Presenting table 1 with iptw for categorical variables

[Rose Matthews]

Hello all. I don’t know if this is stata list remit as this isn’t a code issue but really an idea

I have used iptw using the following code below:

logit $treatment $covariatelist
predict pscore_iptw

//Create Propensity score weights
//weight for control

gen attweight=pscore_iptw/(1-pscore_iptw) if $treatment == 0

//creating weight for treatment
replace attweight = 1 if $treatment == 1

//Apply weights to means
mean $xlist if $treatment == 0 [pw=attweight] 

//control
mean $xlist if $treatment == 1 [pw=attweight] //treatment

PROBLEM:

i need to present my table 1. Similar to tiis
https://www.researchgate.net/profile...adjustment.png

Now I present the mean weights of a variable pre adjustment and post adjustment, this is easy with a continous variable as I only have 1 value ie 1 mean weight, and even more so with a categorical variable with 2 levels, as one of these is the reference [1]

QUESTION:
How do I present the weights for the different levels of a categorical variable with more than 2 levels eg ASA , which has 3 levels ASA1 ASA2 ASA3. Asa is a part of the global macro $covaristelist

a colleague advised me to use -svyset- in this way
webuse nhanes2
svyset psu [pweight=finalwgt], strata(strata) vce(linearized)
singleunit(missing)
svy: tab region


however, I don’t see how the above can be related to the way I generate the attweight p weights above.

or pwrhaps in your experience how should I present table 1 following iptw ?