Hello all,

I am working on graphing yhat of death by month to illustrate the impact of a health care intervention (implemented in month 10), but I am having trouble putting together the appropriate code.

1. The model is a mixed effects logistic regression model [using meglm] and the design is interrupted time series

2. The below code is essentially what I want because it shows the predicted values of the outcome of interest before and after the intervention (intervention at month 10) for each month

twoway(scatter yhat month) (line yhat month if month < 10, sort) (line yhat month if month >= 10, sort), xline(10)

3. However, I'm trying to make it work for my purposes and I would love help!!
- I need to store yhats for each month for each meglm model (reason: takes days for each meglm model to run!)
- I want to adapt the above code so I am showing yhats for each month using stored estimates while hiding the scatter plot, it is looking too messy
- I need to find a way of storing the graphs and then editing them once they are stored (way of storing graphs as is and then editing them?)

Thanks for any advice!

Amy