Our running analysis of income gender inequality in Illinois.

inclass.R

pums <- read.csv("small_pums.csv")

hist(pums$WAGP)

male_income <- pums$WAGP[pums$SEX=="male"]
female_income <- pums$WAGP[pums$SEX=="female"]

plot(WAGP ~ SEX, data=pums)

summary(lm(WAGP ~ 1,data=pums))

model_1 <- lm(WAGP ~ SEX, data=pums)
summary(model_1)

pums$ESR <- factor(pums$ESR,
                   labels=c("civilian employed, at work",
                            "civilian employed, with a job but not at work",
                            "unemployed",
                            "armed forces, at work",
                            "not in labor force"))

mean(pums$WAGP,na.rm = TRUE)

sum(is.na(pums$WAGP))

summary(pums$ESR)

model.2 <- lm(WAGP ~ SEX,
              data=pums[pums$ESR=="civilian employed, at work",])

plot(WAGP ~ SEX,
     data=pums[pums$ESR=="civilian employed, at work",])

summary(model.2)

pums$DIS
pums$disability = factor(pums$DIS, labels = c("with disability", "without disabiltiy"))

plot(disability ~ SEX, data=pums)

pums$college <- factor(pums$SCHL > 17, labels=c("no college", "some college"))

model.2 = lm(WAGP ~ SEX,
             data=pums[pums$ESR=="civilian employed, at work",])
summary(model.2)


model.3 = lm(WAGP ~ SEX + college,
             data=pums[pums$ESR=="civilian employed, at work",])
summary(model.3)

pums$FOD1P
#2300 gen ed, 2308 science + comp teacher educ, 1401 arch
FOD1P = ifelse(pums$FOD1P==2300, 
               "gen ed", 
               ifelse(pums$FOD1P==2308, 
                      "science teach", 
                      ifelse(pums$FOD1P==1401, 
                             "arch",
                             "other")))
FOD1P[is.na(FOD1P)] <- "no bachelors"
summary(factor(FOD1P))

sum(pums$FOD1P==2300, na.rm=TRUE)

pums$FOD1P.simple=factor(FOD1P)
lm(WAGP ~ SEX + FOD1P.simple,
   data=pums[pums$ESR=="civilian employed, at work",])
levels(pums$FOD1P.simple)
employed <- pums[pums$ESR=="civilian employed, at work",]


aggregate(data=employed, WAGP~SEX+FOD1P.simple, mean)

pums$FOD.all=pums$FOD1P
pums$FOD.all[is.na(pums$FOD.all)]="no bachelors"

employed <- pums[pums$ESR=="civilian employed, at work",]



lm(WAGP ~ SEX + factor(FOD.all), employed)



lm(WAGP ~ AGEP, employed)