Support #515

Matching pid across waves

Added by Christopher Booth almost 8 years ago. Updated almost 8 years ago.

Data documentation
Start date:
% Done:



I have merged whhresp and windresp files using a m:1 match as you mentioned before. However, when matching pid between waves J and O I have found that only 1500 individuals are included in both waves. I am under the impression that this should not be the case as all individuals in the sample are followed for every wave? So should all individuals interviewed in wave J also have been interviewed in wave O? Please could you let me know if this is the case and possibly what could have led me to only finding 1500 persons with the same pids across waves J and O.

Thank you


Updated by Alita Nandi almost 8 years ago

  • Assignee changed from Gundi Knies to Christopher Booth
  • % Done changed from 0 to 90

Hello Christopher,

I have just replicated what you have done and I found 10,514 individuals in both waves J and O. Here is the code I used:

use oindresp, clear
merge m:1 ohid using ohhresp
drop if _m==2
drop _m
save o, replace

use jindresp, clear
merge m:1 jhid using jhhresp
drop if _m==2
drop _m
save j, replace

use o, clear
merge 1:1 pid using j

Best wishes,


Updated by Victoria Nolan almost 8 years ago

  • Status changed from New to Closed
  • % Done changed from 90 to 100

Also available in: Atom PDF