Dear Statalist,
PFA the dummy data.
Here I have the following variables -
1. Cluster ID (cluster_id)
2. Patient ID (patient_id)
3. Time - 0 for baseline and 1 for endline (time)
4. Treatment - 0 for control and 1 for intervention (treatment)
5. Systolic BP (systolic)
6. Diastolic BP (diastolic)
I have two datasets of different times
1. A cross sectional survey at baseline and
2. A cross sectional survey at endline.
I want to see the difference in difference in the outcome variables, for example, systolic BP.
I have done the following code,
reg systolic time#treatment, r
Shall I do something for taking the clusters into account?
Note: The respondents at baseline are totally different from the respondents at endlline, only the clusters are same at the two timepoints.
0 Response to Difference in Difference
Post a Comment