Support #720

GPS & BHPS sample

Added by Theodora Kokosi about 7 years ago. Updated about 7 years ago.

Data releases
Start date:
% Done:



Dear all,

I would like to ask what is the sample size of the respondents in wave 2 and wave 3 (the productive cases in the main respondents datafiles). I would like to include all the respondents from all the countries (GB and Northern Ireland but not the ethnic minorities boost). The reason I am asking is because the numbers in the datasets and the numbers in the manuals do not match up and I am trying to figure out what is going on.

Any information provided would be much appreciated.

Kind regards,


Updated by Gundi Knies about 7 years ago

  • Category set to Data releases
  • Assignee set to Theodora Kokosi
  • Target version set to X M

Hi Theodora,
can you be more specific please. Which two pieces of information are you comparing exactly? And which version of the data are you looking at? The tables in the manual (user guide?) may relate to previous releases of the data, or may have been produced directly following the fieldwork.
thank you!
best wishes,


Updated by Theodora Kokosi about 7 years ago

Hi Gundi,

thank you for your reply. I am looking at this version of data: UKDA-6614-spss w. 1-5. The manual I am also using is 6614_UserManual_Wave1to5_v1.1. For example, the sample size in the main respondents' dataset (b_indresp.sav) is 54,597 whereas in the user guide in p.21 (table 5) it says that it is 53,254 (GB) + 2,840 (NI). Is it something that I am missing? If you need more information, please let me know.

Best wishes,


Updated by Gundi Knies about 7 years ago

  • Status changed from New to Feedback
  • % Done changed from 0 to 90

Thanks for clarifying.
Table 21 reports the response rates, including non-response (household refusal etc.). The indresp data files only include records for individuals who provided an adult interview, a proxy or a telephone interview. to get expected indresp sample sizes you therefore need to look at the first three rows at the top: 50,389+3,870+329=54,585 records.
The wave-specific tables are created when the new wave data are first released and not updated each wave. In this case the difference is 12 cases and it is probably a household/people who were identified as not having been eligible for interview or were found to be duplicates at a later point in time.

Hope this clarifies,


Updated by Victoria Nolan about 7 years ago

  • Status changed from Feedback to Closed
  • % Done changed from 90 to 100
  • Private changed from Yes to No

Also available in: Atom PDF