Project

General

Profile

Actions
Copy link

Support #151

closed

Unweighted sample sizes among sub-groups

Added by Chris Martin over 11 years ago. Updated over 11 years ago.

Status:
Closed
Priority:
Normal
Assignee:
Redmine Admin
Category:
Data analysis
Start date:
05/23/2013
% Done:

100%

Description

Hi,

I've doing some basic cross-sectional analysis of Wave 2 individual-level data. I understand that the appropriate weighting variable has zero values.

What's the easiest way of finding the unweighted sample size to report - is it to look at the number of the cases with non-zero values of the weighting value in my sub-group of interest? For example, the unweighted sample size for Adults in Scotland who have done Health, fitness, gym or conditioning activities in the last year (b_sports11) will be....

weight off.
select if (b_country = 3) and (b_indpxus_wx > 0).
fre b_sports11.

Regards,
Chris

Actions
Copy link
 #1

Updated by Redmine Admin over 11 years ago

  • