**********************************************************
*	Program Name:	Calculating SMR and IPTW in SAS
*	Original date:	April 14 2019
*	Updated:	Feb 22 2021 for categorical exposure
*	Author:		Bailey DeBarmore
*	Software:	Stata
*	Downloaded from www.baileydebarmore.com/epicode
**********************************************************;




******************************************
* Calculating SMR weights
*****************************************;
​* Syntax for teffects statement

*teffects ipw (<outcome>) (<exposure> <covariates>), atet
*where <outcome> is your outcome variable, <exposure> is your exposure variable, and 
*<covariates> is a list of your covariates to generate your weights. 

*Example: Binary
*Outcome = lowbirthwt
*Exposure = maternalsmoke
*Covariates = maternalage nonwhite

*Use the teffects statement to generate your weights and then apply them in a logistic (default) model all in 1 step

teffects ipw (lowbirthwt) (maternalsmoke maternalage nonwhite), atet

*If your outcome is continuous, you can specify a probit model

*Example: Continuous
*Outcome = birthwt
*Exposure = maternalsmoke
*Covariates = maternalage nonwhite

teffects ipw (birthwt) (maternalsmoke maternalage nonwhite, probit), atet

******************************************
* Calculating IPTW
*****************************************;
​
​* Syntax for teffects statement

*teffects ipw (<outcome>) (<exposure> <covariates>), ate
*where <outcome> is your outcome variable, <exposure> is your exposure variable, and 
*<covariates> is a list of your covariates to generate your weights. 

*Example: Binary
*Outcome = lowbirthwt
*Exposure = maternalsmoke
*Covariates = maternalage nonwhite

*Use the teffects statement to generate your weights and then apply them in a logistic (default) model all in 1 step

teffects ipw (lowbirthwt) (maternalsmoke maternalage nonwhite), ate

*If your outcome is continuous, you can specify a probit model

*Example: Continuous
*Outcome = birthwt
*Exposure = maternalsmoke
*Covariates = maternalage nonwhite

teffects ipw (birthwt) (maternalsmoke maternalage nonwhite, probit), ate

*---------------------------------------------------------------------*

*If your treatment (exposure) is categorical, you can't use teffects.
*Instead, use mlogit to estimate the probability of treatment
*adjusted for your variables and then use postestimation 'predict'
*to create a denominator variable for each value of treatment
*using option outcome

*Example code is shown below for a treatment (exposure) with values 0, 1, 2, 3

mlogit <exposure> <vars>
predict p0, outcome(0)
​​predict p1, outcome(1)
predict p2, outcome(2)
predict p3, outcome(3)

*Then create your unstabilized iptw variable by exposure level using your new denominators

gen iptw=.
replace iptw=1/p0 if <exposure>==0
​replace iptw=1/p1 if <exposure>==1
replace iptw=1/p2 if <exposure>==2
replace iptw=1/p3 if <exposure>==3
​
*To create stabilized weights, tabulate your treatment (exposure) varaible to get 
*the proportion of your dataset in each category. Then plug in those values as
*the numerator for stabilized weights. Code below is shown for an example where
60% are in X=0, 14% in X=1, 20% in X=2, and 6% in X=3.

gen siptw=.
replace siptw=0.6/p0 if <exposure>==0
replace siptw=0.14/p1 if <exposure>==1
replace siptw=0.2/p2 if <exposure>==2
replace siptw=0.06/p3 if <exposure>==3