**********************************
* Import data and only keep 1995 *
**********************************

clear
set memory 1g
use "http://biostat.mc.vanderbilt.edu/wiki/pub/Main/CourseBios312/salary.dta"
table year
keep if year==95


de

**************************************************
* Convert string variables to numeric indicators *
**************************************************

* Make a male indicator variable; Female is reference group
gen male=.
replace male=1 if sex=="M"
replace male=0 if sex=="F"
table sex male

* Can also create a 'female' indicator variable where male is the reference group
gen female=.
replace female=1 if sex=="F"
replace female=0 if sex=="M"
table sex female


************************************
* Salary by Sex: Unadjusted models *
************************************

graph box salary, by(sex)

regress salary male
regress salary female
ttest salary, by(sex)

* Caclulate pooled standard deviation 
di ((1481.218^2 * 408 + 2089.757^2 * 1187) / 1595)^.5


* Other methods of specifying the regression model
regress salary male female
regress salary male female, noconstant

* Aside: the xi command
xi: regress salary i.sex
list sex male female _Isex_2 if _n <= 10

*What about yearly salary instead?
gen salaryyr = salary*12
regress salary male
regress salaryyr male


*************************************
* Salary by rank: Unadjusted models *
*************************************

table rank

gen rankassist=.
replace rankassist=1 if rank=="Assist"
replace rankassist=0 if rank=="Full" | rank=="Assoc"
table rankassist rank


gen rankassoc=.
replace rankassoc=1 if rank=="Assoc"
replace rankassoc=0 if rank=="Full" | rank=="Assist"
table rankassoc rank

gen rankfull=.
replace rankfull=1 if rank=="Full"
replace rankfull=0 if rank=="Assoc" | rank=="Assist"
table rankfull rank

graph box salary, by(rank)

regress salary rankassoc rankfull
regress salary rankassist rankfull
regress salary rankassoc rankassist

xi: regress salary i.rank

table rank, c(n salary mean salary sd salary)

di ((314*1063.612^2 + 436*1140.953^2 + 844*1901.428^2) / (315+437+845-3))^.5

regress salary rankassist rankassoc rankfull, nocon
di 1578.9976 / 315^.5
di 1578.9976 / 437^.5
di 1578.9976 / 845^.5


****************************************
* Salary by year of degree and startyr *
****************************************

scatter yrdeg startyr
scatter yrdeg startyr || lfit yrdeg startyr

lowess yrdeg startyr, bwidth(.2) addplot((lfit yrdeg startyr))

regress yrdeg startyr
corr yrdeg startyr

regress salary yrdeg
regress salary startyr

regress salary yrdeg startyr