** LAST LAB **

clear all
set obs 30000
set seed 123

/* regression of z1 and z2 on x */
scalar beta10 = -1
scalar beta11 = .75
scalar beta20 = .1
scalar beta21 = .9

gen x = rnormal(2,4)
gen xi1 = rnormal(0,2)
gen xi2 = rnormal(0,1.5)
gen z1 = beta10 + beta11 * x + xi1
gen z2 = beta20 + beta21 * x + xi2

/* regression of ystar on x and z1,z2*/
scalar gamma0 = 2
scalar gamma1 = .3
scalar gamma2 = .25
scalar gamma3 = .1

scalar sigma2 = 1.45
gen epsilon2 = rnormal(0,sigma2)
gen ystar = gamma0 + gamma1*x + gamma2*z1 + gamma3 * z2 + epsilon2

/* regression of ystar on x */
reg ystar x
mat b = e(b)

scalar alpha0 = b[1,2]
scalar alpha1 = b[1,1]
scalar sigma1 = e(rmse)

/* generate observed outcome y*/

sum ystar,mean
local ymean = r(mean)
gen y = ystar > `ymean'


/* run Probit */



* probit of y on x
probit y x
mat b = e(b)
scalar alpha1_est = b[1,1]

probit y x z1 z2
mat b = e(b)
scalar gamma1_est = b[1,1]

* residualize z
reg z1 x
predict zres1, res
reg z2 x
predict zres2, res

probit y x zres1 zres2, nohead nolog
mat b = e(b)
scalar alpha1_est_resid = b[1,1]

* compare ratios of gamma1/alpha
di gamma1/alpha1
di gamma1_est/alpha1_est
di gamma1_est/alpha1_est_resid








/*** GSS example ***/

clear all
set maxvar 10000
use gss7214

keep if year==2014
svyset vpsu [pw=wtssnr], strata(vstrat) singleunit(scale)

recode region 1/2=1 3/4=2 5/7=3 8=4 9=5, gen(Region5)
lab var Region5 "Region"
lab def Region5 1 "Northeast" 2 "Midwest" 3 "South" 4 "Mountain" 5 "Pacific"
lab val Region5 Region5

gen Repvote=pres12==2 if pres12<4
lab var Repvote "Voted for Republican"
lab val Repvote yesno

gen lat=hispanic>1 if hispanic<.
replace lat = 1 if hispanic>=. & ethnic==17
replace lat = 1 if hispanic>=. & ethnic==22
replace lat = 1 if hispanic>=. & ethnic==25
replace lat = 1 if hispanic>=. & ethnic==28
replace lat = 1 if hispanic>=. & ethnic==38
replace lat = 1 if hispanic>=. & eth1==17
replace lat = 1 if hispanic>=. & eth1==22
replace lat = 1 if hispanic>=. & eth1==25
replace lat = 1 if hispanic>=. & eth1==28
replace lat = 1 if hispanic>=. & eth1==38
replace lat = 1 if hispanic>=. & eth2==17
replace lat = 1 if hispanic>=. & eth2==22
replace lat = 1 if hispanic>=. & eth2==25
replace lat = 1 if hispanic>=. & eth2==28
replace lat = 1 if hispanic>=. & eth2==38
replace lat = 1 if hispanic>=. & eth3==17
replace lat = 1 if hispanic>=. & eth3==22
replace lat = 1 if hispanic>=. & eth3==25
replace lat = 1 if hispanic>=. & eth3==28
replace lat = 1 if hispanic>=. & eth3==38
lab var lat "Hispanic Heritage"
lab def lat 0 "Other" 1 "Hispanic"
lab val lat lat

recode race 1=1 2=2 3=4, gen(Race4)
replace Race4 = 3 if lat==1 & race!=2
lab var Race4 "Racial ancestry"
lab def Race4 1 White 2 Black 3 Latino 4 Other, modify
lab val Race4 Race4


gen Partyid7=partyid+1 if partyid<=6
replace Partyid7=.o if partyid==7
replace Partyid7=partyid if partyid>=.
lab var Partyid7 "Party identification"
lab def Partyid7 1 "Dem: strong" 2 "Dem: not strong" 3 "Ind: lean Dem" 4 "Ind: no lean" 5 "Ind: lean Rep" 6 "Rep: not strong" 7 "Rep: strong"
lab val Partyid7 Partyid7

gen Racdisc=racdif1==1 if racdif1<.
replace Racdisc=racdif1 if racdif1>=.
lab var Racdisc "Discrimination why blacks get less"
lab val Racdisc yesno

gen Raclack=racdif4==1 if racdif4<.
replace Raclack=racdif4 if racdif4>=.
lab var Raclack "Blacks lack what it takes"
lab val Raclack yesno

***  Combine -wrkwayup- & -racdif4- to one variable
gen Racresent = 3-wrkwayup+Raclack-Racdisc


***   Run Models
svy: reg Racresent Partyid i.Region5 if Race4==1 & Repvote<. 
predict Racres_resid if e(sample), resid 

svy: logit Repvote i.Region5 Partyid Racres_resid if Race4==1
est stor Base_logit
svy: logit Repvote i.Region5 Partyid Racresent if Race4==1
est stor Mediate_logit

esttab *_logit , c(b(fmt(3)) se(fmt(3) par)) stat(N, fmt(0)) nocons