library(anesr)
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.2 v purrr 0.3.4
## v tibble 3.0.3 v dplyr 1.0.2
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.5.0
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(coefplot)
## Warning: package 'coefplot' was built under R version 4.0.3
data("timeseries_2016")
anes16 <- timeseries_2016
clean <- function(x){ifelse (x < 0, NA, x)}
anes_clean <- anes16 %>%
mutate(across (everything(), clean))
anes_clean <- anes_clean %>%
mutate(V161158x = V161158x - 1 )
mod1 <- lm(V161087 ~ V161158x, data = anes_clean)
summary(mod1)
##
## Call:
## lm(formula = V161087 ~ V161158x, data = anes_clean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -70.64 -16.91 -4.17 14.36 93.83
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.1700 0.6715 9.189 <2e-16 ***
## V161158x 10.7454 0.1874 57.337 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 26.19 on 4209 degrees of freedom
## (59 observations deleted due to missingness)
## Multiple R-squared: 0.4385, Adjusted R-squared: 0.4384
## F-statistic: 3288 on 1 and 4209 DF, p-value: < 2.2e-16
anes_clean <- anes_clean %>%
mutate(gen = case_when (V161342 == 2 ~ 0 ,
V161342 == 1 ~ 1 ,
V161342 == 3 ~ 0
))
mod1 <- lm(V161087 ~ gen, data = anes_clean)
summary(mod1)
##
## Call:
## lm(formula = V161087 ~ gen, data = anes_clean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -40.743 -33.751 -3.751 29.257 66.249
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 33.7509 0.7378 45.744 < 2e-16 ***
## gen 6.9920 1.0763 6.496 9.2e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 34.76 on 4186 degrees of freedom
## (82 observations deleted due to missingness)
## Multiple R-squared: 0.009981, Adjusted R-squared: 0.009744
## F-statistic: 42.2 on 1 and 4186 DF, p-value: 9.198e-11
anes_clean <- anes_clean %>%
mutate(V161081 = V161081 - 1)
mod2 <- lm(V161087 ~ V161081, data = anes_clean)
summary(mod2)
##
## Call:
## lm(formula = V161087 ~ V161081, data = anes_clean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -44.922 -29.922 -4.922 25.078 85.631
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 14.3690 0.9846 14.59 <2e-16 ***
## V161081 30.5535 1.1418 26.76 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 32.3 on 4194 degrees of freedom
## (74 observations deleted due to missingness)
## Multiple R-squared: 0.1458, Adjusted R-squared: 0.1456
## F-statistic: 716 on 1 and 4194 DF, p-value: < 2.2e-16
anes_clean <- anes_clean %>%
mutate(V161361x = V161361x - 1)
mod3 <- lm(V161087 ~ V161361x , data = anes_clean)
summary(mod3)
##
## Call:
## lm(formula = V161087 ~ V161361x, data = anes_clean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -37.440 -36.696 -6.729 32.884 63.433
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 37.43974 1.12754 33.205 <2e-16 ***
## V161361x -0.03233 0.06815 -0.474 0.635
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 34.87 on 4028 degrees of freedom
## (240 observations deleted due to missingness)
## Multiple R-squared: 5.585e-05, Adjusted R-squared: -0.0001924
## F-statistic: 0.225 on 1 and 4028 DF, p-value: 0.6353
mod1 <- lm(V161087 ~ V161158x, data = anes_clean)
mod2 <- lm(V161087 ~ V161081, data = anes_clean)
mod3 <- lm(V161087 ~ V161361x , data = anes_clean)
mod4 <- lm(V161087 ~ V161158x + gen + V161081 + V161361x , data = anes_clean)
summary(mod4)
##
## Call:
## lm(formula = V161087 ~ V161158x + gen + V161081 + V161361x, data = anes_clean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -75.451 -16.112 -0.608 16.754 92.790
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.87354 1.15632 3.350 0.000816 ***
## V161158x 9.93979 0.20945 47.456 < 2e-16 ***
## gen 3.33612 0.82445 4.046 5.30e-05 ***
## V161081 10.09316 1.02682 9.830 < 2e-16 ***
## V161361x -0.29819 0.05134 -5.808 6.81e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 25.65 on 3971 degrees of freedom
## (294 observations deleted due to missingness)
## Multiple R-squared: 0.461, Adjusted R-squared: 0.4605
## F-statistic: 849.1 on 4 and 3971 DF, p-value: < 2.2e-16
coefplot::coefplot(mod4)
Written questions
1 1 The coefficent for party ID 2 Value is statistically signifigant using the 5% threshhold 3 Linea regression is appropriate
2 1 Men as opposed to those who donโt identify as male is 6,992 point increase in support for Donal Trump on a 100 point scale
3 1 Those who think the country is on the wrong track tend to be 40 points higher on the feelings thermometer compared to those who think the country is on the right track
4 1 Income does not have a statistically signifigant effect when analyzing the estimated slope. Every point on the income scale leads to a .03233 points lower on the feelings scale for Donald Trump
5 1 2 Gender is not signifigant at the 5% threshhold