Oaxaca with R

setwd ("F:/Dropbox/R/")

#install.packages("oaxaca")

require("oaxaca")

# set random seed

set.seed(08544)

# load data set of Hispanic workers in Chicago

data("chicago")

# perform Blinder-Oaxaca Decomposition:

# explain differences in log real wages across native and foreign-born groups

results <- oaxaca(ln.real.wage ~ age + female + LTHS + some.college +

college + advanced.degree | foreign.born,

data = chicago, R = 50)

results$n

results$y

results$threefold$overall

# plot results of the threefold decomposition, variable-by-variable

# only include educational variables

# decomposition components along the left side of the plot

plot(results, component.left = TRUE,

     variables = c("LTHS", "some.college", "college", "advanced.degree"),

     variable.labels = c("LTHS" = "less than high school",

      "some.college" = "some college",

       "advanced.degree" = "advanced degree"))

plot(results, components = c("endowments","coefficients"))

# plot results of the twofold decomposition (overall results)

# equal weight for Group A and B in reference coefficient determinantion (weight = 0.5)

# unexplained portion split into A and B

plot(results, decomposition = "twofold", type = "overall",

     weight = 0.5, unexplained.split = TRUE,

     bar.color = c("limegreen", "hotpink", "steelblue"))

results$twofold$overall

plot(results, decomposition = "twofold", weight = -1)

plot(results, decomposition = "twofold", weight = -1,

      unexplained.split = TRUE, components = c("unexplained A",

      "unexplained B"), component.labels = c("unexplained A" =

      "In Favor of Natives", "unexplained B" = "Against the Foreign-Born"),

      variables = c("age", "female", "college"), variable.labels = c("age" =

      "Years of Age", "female" = "Female", "college" = "College Education"))

plot(results, decomposition = "twofold", weight = -1,

    unexplained.split = TRUE, components = c("unexplained A",

    "unexplained B"), component.labels = c("unexplained A" =

    "In Favor of Natives", "unexplained B" = "Against the Foreign-Born"),

    component.left = TRUE, variables = c("age","female","college"),

    variable.labels = c("age" = "Years of Age", "female" = "Female",

    "college" = "College Education"))

#Specifc numerical values of the point estimates of the unexplained discrimination components

#can, of course, be obtained directly from the "oaxaca"-class object:

variables <- c("age", "female", "college")

columns <- c("weight", "coef(unexplained A)", "coef(unexplained B)")

results$twofold$variables[[5]][variables, columns]