CBZS: ANES Data
Select variables of interest
V241221 (party id); V241177 (ideology); V241551 (gender); V241501x (race); V242337 (social class); V241465x (education); V241566x (household income); V241458x (age); V242305 (Because of the rich and powerful, it becomes difficult for the rest of us to get ahead); V242350 (minimum wage increase); V242316b (tax on millionaires); V242253x (government should reduce income inequality).
df_anes <- df_anes_raw %>%
rename(party_id = V241221,
ideo = V241177,
gender = V241551,
race = V241501x,
class = V242337,
edu = V241465x,
income = V241566x,
age = V241458x,
class_zs = V242305,
minwage = V242350,
taxrich = V242316b,
reduceineq = V242253x) %>%
select(party_id,
ideo,
gender,
race,
class,
edu,
income,
age,
class_zs,
minwage,
reduceineq)clean data
df_anes <- df_anes %>%
mutate(party_id = case_when(party_id == 1 ~ "dem",
party_id == 2 ~ "rep",
party_id == 3 ~ "ind",
party_id == 5 ~ "other",
.default = NA),
ideo = case_when(ideo < 0 ~ NA,
ideo == 99 ~ NA,
.default = as.numeric(ideo)),
gender = case_when(gender == 1 ~ "man",
gender == 2 ~ "woman",
gender == 3 ~ "nonbinary",
gender == 4 ~ "other",
.default = NA),
race = case_when(race == 1 ~ "white,non-hisp",
race == 2 ~ "black,non-hisp",
race == 3 ~ "hisp",
race == 4 ~ "asian,non-hisp",
race == 5 ~ "native,non-hisp",
race == 6 ~ "multiracial,non-hisp",
.default = NA),
class = case_when(class == 1 ~ "lower",
class == 2 ~ "working",
class == 3 ~ "middle",
class == 4 ~ "upper",
.default = NA),
edu = case_when(edu < 0 ~ NA,
.default = as.numeric(edu)),
income = case_when(income < 0 ~ NA,
.default = as.numeric(income)),
age = case_when(age < 0 ~ NA,
.default = as.numeric(age)),
class_zs = case_when(class_zs < 0 ~ NA,
.default = as.numeric(class_zs)),
minwage = case_when(minwage < 0 ~ NA,
.default = as.numeric(minwage)),
reduceineq = case_when(reduceineq < 0 ~ NA,
.default = as.numeric(reduceineq))) %>%
mutate(minwage_R = 5 - minwage,
reduceineq_R = 8 - reduceineq,
class_num = as.numeric(factor(class,levels = c("lower",
"working",
"middle",
"upper"))))Ok, because the social class variable doesn’t really let us see if people self-identify as working class independently (it’s part of the SES scale), we’re gonna try to separate them out by looking at an objective measure: education. Anyone with a college degree who identifies as working class will be a 1. Those with a college degree who do not identify as working class will be a 0. Anyone without a college degree will be NA (note: this is just for a very specific analysis that I’ll try later).
df_anes <- df_anes %>%
mutate(wrkclassidentity = ifelse(edu > 3 & class == "working",1,
ifelse(edu > 3 & class != "working",0,NA)))Descriptives
Alright, let’s take a look at our sample.
