Decomposing the difference between two means

// GSS 1990-2004
use year race sibs reg16 educ maeduc if inrange(year, 1990, 2004) ///
  & year != 2002 ///  // 2002 measures race in a non-standard way
    using "gss7221_r1.dta", clear

// In Table 7.8 Treiman states that he's got 17,090 cases (14,985 non-black + 
// 2,105 black). There seems to be no way I can get there with the data
// because maeduc, mother's education, only has 15,996 valid observations.

// The reason for this seems to be that in his do-file, he starts with
// the 1990 GSS file and then appends all other GSS year files -- including
// the 1990 file, thus including the 1990 file twice. Running the do-file with

// expand 2 if year == 1990

// uncommented (almost) replicates the numbers reported in the book.

drop year // Not needed

// Race variables
generate black    = (race == 2)
generate nonblack = !black
drop race

// Truncate number of siblings at 15
replace sibs = 15 if sibs > 15  & !missing(sibs)
label var sibs "Sibsize"

// South
gen south = (inrange(reg16, 5, 7))
label var south "Southern origin"
drop reg16

// Education
label var educ "Education"
label var maeduc "Mother's education"

// Listwise deletion
mark touse if !missing(educ, maeduc, sibs)
keep if touse



// Table 7.8a
eststo clear
local vlist educ maeduc sibs south 
local upper

local lower `vlist'

foreach v of local vlist {
  estpost correlate `v' `lower' if !black
  local nnonblack = e(N)
  foreach m in b rho p count {
   matrix `m' = e(`m')
  }
  if "`upper'"!="" {
   estpost correlate `v' `upper' if black
   local nblack = e(N)
   foreach m in b rho p count {
    matrix `m' = e(`m'), `m'
   }
  }
  ereturn post b
  foreach m in rho p count {
   quietly estadd matrix `m' = `m'
  }
  eststo `v'
  local lower: list lower - v
  local upper `upper' `v'
}

// Table 7.8b
esttab using table2.tex, replace nonumbers noobs mtitles not booktabs label nostar ///
       title(Correlations between study variables: Blacks (\emph{N} = `nblack') above, non-blacks (\emph{N}  = `nnonblack') below the diagonal) ///
mtitle("Education" "Mother's education" "Sibsize" "Southern origin")

eststo clear
eststo: estpost sum educ maeduc sibs south if black
eststo: estpost sum educ maeduc sibs south if !black

esttab using table1.tex, booktabs replace ///
       cells("mean(label(Mean) fmt(2))" "sd(label(SD) fmt(2) par)") ///
       label mtitle("Blacks" "Non-Blacks") ///
       title("Means and standard deviations of study variables")



// Table 7.9 
eststo clear
eststo: regress educ maeduc sibs south if touse & black
eststo: regress educ maeduc sibs south if touse & !black

esttab using table3.tex, booktabs replace ///
       b(2) se(2) r2(2) ///
       label mtitle("Blacks" "Non-Blacks") ///
       title("Coefficients of a model of years of schooling, for blacks and non-blacks, US adults, 1990--2004")



// Table 7.10
eststo clear
eststo: oaxaca educ maeduc sibs south if touse, by(black) detail noisily
eststo: oaxaca educ maeduc sibs south if touse, by(nonblack) detail noisily
esttab using table4.tex, booktabs replace ///
       b(2) nose not label mtitle("Blacks as reference" "Non-Blacks as reference") ///
       eqlabel("\emph{Overall}" ///
               "\emph{Differences in assets}" ///
               "\emph{Differences in returns to assets}" ///
               "\emph{Interactions}") ///
       coeflabels(overall:difference "Difference in years of schooling" ///
                 overall:endowments "Total due to difference in assets" ///
                 overall:coefficients "Total due to difference in returns" ///
                 overall:interaction "Total due to interactions") ///
       drop(overall:group*) ///
       varwidth(30) alignment(D{.}{.}{-1}) ///
       title("Decomposition of the difference in the mean years of schooling by blacks and non-blacks, US adults, 1990--2004")