Is there a a command similar to stir in stata, for generating incident rates by group, but after accounting for clustered data? My data is in the following structure; where..
The data example:
Thank you for your time!
- Each ID can have infections with multiple strains, and so appears multiple times, once for each strain that its negative for at the baseline so we can assess incidence over followup.
- ID is the participant identifier and newid is a variable i made which is a infection/strain level identifier
The data example:
Code:
* Example generated by -dataex-. For more info, type help dataex clear input double id float newid double(strain_type visit) float(Oral_Date Result incexit) 10004 1 6 52 18211 0 0 10004 1 6 53 18386 0 175 10004 1 6 54 18561 0 350 10004 1 6 55 18722 0 511 10004 1 6 56 18904 0 693 10004 1 6 57 19086 0 875 10004 1 6 58 19275 0 1064 10004 1 6 59 19457 0 1246 10004 1 6 60 19642 0 1431 10004 1 6 61 19845 0 1634 10004 1 6 102 21116 0 2905 10004 1 6 103 21480 0 3269 10004 2 11 52 18211 0 0 10004 2 11 53 18386 0 175 10004 2 11 54 18561 0 350 10004 2 11 55 18722 0 511 10004 2 11 56 18904 0 693 10004 2 11 57 19086 0 875 10004 2 11 58 19275 0 1064 10004 2 11 59 19457 0 1246 10004 2 11 60 19642 0 1431 10004 2 11 61 19845 0 1634 10004 2 11 102 21116 0 2905 10004 2 11 103 21480 0 3269 10004 3 16 52 18211 0 0 10004 3 16 53 18386 0 175 10004 3 16 54 18561 0 350 10004 3 16 55 18722 0 511 10004 3 16 56 18904 0 693 10004 3 16 57 19086 0 875 10004 3 16 58 19275 0 1064 10004 3 16 59 19457 0 1246 10004 3 16 60 19642 0 1431 10004 3 16 61 19845 0 1634 10004 3 16 102 21116 0 2905 10004 3 16 103 21480 0 3269 10004 4 18 52 18211 0 0 10004 4 18 53 18386 0 175 10004 4 18 54 18561 0 350 10004 4 18 55 18722 0 511 10004 4 18 56 18904 0 693 10004 4 18 57 19086 0 875 10004 4 18 58 19275 0 1064 10004 4 18 59 19457 0 1246 10004 4 18 60 19642 0 1431 10004 4 18 61 19845 0 1634 10004 4 18 102 21116 0 2905 10004 4 18 103 21480 0 3269 end format %dN/D/CY Oral_Date