Race
df_anes %>%
group_by(race) %>%
summarise(N = n()) %>%
ungroup() %>%
mutate(Perc = round(100*(N/sum(N)),2)) %>%
ungroup() %>%
arrange(desc(N)) %>%
kbl() %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| race | N | Perc |
|---|---|---|
| white,non-hisp | 3946 | 71.47 |
| hisp | 582 | 10.54 |
| black,non-hisp | 508 | 9.20 |
| asian,non-hisp | 197 | 3.57 |
| multiracial,non-hisp | 188 | 3.41 |
| NA | 67 | 1.21 |
| native,non-hisp | 33 | 0.60 |
Gender
df_anes %>%
group_by(gender) %>%
summarise(N = n()) %>%
ungroup() %>%
mutate(Perc = round(100*(N/sum(N)),2)) %>%
ungroup() %>%
arrange(desc(N)) %>%
kbl() %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| gender | N | Perc |
|---|---|---|
| woman | 2773 | 50.23 |
| man | 2397 | 43.42 |
| NA | 287 | 5.20 |
| nonbinary | 46 | 0.83 |
| other | 18 | 0.33 |
Education
- Less than high-school
- High school
- Some post high-school
- Bachelor’s degree
- Graduate degree
df_anes %>%
group_by(edu) %>%
summarise(N = n()) %>%
ungroup() %>%
mutate(Perc = round(100*(N/sum(N)),2)) %>%
ungroup() %>%
arrange(edu) %>%
kbl() %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| edu | N | Perc |
|---|---|---|
| 1 | 282 | 5.11 |
| 2 | 971 | 17.59 |
| 3 | 1726 | 31.26 |
| 4 | 1374 | 24.89 |
| 5 | 1081 | 19.58 |
| NA | 87 | 1.58 |
Income
1 = Under 5000 to 28 = Over 250,000
df_anes %>%
ggplot(aes(x = income)) +
geom_histogram(fill = "lightblue",
color = NA,
binwidth = 1) +
scale_x_continuous(breaks = seq(1,28,3),
limits = c(0,29)) +
geom_vline(xintercept = median(df_anes$income,na.rm = T),
color = "grey15",
size = 1,
linetype = "dashed") +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
axis.line = element_line(color = "grey66"),
axis.text.y = element_text(color = "black"),
axis.text.x = element_text(color = "black",
face = "bold"),
axis.title.x = element_text(color = "black",
face = "bold"))
Class
df_anes %>%
group_by(class) %>%
summarise(N = n()) %>%
ungroup() %>%
mutate(Perc = round(100*(N/sum(N)),2)) %>%
ungroup() %>%
kbl() %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| class | N | Perc |
|---|---|---|
| lower | 418 | 7.57 |
| middle | 2520 | 45.64 |
| upper | 263 | 4.76 |
| working | 1707 | 30.92 |
| NA | 613 | 11.10 |
Class and education
I just want to square them to see how many people identify as working class even when they have a bachelor’s degree
df_anes %>%
group_by(edu,class) %>%
summarise(N = n()) %>%
ungroup() %>%
kbl() %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")## `summarise()` has grouped output by 'edu'. You can override using the `.groups`
## argument.| edu | class | N |
|---|---|---|
| 1 | lower | 45 |
| 1 | middle | 70 |
| 1 | upper | 6 |
| 1 | working | 104 |
| 1 | NA | 57 |
| 2 | lower | 153 |
| 2 | middle | 270 |
| 2 | upper | 18 |
| 2 | working | 398 |
| 2 | NA | 132 |
| 3 | lower | 155 |
| 3 | middle | 646 |
| 3 | upper | 26 |
| 3 | working | 695 |
| 3 | NA | 204 |
| 4 | lower | 43 |
| 4 | middle | 790 |
| 4 | upper | 81 |
| 4 | working | 339 |
| 4 | NA | 121 |
| 5 | lower | 13 |
| 5 | middle | 709 |
| 5 | upper | 131 |
| 5 | working | 148 |
| 5 | NA | 80 |
| NA | lower | 9 |
| NA | middle | 35 |
| NA | upper | 1 |
| NA | working | 23 |
| NA | NA | 19 |
Age
Note that they just assigned 80 to anyone over 80, so it looks skewed.
