// Open Allbus 2010 data
use "ZA4612_v1-0-1.dta", clear
// Men 25-64 only
keep if v298 == 1
keep if inrange(v301, 20, 64)
// Combine top bottom variables into one
// (Seems pointless, though, as education in years
// was only measured in one of the splits)
generate topbot = v933 if v933 <= 10
replace topbot = v827 if missing(topbot)
replace topbot = . if topbot > 10
// Education, truncated to 5th-95th percentile
qui sum v917 if v917 < 94, detail
generate education = v917 if v917 < 94
replace education = r(p95) if education >= r(p95) & !missing(education)
replace education = r(p95) if education >= r(p95) & !missing(education)
replace education = r(p5) if education <= r(p5) & !missing(education)
// ISEI
generate isei88 = v358 if !inlist(v358, 0, 99)
replace isei88 = v392 if !inlist(v392, 0, 99)
// Household income, logged
generate income = v674 if !inlist(v674, 99997, 99999)
generate lnincome = log(income)
// Generate correlation matrix
cor topbot education income isei
matrix correlations = r(C)
// Plot
plotmatrix, mat(correlations) split(-1(0.10)1) color(vermillion) ///
freq formatcells(%6.2f) nodiag legend(title(Pearson's {it:r}) col(1))
