************************************
************************************
***SOCI 420: ADVANCED METHODS OF SOCIAL RESEARCH
***HYPOTHESIS TESTING I: THE ONE-SAMPLE CASE (chapter 8)
************************************
************************************

************************************
***CLEAR MEMORY
************************************
clear all

************************************
***CREATE SHORTCUTS AND LOG FILE
************************************
***Shortcut for folders
global codes  = "H:\course\codes"
global data   = "H:\course\data"
global output = "H:\course\output"

***Start saving results window
log using "$codes\Stata08.log", replace text

************************************
***OPENING COMMANDS
************************************
***Tell Stata to not pause for "more" messages
set more off

***Open 2021 GSS
use "$data\GSS2021.dta", clear

***Complex survey design
svyset [weight=wtssnrps], strata(vstrat) psu(vpsu) singleunit(scaled)

************************************
***GENERATE VARIABLES
************************************

************************************
***Sex

***Original variable
tab sex
tab sex, m
tab sex, m nolabel

***Generate variable
generate female=.
  replace female=0 if sex==1
  replace female=1 if sex==2

***Verify variable
tab female, m
tab sex female, m

***Labels
label variable female "Sex" // Label for variable
label define female 0 "Male" 1 "Female" // Labels for categories
label values female female // Assign labels for categories

tab female, m

************************************
***Hispanic

***Original variable
tab hispanic
tab hispanic, m
tab hispanic, m nolabel

***Generate variable
gen hisp=.
  replace hisp=0 if hispanic==1
  replace hisp=1 if hispanic>=2 & hispanic<=50

***Verify variable
tab hisp, m
tab hispanic hisp, m

***Labels
label variable hisp "Hispanic" // Label for variable
label define hisp 0 "Non-Hispanic" 1 "Hispanic" // Labels for categories
label values hisp hisp // Assign labels for categories

tab hisp, m

************************************
***Race/ethnicity

***Original variable
tab race
tab race, m
tab race, m nolabel

***Generate variable
gen raceeth=.
  replace raceeth=1 if race==1 & hisp==0 //non-hispanic white
  replace raceeth=2 if race==2 & hisp==0 //non-hispanic black
  replace raceeth=3 if hisp==1           //hispanic
  replace raceeth=4 if race==3 & hisp==0 //other

***Verify variable
tab raceeth, m
tab raceeth race, m
tab raceeth hisp, m

***Labels
label variable raceeth "Race/Ethnicity" // Label for variable
label define racecode 1 "Non-hispanic white" 2 "Non-hispanic black" 3 "Hispanic" 4 "Other" // Labels for categories
label values raceeth racecode // Assign labels for categories

tab raceeth, m

************************************
***Age group

***Original variable
tab age
tab age, m
tab age, m nolabel

***Generate variable
egen agegr = cut(age), at(18,25,45,65,90)

***Verify variable
tab agegr, m
table agegr, stat(min age) stat(max age) stat(count age)

***Labels
label variable agegr "Age group" // Label for variable
label define agecode 18 "18-24" 25 "25-44" 45 "45-64" 65 "65-89" // Labels for categories
label values agegr agecode // Assign labels for categories

tab agegr, m

************************************
***Education group

***Original variable
tab educ, m
tab educ, m nolabel

***Generate variable
gen educgr=.
  replace educgr=1 if educ>=0 & educ<=11 // Less than high school
  replace educgr=2 if educ==12 // High school
  replace educgr=3 if educ>=13 & educ<=15 // Some college
  replace educgr=4 if educ==16 // College
  replace educgr=5 if educ>=17 & educ<=20 // 5+ years of college, graduate school

