z | 0.12 | <0.001 | 0.13 | <0.001 | 0.12 | <0.001 | 0.12 | <0.001 | 0.13 | <0.001 | 0.12 | <0.001 | 0.13 | <0.001 |
| education z | 0.06 | <0.001 | 0.06 | <0.001 | 0.06 | <0.001 | 0.07 | <0.001 | 0.06 | <0.001 | 0.06 | <0.001 | 0.06 | <0.001 |
| bias mean z × bias sd z | 0.05 | 0.008 | 0.05 | 0.006 | 0.05 | 0.006 | 0.04 | 0.042 | 0.04 | 0.011 | 0.04 | 0.023 | 0.05 | 0.007 |
|
bias mean z × affect mean z |
0.01 | 0.474 | ||||||||||||
| bias sd z × affect mean z | -0.01 | 0.492 | ||||||||||||
| bias mean z × UK 0 | -0.23 | <0.001 | 0.02 | 0.607 | -0.00 | 0.923 | -0.03 | 0.344 | -0.09 | 0.060 | -0.07 | 0.040 | 0.04 | 0.522 |
| bias mean z × ideology z | 0.00 | 0.792 | -0.00 | 0.901 | 0.01 | 0.526 | 0.01 | 0.338 | 0.00 | 0.981 | 0.01 | 0.392 | 0.00 | 0.992 |
| bias mean z × age z | 0.04 | 0.008 | 0.04 | 0.017 | 0.05 | 0.002 | 0.05 | 0.002 | 0.04 | 0.007 | 0.05 | <0.001 | 0.05 | 0.001 |
| bias mean z × education z | 0.01 | 0.461 | 0.01 | 0.653 | 0.01 | 0.644 | 0.01 | 0.549 | 0.01 | 0.396 | 0.01 | 0.591 | 0.01 | 0.730 |
| bias sd z × UK 0 | 0.08 | 0.034 | -0.03 | 0.400 | -0.03 | 0.465 | -0.06 | 0.087 | 0.02 | 0.666 | -0.09 | 0.019 | -0.05 | 0.235 |
| bias sd z × ideology z | 0.07 | <0.001 | 0.07 | <0.001 | 0.07 | <0.001 | 0.08 | <0.001 | 0.07 | <0.001 | 0.07 | <0.001 | 0.07 | <0.001 |
| bias sd z × age z | -0.01 | 0.598 | -0.01 | 0.535 | -0.00 | 0.751 | -0.00 | 0.995 | -0.00 | 0.849 | -0.00 | 0.938 | 0.00 | 0.909 |
| bias sd z × education z | -0.03 | 0.026 | -0.03 | 0.021 | -0.03 | 0.027 | -0.03 | 0.020 | -0.03 | 0.017 | -0.03 | 0.050 | -0.03 | 0.032 |
| affect mean z × UK 0 | 0.25 | <0.001 | ||||||||||||
|
affect mean z × ideology z |
0.04 | 0.009 | ||||||||||||
| affect mean z × age z | -0.00 | 0.745 | ||||||||||||
|
affect mean z × education z |
-0.01 | 0.501 | ||||||||||||
| analytic mean z | -0.17 | <0.001 | ||||||||||||
|
bias mean z × analytic mean z |
0.03 | 0.100 | ||||||||||||
|
bias sd z × analytic mean z |
-0.00 | 0.948 | ||||||||||||
| analytic mean z × UK 0 | 0.21 | <0.001 | ||||||||||||
|
analytic mean z × ideology z |
-0.05 | 0.001 | ||||||||||||
| analytic mean z × age z | -0.03 | 0.027 | ||||||||||||
|
analytic mean z × education z |
0.00 | 0.846 | ||||||||||||
| authentic mean z | 0.17 | <0.001 | ||||||||||||
|
bias mean z × authentic mean z |
-0.02 | 0.308 | ||||||||||||
|
bias sd z × authentic mean z |
-0.00 | 0.922 | ||||||||||||
| authentic mean z × UK 0 | -0.17 | <0.001 | ||||||||||||
|
authentic mean z × ideology z |
0.01 | 0.663 | ||||||||||||
| authentic mean z × age z | 0.00 | 0.803 | ||||||||||||
|
authentic mean z × education z |
0.00 | 0.973 | ||||||||||||
| clout mean z | 0.15 | <0.001 | ||||||||||||
|
bias mean z × clout mean z |
-0.01 | 0.561 | ||||||||||||
| bias sd z × clout mean z | -0.03 | 0.030 | ||||||||||||
| clout mean z × UK 0 | -0.11 | 0.001 | ||||||||||||
| clout mean z × ideology z | 0.06 | <0.001 | ||||||||||||
