*****************************************************************************
*                                                                           *
* exer3-1.do                                                                *
*                                                                           *
* PURPOSE:  analysis of cancer data                                         *
*                                                                           *
* DATE:  01/04/20                                                           *
*                                                                           *
*****************************************************************************

infile age alc tob y count using NewTuyns.dat

***
*** variable labels
***
label variable age "Age Group"
label variable alc "Alcohol"
label variable tob "Tobacco"
label variable y "Case/Control Status"

label define agegps 1 "25-34" 2 "35-44" 3 "45-54" 4 "55-64" 5 "65-74" 6 "75+"
label define alcgps 1 "<40g/day" 2 "40-79g/day" 3 "80-119g/day" 4 "120+g/day"
label define tobgps 1 "0-9g/day" 2 "10-19g/day" 3 "20-29g/day" 4 "30+g/day"
label define status 1 "Case" 0 "Control"

label values age agegps
label values alc alcgps
label values tob tobgps
label values y status

***
*** disease and age
***
tabulate y age [freq=count], chi2 row
tabodds y age [freq=count], or

***
*** dichotomize the exposures (for now -- more later with logitistic regn)
***
generate newalc=alc
recode newalc 1/2=0 3/4=1
label define newgps 0 "<80g/day" 1 ">=80g/day"
label values newalc newgps

generate newtob=tob
recode newtob 1=0 2/4=1
label define newgps2 0 "<10g/day" 1 ">=10g/day"
label values newtob newgps2


***
*** bivariate summaries
***
tabulate age newtob [freq=count], chi2 row
tabulate age newalc [freq=count], chi2 row

tabulate newtob newalc [freq=count], chi2 row
tabulate tob alc [freq=count], chi2 row


***
*** odds ratios - crude and adjusted
***

cc y newalc [freq=count]
cc y newalc [freq=count], by(age)
cc y newalc [freq=count], by(tob)

mhodds y newalc age [freq=count]
mhodds y newtob age tob [freq=count]
mhodds y newalc age [freq=count], by(tob)



cc y newtob [freq=count]
cc y newtob [freq=count], by(age)
cc y newtob [freq=count], by(alc)

mhodds y newtob age [freq=count]
mhodds y newtob age alc [freq=count]
mhodds y newtob age [freq=count], by(alc)


***
*** create a combined variable and stratify jointly
***

generate agealc = 100*age + alc
mhodds y newtob agealc [freq=count]