df_anes %>%
ggplot(aes(x = age)) +
geom_histogram(fill = "lightblue",
color = NA,
binwidth = 1) +
# scale_x_continuous(breaks = seq(1,28,3),
# limits = c(0,29)) +
geom_vline(xintercept = mean(df_anes$age,na.rm = T),
color = "grey15",
size = 1,
linetype = "dashed") +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
axis.line = element_line(color = "grey66"),
axis.text.y = element_text(color = "black"),
axis.text.x = element_text(color = "black",
face = "bold"),
axis.title.x = element_text(color = "black",
face = "bold"))
Party ID
df_anes %>%
group_by(party_id) %>%
summarise(N = n()) %>%
ungroup() %>%
mutate(Perc = round(100*(N/sum(N)),2)) %>%
ungroup() %>%
arrange(desc(N)) %>%
kbl() %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| party_id | N | Perc |
|---|---|---|
| dem | 1865 | 33.78 |
| rep | 1652 | 29.92 |
| ind | 1553 | 28.13 |
| NA | 298 | 5.40 |
| other | 153 | 2.77 |
Political ideology
1 = Extremely Liberal to 7 = Extremely Conservative
df_anes %>%
ggplot(aes(x = ideo)) +
geom_histogram(fill = "lightblue",
color = NA,
binwidth = 1) +
scale_x_continuous(breaks = seq(1,7,1),
limits = c(0,8)) +
geom_vline(xintercept = mean(df_anes$ideo,na.rm = T),
color = "grey15",
size = 1,
linetype = "dashed") +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
axis.line = element_line(color = "grey66"),
axis.text.y = element_text(color = "black"),
axis.text.x = element_text(color = "black",
face = "bold"),
axis.title.x = element_text(color = "black",
face = "bold"))
Class Zero-Sum
How well does the following statement describe your view? (1 =
Not at all well to 5 = Extremely well)
Because of the rich and powerful, it becomes difficult for the rest
of us to get ahead.
df_anes %>%
ggplot(aes(x = class_zs)) +
geom_histogram(fill = "lightblue",
color = NA,
binwidth = 1) +
scale_x_continuous(breaks = seq(1,5,1),
limits = c(0,6)) +
geom_vline(xintercept = mean(df_anes$class_zs,na.rm = T),
color = "grey15",
size = 1,
linetype = "dashed") +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
axis.line = element_line(color = "grey66"),
axis.text.y = element_text(color = "black"),
axis.text.x = element_text(color = "black",
face = "bold"),
axis.title.x = element_text(color = "black",
face = "bold"))
Minimum wage increase
Should the federal minimum wage be [raised (4), kept the same (3),lowered but not eliminated (2), or eliminated altogether (1)]?
df_anes %>%
ggplot(aes(x = minwage_R)) +
geom_histogram(fill = "lightblue",
color = NA,
binwidth = 1) +
scale_x_continuous(breaks = seq(1,4,1),
limits = c(0,5)) +
geom_vline(xintercept = mean(df_anes$minwage_R,na.rm = T),
color = "grey15",
size = 1,
linetype = "dashed") +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
axis.line = element_line(color = "grey66"),
axis.text.y = element_text(color = "black"),
axis.text.x = element_text(color = "black",
face = "bold"),
axis.title.x = element_text(color = "black",
face = "bold"))
Reduce inequality
Do you favor or oppose, or neither favor nor oppose the government trying to reduce the difference in incomes between the richest and poorest households? (1 = Oppose a great deal to 7 = Favor a great deal)
df_anes %>%
ggplot(aes(x = reduceineq_R)) +
geom_histogram(fill = "lightblue",
color = NA,
binwidth = 1) +
scale_x_continuous(breaks = seq(1,7,1),
limits = c(0,8)) +
geom_vline(xintercept = mean(df_anes$reduceineq_R,na.rm = T),
color = "grey15",
size = 1,
linetype = "dashed") +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.ticks = element_blank(),
axis.line = element_line(color = "grey66"),
axis.text.y = element_text(color = "black"),
axis.text.x = element_text(color = "black",
face = "bold"),
axis.title.x = element_text(color = "black",
face = "bold"))
Analysis
Correlation matrix
df_anes %>%
select(class_zs,minwage_R,reduceineq_R,ideo,income,edu,age) %>%
corPlot(upper = TRUE,stars = TRUE,xsrt = 270)
The “reducing inequality” item looks very weird. Feels like they made a coding error, or the codebook is wrong. I think it’s the opposite of what they’re saying. Hmm. The rest makes sense.
