************************************
************************************
***SOCI 600: INTRODUCTION TO SOCIOLOGICAL DATA ANALYSIS
***ANALYSIS OF VARIANCE & CHI SQUARE
************************************
************************************

************************************
***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\Stata06a-b.log", replace text

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

***Open 2021 ACS (only Texas)
use "$data\ACS2021.dta", clear

***Complex survey design
svyset cluster [pweight=perwt], strata(strata) singleunit(scaled)

************************************
***GENERATE VARIABLES
************************************
***Sex
gen female=.
  replace female=0 if sex==1 // Male
  replace female=1 if sex==2 // Female

label define female 0 "Male" 1 "Female"
label values female female

***Race/ethnicity
gen raceth=.
  replace raceth=1 if race==1 & hispan==0 // White
  replace raceth=2 if race==2 & hispan==0 // Black
  replace raceth=3 if hispan>=1 & hispan<=4 // Hispanic
  replace raceth=4 if (race==4 | race==5 | race==6) & hispan==0 // Asian
  replace raceth=5 if race==3 & hispan==0 // Native American
  replace raceth=6 if (race==7 | race==8 | race==9) & hispan==0 // Other

label define raceth 1 "White" 2 "African American" 3 "Hispanic" ///
                    4 "Asian" 5 "Native American" 6 "Other races"
label values raceth raceth

***Age
egen agegr = cut(age), at(0,16,20,25,35,45,55,65,100)

label define agecode 0 "0-15" 16 "16-19" 20 "20-24" 25 "25-34" ///
                     35 "35-44" 45 "45-54" 55 "55-64" 65 "65-100"
label values agegr agegr

***Educational attainment
gen educgr=.
  replace educgr=1 if educ>=0 & educ<=5 // Less than high school
  replace educgr=2 if educ==6 // High school
  replace educgr=3 if educ==7 | educ==8 // Some college
  replace educgr=4 if educ==10 // College
  replace educgr=5 if educ==11 // 5+ years of college, graduate school

label define educgr 1 "Less than high school" 2 "High school" ///
                    3 "Some college" 4 "College" 5 "Graduate school"
label values educgr educgr

***Marital status
gen marital=.
  replace marital=1 if marst==1 | marst==2 // Married
  replace marital=2 if marst>=3 & marst<=5 // Separated, divorced, widowed
  replace marital=3 if marst==6 // Never married, single

label define marital 1 "Married" 2 "Separated, divorced, widowed" 3 "Never married"
label values marital marital

***Migration status
gen migrant=.
  replace migrant=1 if migrate1d==10 | migrate1d==23 // same house or within PUMA
  replace migrant=2 if migrate1d>=24 & migrate1d<=32 // internal migrant
  replace migrant=3 if migrate1d==40 // international migrant

label define migrant 1 "Non-migrant" 2 "Internal migrant" 3 "International migrant"
label values migrant migrant

***Wage and salary income
gen income=.
  replace income=incwage if incwage!=999999

************************************
***ANOVA - Income by race/ethnicity
************************************
***Descriptive table
***"tabstat" command by race/ethnicity does not accept complex survey design
tabstat income if income!=0 & income!=. [fweight=perwt], by(raceth) stat(mean sd n)

***"mean" command by race/ethnicity accepts complex survey design (correct estimation of standard deviation)
svy, subpop(if income!=0 & income!=.): mean income, over(raceth)
estat sd

***"mean" command for overall population accepts complex survey design (correct estimation of standard deviation)
svy, subpop(if income!=0 & income!=.): mean income
estat sd

***Sample distribution by race/ethnicity and missing cases (no weights)
tab raceth if income!=0 & income!=., m

***Population distribution by race/ethnicity (with weight)
tab raceth if income!=0 & income!=. [fweight=perwt]

***One-way ANOVA does not accept complex survey design
oneway income raceth if income!=0 & income!=. [aweight=perwt]
anova income raceth if income!=0 & income!=. [aweight=perwt]

************************************
***CHI SQUARE - Education by race/ethnicity
************************************
***It would be incorrect to use fweight,
***because you would get statistical significance
***by indicating to the test that you have
***more observations than what was actually collected

***Weights that preserve sample size (aweight, pweight)
***are not allowed in Stata to estimate chi square

***Thus, estimate chi square using the
***complex survey design command (svy)

***Use column percentages with weight
tab educgr raceth [fweight=perwt], col
tab educgr raceth [fweight=perwt], col nofreq // column percentage

***Observed frequencies (fo)
tab educgr raceth // sample size

***Expected frequencies (fe)
tab educgr raceth, exp nofreq

***Chi square option works only without weights
tab educgr raceth, chi col
tab educgr raceth, chi col nofreq

***Use the chi square estimated with complex survey design
svy: tab educgr raceth, col // chi square test

***Use population size from this table
tab educgr raceth [fweight=perwt] // population size

***Use missing cases from this table
tab educgr raceth, m // missing cases

************************************
***CLOSING COMMANDS
************************************
***Save data
save "$data\Stata06a-b.dta", replace

***Save log
log close