/* An Example of dummy dependent variable (binary choice) model 
Data " cps_msa2013 : 2013 Current population survey for 3 MSA
3 MSA : NY, LA, CHICAGO
Created by Jin Man Lee
Updated: 10/31/2023
*/  
clear all
use https://bigblue.depaul.edu/jlee141/econdata/cps_data/cps_msa2013.dta

gen educyr = 0 
replace educyr =  1 if educ92 == 1 
replace educyr =  4 if educ92 == 2 
replace educyr =  6 if educ92 == 3 
replace educyr =  8 if educ92 == 4 
replace educyr =  9 if educ92 == 5 
replace educyr =  10 if educ92 == 6 
replace educyr =  11 if educ92 == 7 
replace educyr =  12 if educ92 == 8  |  educ92 == 9  
replace educyr =  14 if educ92 == 10 | educ92 == 11 | educ92 == 12 
replace educyr =  16 if educ92 == 13 
replace educyr =  18 if educ92 == 14  
replace educyr =  20 if educ92 == 15 
replace educyr =  21 if educ92 == 16 
gen edusq = educyr*educyr 
tab lfstat female
tab lfstat female, nolabel

gen laborp = (lfstat == 1 | lfstat == 2 )
keep if !missing(laborp) & female == 1
tab laborp female
gen lhincome = log(inch_all) 

/* LP, PROBIT, and LOGIT Models */
reg laborp age educyr married child lhincome
predict p_reg 
mfx

probit laborp age educyr married child lhincome
predict p_probit 
mfx

logit laborp age educyr married child lhincome
predict p_logit
mfx

twoway (scatter (laborp p_reg) lhincome) (scatter p_probit lhincome) (scatter p_logit lhincome)