Linear models
Linear model 1A
Outcome: Minimum wage support; predictor: class zero-sum.
m1 <- lm(minwage_R ~ class_zs,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 2.81 | [2.74, 2.88] | 82.54 | 4854 | < .001 |
| Class zs | 0.19 | [0.17, 0.21] | 19.15 | 4854 | < .001 |
Linear model 1B
Outcome: Minimum wage support;
Predictor: class zero-sum;
Controls: Party ID and political ideology
m1 <- lm(minwage_R ~ class_zs + party_id + ideo,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 3.79 | [3.68, 3.90] | 66.20 | 4045 | < .001 |
| Class zs | 0.10 | [0.08, 0.12] | 8.91 | 4045 | < .001 |
| Party idind | -0.14 | [-0.20, -0.07] | -4.21 | 4045 | < .001 |
| Party idother | -0.47 | [-0.63, -0.31] | -5.67 | 4045 | < .001 |
| Party idrep | -0.29 | [-0.37, -0.21] | -7.04 | 4045 | < .001 |
| Ideo | -0.13 | [-0.15, -0.11] | -13.26 | 4045 | < .001 |
Linear model 1C
Outcome: Minimum wage support;
Predictor: class zero-sum;
Controls: Party ID, political ideology, race, gender, income, education,
and age
m1 <- lm(minwage_R ~ class_zs + party_id + ideo + race + gender + income + edu + age,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 3.76 | [3.53, 3.99] | 32.00 | 3676 | < .001 |
| Class zs | 0.10 | [0.08, 0.12] | 8.47 | 3676 | < .001 |
| Party idind | -0.10 | [-0.17, -0.03] | -2.90 | 3676 | .004 |
| Party idother | -0.45 | [-0.62, -0.27] | -5.09 | 3676 | < .001 |
| Party idrep | -0.27 | [-0.36, -0.19] | -6.34 | 3676 | < .001 |
| Ideo | -0.13 | [-0.16, -0.11] | -12.51 | 3676 | < .001 |
| Raceblack,non-hisp | 0.07 | [-0.10, 0.23] | 0.81 | 3676 | .415 |
| Racehisp | 0.10 | [-0.05, 0.26] | 1.30 | 3676 | .192 |
| Racemultiracial,non-hisp | 0.07 | [-0.12, 0.26] | 0.74 | 3676 | .459 |
| Racenative,non-hisp | 0.12 | [-0.28, 0.51] | 0.58 | 3676 | .562 |
| Racewhite,non-hisp | 0.00 | [-0.14, 0.13] | -0.03 | 3676 | .973 |
| Gendernonbinary | 0.13 | [-0.13, 0.38] | 0.97 | 3676 | .331 |
| Genderother | 0.05 | [-0.48, 0.58] | 0.19 | 3676 | .849 |
| Genderwoman | 0.14 | [0.09, 0.19] | 5.41 | 3676 | < .001 |
| Income | 0.00 | [-0.01, 0.00] | -1.21 | 3676 | .228 |
| Edu | -0.02 | [-0.05, 0.00] | -1.87 | 3676 | .061 |
| Age | 0.00 | [0.00, 0.00] | 1.39 | 3676 | .165 |
Linear model 1D
Outcome: Minimum wage support;
Predictor: class zero-sum;
Controls: Party ID, political ideology, race, gender, income, education,
age, and class
m1 <- lm(minwage_R ~ class_zs + party_id + ideo + race + gender + income + edu + age + class,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 3.76 | [3.52, 4.00] | 30.31 | 3670 | < .001 |
| Class zs | 0.10 | [0.08, 0.12] | 8.34 | 3670 | < .001 |
| Party idind | -0.10 | [-0.17, -0.03] | -2.97 | 3670 | .003 |
| Party idother | -0.45 | [-0.62, -0.28] | -5.10 | 3670 | < .001 |
| Party idrep | -0.27 | [-0.36, -0.19] | -6.35 | 3670 | < .001 |