***Verify variable
tab educgr, m
tab educ educgr, m
  
***Labels
label variable educgr "Education group" // Label for variable
label define educgr 1 "Less than high school" 2 "High school" 3 "Some college" 4 "College" 5 "Some graduate school" // Labels for categories
label values educgr educgr // Assign labels for categories

tab educgr, m

************************************
***Religion

***Original variable
tab relig
tab relig, m
tab relig, m nolabel

***Generate variable
gen religion=.
  replace religion=1 if relig==1 //protestant
  replace religion=2 if relig==2 //catholic
  replace religion=3 if relig==3 //jewish
  replace religion=4 if relig>=5 & relig<=13 //other
  replace religion=5 if relig==4 //none

***Verify variable
tab religion, m
tab relig religion, m

***Labels
label variable religion "Religion" // Label for variable
label define relcode 1 "Protestant" 2 "Catholic" 3 "Jewish" 4 "Other" 5 "None" // Labels for categories
label values religion relcode // Assign labels for categories

tab religion, m

************************************
***Veterans

***Original variable
tab vetyears
tab vetyears, m
tab vetyears, m nolabel

***Generate variable
gen veteran=.
  replace veteran=1 if vetyears>=1 & vetyears<=4 // Some years of active duty
  replace veteran=0 if vetyears==0 // No active duty

***Verify variable
tab veteran, m
tab vetyears veteran, m

***Labels
label variable veteran "Veteran" // Label for variable
label define veteran 0 "Non-Veteran" 1 "Veteran" // Labels for categories
label values veteran veteran // Assign labels for categories

tab veteran, m

************************************
***Immigration attitude

***Original variable
tab letin1, m
tab letin1, m nolabel

***Generate variable
***"remain the same as it is" will be missing
gen proimmig=.
  replace proimmig=1 if letin1==1 | letin1==2
  replace proimmig=0 if letin1==4 | letin1==5

***Verify variable  
tab proimmig, m
tab letin1 proimmig, m

***Labels
label variable proimmig "Immigration attitude" // Label for variable
label define proimmig 0 "Anti-immigration" 1 "Pro-immigration" // Labels for categories
label values proimmig proimmig // Assign labels for categories

tab proimmig, m

************************************
***Political party

***Original variable
tab partyid, m
tab partyid, m nolabel

***Generate variable
***"Independents" will be missing
gen democrat=.
  replace democrat=1 if partyid>=0 & partyid<=2
  replace democrat=0 if partyid>=4 & partyid<=6

***Verify variable
tab democrat, m
tab partyid democrat, m

***Labels  
label variable democrat "Political party" // Label for variable
label define party 1 "Democrats" 0 "Republicans" // Label for categories
label values democrat party // Assign labels for categories

tab democrat, m

************************************
***ONE-SAMPLE Z-TEST AND t-TEST
************************************
***Personal income of Veterans (GSS)
***compared to population 15+ (U.S. Census Bureau)
***https://fred.stlouisfed.org/series/MAPAINUSA646N#

***Mean personal income in 2021 (U.S. Census Bureau) = 57,143

***Mean personal income of Veterans in 2021 (GSS)
svy, subpop(if veteran==1): mean conrinc
mean conrinc if veteran==1

***Is the mean income of Veterans ($49,562.49) significantly lower
***than mean income of population 15+ ($57,143)?

***Z-test (it does not allow the use of weight or complex survey design)
ztest conrinc=57143 if veteran==1

***t-test (it does not allow the use of weight or complex survey design)
ttest conrinc=57143 if veteran==1

************************************
***ONE-SAMPLE TEST OF PROPORTIONS
************************************
***Gender composition of sample of adult population (18+) (GSS)
***compared to overall population (U.S. Census Bureau)
***https://www.census.gov/quickfacts/fact/table/US/PST045221

***Percentage of women in the total population in 2021 (U.S. Census Bureau) = 50.5%

***Percentage of 18+ women in 2021 (GSS)
tab female [aweight=wtssnrps]
tab female

***Is the percentage of women 18+ (55.94%) significantly higher
***than the percentage of women in the total population (50.5%)?

***Proportion test (it does not allow the use of weight or complex survey design)
prtest female=.505

************************************
***CLOSING COMMANDS
************************************
***Save data
save "$data\Stata08.dta", replace

***Save log
log close