| clout mean z × age z | 0.03 | 0.084 | ||||||||||||
|
clout mean z × education z |
-0.01 | 0.562 | ||||||||||||
| posEmo mean z | -0.03 | 0.577 | ||||||||||||
|
bias mean z × posEmo mean z |
0.01 | 0.748 | ||||||||||||
| bias sd z × posEmo mean z | -0.02 | 0.205 | ||||||||||||
| posEmo mean z × UK 0 | 0.06 | 0.297 | ||||||||||||
|
posEmo mean z × ideology z |
0.06 | <0.001 | ||||||||||||
| posEmo mean z × age z | 0.01 | 0.488 | ||||||||||||
|
posEmo mean z × education z |
-0.02 | 0.285 | ||||||||||||
| negEmo mean z | -0.19 | <0.001 | ||||||||||||
|
bias mean z × negEmo mean z |
0.01 | 0.513 | ||||||||||||
| bias sd z × negEmo mean z | 0.01 | 0.618 | ||||||||||||
| negEmo mean z × UK 0 | 0.23 | <0.001 | ||||||||||||
|
negEmo mean z × ideology z |
0.01 | 0.624 | ||||||||||||
| negEmo mean z × age z | -0.00 | 0.815 | ||||||||||||
|
negEmo mean z × education z |
-0.00 | 0.781 | ||||||||||||
| threat mean z | -0.12 | 0.024 | ||||||||||||
|
bias mean z × threat mean z |
0.00 | 0.770 | ||||||||||||
| bias sd z × threat mean z | 0.02 | 0.242 | ||||||||||||
| threat mean z × UK 0 | 0.11 | 0.049 | ||||||||||||
|
threat mean z × ideology z |
-0.03 | 0.090 | ||||||||||||
| threat mean z × age z | -0.01 | 0.739 | ||||||||||||
|
threat mean z × education z |
0.00 | 0.781 | ||||||||||||
| Observations | 4460 | 4460 | 4460 | 4460 | 4460 | 4460 | 4460 | |||||||
| R2 / R2 adjusted | 0.099 / 0.095 | 0.103 / 0.099 | 0.100 / 0.096 | 0.103 / 0.098 | 0.096 / 0.092 | 0.100 / 0.096 | 0.093 / 0.089 | |||||||
2.12 12. measures
# vaccine intentions
mean(dUS$vaxxIntentions, na.rm = T); sd(dUS$vaxxIntentions, na.rm = T)## [1] 0.5844539## [1] 2.156637mean(dUK$vaxxIntentions, na.rm = T); sd(dUK$vaxxIntentions, na.rm = T)## [1] 1.368842## [1] 1.812618cor.test(af$bias.af, af$bias.as)##
## Pearson's product-moment correlation
##
## data: af$bias.af and af$bias.as
## t = 11.454, df = 21, p-value = 1.711e-10
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.8363048 0.9695822
## sample estimates:
## cor
## 0.9284467# conservative media consumption
mean(d$bias.mean.1.15, na.rm = T); sd(d$bias.mean.1.15, na.rm = T)## [1] -0.4205296## [1] 0.531026mean(d$bias.mean.2.15, na.rm = T); sd(d$bias.mean.2.15, na.rm = T)## [1] -0.4084528## [1] 0.526748mean(d$bias.mean.3.20, na.rm = T); sd(d$bias.mean.3.20, na.rm = T)## [1] -0.2308115## [1] 0.4403217mean(dUK$bias.mean, na.rm = T); sd(dUK$bias.mean, na.rm = T)## [1] -0.01259991## [1] 0.3303387# ideological variety of media consumption
mean(d$bias.sd.1.15, na.rm = T); sd(d$bias.sd.1.15, na.rm = T)## [1] 1.094834## [1] 0.6386927mean(d$bias.sd.2.15, na.rm = T); sd(d$bias.sd.2.15, na.rm = T)## [1] 1.053586## [1] 0.6232238mean(d$bias.sd.3.20, na.rm = T); sd(d$bias.sd.3.20, na.rm = T)## [1] 1.415245## [1] 1.155824mean(dUK$bias.mean, na.rm = T); sd(dUK$bias.sd, na.rm = T)## [1] -0.01259991## [1] 0.7730456