| Ideo | -0.13 | [-0.15, -0.11] | -12.44 | 3670 | < .001 |
| Raceblack,non-hisp | 0.07 | [-0.10, 0.23] | 0.81 | 3670 | .421 |
| Racehisp | 0.11 | [-0.05, 0.26] | 1.33 | 3670 | .185 |
| Racemultiracial,non-hisp | 0.07 | [-0.12, 0.26] | 0.73 | 3670 | .464 |
| Racenative,non-hisp | 0.11 | [-0.29, 0.50] | 0.54 | 3670 | .589 |
| Racewhite,non-hisp | 0.00 | [-0.14, 0.14] | 0.02 | 3670 | .986 |
| Gendernonbinary | 0.12 | [-0.13, 0.37] | 0.92 | 3670 | .356 |
| Genderother | 0.04 | [-0.48, 0.57] | 0.16 | 3670 | .871 |
| Genderwoman | 0.14 | [0.09, 0.19] | 5.39 | 3670 | < .001 |
| Income | 0.00 | [0.00, 0.00] | -0.67 | 3670 | .501 |
| Edu | -0.02 | [-0.05, 0.01] | -1.42 | 3670 | .154 |
| Age | 0.00 | [0.00, 0.00] | 1.67 | 3670 | .095 |
| Classmiddle | -0.08 | [-0.19, 0.04] | -1.34 | 3670 | .180 |
| Classupper | 0.00 | [-0.15, 0.15] | 0.03 | 3670 | .979 |
| Classworking | -0.02 | [-0.13, 0.08] | -0.43 | 3670 | .667 |
Linear model 2
Ok, let’s take only those who have a bachelor’s degree or more (that’s what’s often used a separator of working class from middle class). And for them, we’ll see if they identify as working class.
Outcome: Minimum wage support;
Predictor: identifying as working class
Subsample: Only those with bachelor’s degree or more
m1 <- lm(minwage_R ~ wrkclassidentity,data = df_anes %>% filter(!is.na(wrkclassidentity)))
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 3.42 | [3.38, 3.46] | 165.82 | 2237 | < .001 |
| Wrkclassidentity | 0.04 | [-0.05, 0.12] | 0.85 | 2237 | .394 |
hmm, they’re not more likely to support minimum wage increase. Ok.
Linear model 3A
Let’s just see if class is predictive of minimum wage support at all.
Here, we’ll treat class a numeric variable (1 = lower; 2 = working; 3 =
middle; 4 = upper).
Outcome: Minimum wage support;
Predictor: class
m1 <- lm(minwage_R ~ class_num,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 3.60 | [3.51, 3.68] | 81.03 | 4871 | < .001 |
| Class num | -0.07 | [-0.10, -0.04] | -4.11 | 4871 | < .001 |
Linear model 3B
Outcome: Minimum wage support;
Predictor: class;
Controls: Education and income
m1 <- lm(minwage_R ~ class_num + edu + income,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 3.55 | [3.45, 3.66] | 68.70 | 4377 | < .001 |
| Class num | -0.07 | [-0.11, -0.03] | -3.60 | 4377 | < .001 |
| Edu | 0.04 | [0.02, 0.07] | 3.16 | 4377 | .002 |
| Income | 0.00 | [-0.01, 0.00] | -2.43 | 4377 | .015 |
Linear model 3C
Outcome: Minimum wage support;
Predictor: class;
Controls: Education, income, race, gender, age
m1 <- lm(minwage_R ~ class_num + edu + income + race + gender + age,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 3.34 | [3.15, 3.54] | 34.22 | 4240 | < .001 |
| Class num | -0.05 | [-0.09, -0.01] | -2.39 | 4240 | .017 |
| Edu | 0.04 | [0.01, 0.06] | 2.92 | 4240 | .003 |
| Income | 0.00 | [0.00, 0.00] | -0.57 | 4240 | .571 |
| Raceblack,non-hisp | 0.26 | [0.10, 0.42] | 3.21 | 4240 | .001 |
| Racehisp | 0.15 | [-0.01, 0.31] | 1.86 | 4240 | .063 |
| Racemultiracial,non-hisp | 0.07 | [-0.12, 0.26] | 0.76 | 4240 | .448 |
| Racenative,non-hisp | 0.15 | [-0.20, 0.50] | 0.83 | 4240 | .409 |
| Racewhite,non-hisp | -0.02 | [-0.16, 0.12] | -0.30 | 4240 | .762 |
| Gendernonbinary | 0.43 | [0.17, 0.68] | 3.23 | 4240 | .001 |
| Genderother | 0.26 | [-0.18, 0.69] | 1.15 | 4240 | .251 |
| Genderwoman | 0.23 | [0.18, 0.28] | 8.90 | 4240 | < .001 |
| Age | 0.00 | [0.00, 0.00] | -1.11 | 4240 | .267 |
Linear model 3D
Outcome: Minimum wage support;
Predictor: class;
Controls: Education, income, race, gender, age, party ID, and political
ideology
m1 <- lm(minwage_R ~ class_num + edu + income + race + gender + age + party_id + ideo,data = df_anes)
apa_lm <- apa_print(m1)
kbl(apa_lm$table) %>%
kable_styling(bootstrap_options = "hover",
full_width = F,
position = "left")| term | estimate | conf.int | statistic | df | p.value |
|---|---|---|---|---|---|
| Intercept | 4.31 | [4.10, 4.52] | 40.57 | 3678 | < .001 |
| Class num | -0.04 | [-0.08, 0.00] | -2.05 | 3678 | .041 |
| Edu | -0.02 | [-0.05, 0.00] | -1.61 | 3678 | .107 |
| Income | 0.00 | [-0.01, 0.00] | -0.97 | 3678 | .331 |
| Raceblack,non-hisp | 0.07 | [-0.09, 0.24] | 0.86 | 3678 | .392 |
| Racehisp | 0.10 | [-0.05, 0.26] | 1.30 | 3678 | .193 |
| Racemultiracial,non-hisp | 0.08 | [-0.11, 0.27] | 0.80 | 3678 | .424 |
| Racenative,non-hisp | 0.16 | [-0.23, 0.54] | 0.79 | 3678 | .430 |
| Racewhite,non-hisp | 0.01 | [-0.13, 0.14] | 0.08 | 3678 | .934 |
| Gendernonbinary | 0.12 | [-0.14, 0.37] | 0.89 | 3678 | .371 |
| Genderother | 0.07 | [-0.46, 0.60] | 0.27 | 3678 | .790 |
| Genderwoman | 0.14 | [0.09, 0.19] | 5.43 | 3678 | < .001 |
| Age | 0.00 | [0.00, 0.00] | 0.24 | 3678 | .808 |
| Party idind | -0.12 | [-0.19, -0.05] | -3.47 | 3678 | < .001 |
| Party idother | -0.47 | [-0.65, -0.30] | -5.37 | 3678 | < .001 |
| Party idrep | -0.32 | [-0.40, -0.23] | -7.34 | 3678 | < .001 |
| Ideo | -0.15 | [-0.17, -0.13] | -14.48 | 3678 | < .001 |
Mediation
Mediation model 1
Predictor: Class Zero-Sum
Mediator: Class
Outcome: Minimum wage support
m1 <- psych::mediate(minwage_R ~ class_zs + (class_num),data = df_anes,std = T,n.iter = 10000)
beta coefficients are standardized
a = -0.14 (p = 0)
b = -0.02 (p = 0.083)
c = 0.26 (p = 0)
c’= 0.26 (p = 0)
Mediation model 2
Predictor: Class
Mediator: Class Zero-Sum
Outcome: Minimum wage support
m1 <- psych::mediate(minwage_R ~ class_num + (class_zs),data = df_anes,std = T,n.iter = 10000)
a = -0.14 (p = 0)
b = 0.26 (p = 0)
c = -0.06 (p = 0)
c’= -0.02 (p = 0.083)