How to combine treatment effect (teffects) for multivalued treatment with difference in difference (DID) ?

[Rythia Afkar]

Halo,

I want to estimate treatment effects for multivalued treatments using a panel data, t1 (before) and t2(after) interventions. I have 4 treatments (variable 'treat'). I understand that in order to estimate ATT(average treatment on the treated) I can apply 3 methods: either teffects ra for regression adjustment, or teffects ipw for inverse probability weighting, or teffects ipwra for doubly robust estimation. My question is:

Can I combine the treatment effect methods using DID (diff in diff) method?

So for example, to combine teffects ra and DID, can I use below command:

teffects ra (difftotcons troof tfloor septic twal toilet water lighting fcook hhsize sltblt askeskin pregnant y*t*r) (treatment), atet

with:
- selected outcome: difftotcons = consumption_year_t2 - consumption_year_t1 (difference in total consumption t2 and t1)
- covariates: troof tfloor septic twal toilet water lighting fcook hhsize sltblt askeskin pregnant y*t*r
- treatment: treat


Thank you in advance for your help!

Best,
Rythia