Starting salaries between 1965 and 1975

knitr::opts_chunk$set(warning=FALSE,
                   message=FALSE)

library(tidyverse)
library(knitr)
library(broom)
library(Sleuth3)

wages <- case1202 %>% 
  mutate(Female = ifelse(Sex=="Female",1,0)) %>%
  select(-Sal77,-Sex)

Initial model

model <- lm(Bsal ~ Senior + Age + Educ + Exper + Female, 
            data=wages)
tidy(model,conf.int=TRUE)

## # A tibble: 6 x 7
##   term         estimate std.error statistic  p.value  conf.low conf.high
##   <chr>           <dbl>     <dbl>     <dbl>    <dbl>     <dbl>     <dbl>
## 1 (Intercept)  6278.      652.        9.62  2.36e-15  4981.      7574.  
## 2 Senior        -22.6       5.30     -4.26  5.08e- 5   -33.1      -12.1 
## 3 Age             0.631     0.721     0.876 3.84e- 1    -0.801      2.06
## 4 Educ           92.3      24.9       3.71  3.61e- 4    42.9      142.  
## 5 Exper           0.501     1.06      0.474 6.36e- 1    -1.60       2.60
## 6 Female       -768.      129.       -5.95  5.39e- 8 -1024.      -512.

Model with mean-centered variables

wages <- wages %>%
  mutate(SeniorCent = Senior - mean(Senior), 
         AgeCent = Age-mean(Age), 
         EducCent = Educ - mean(Educ), 
         ExperCent = Exper - mean(Exper))

• Calculate the regression model using the mean-centered variables.

• How did the model change?

Model with indicator variables

• Use the code below to create a categorical variable for Educ.

wages <- wages %>%
  mutate(EducCat = as.factor(Educ))

• Calculate the regression model using EducCat instead of Educ.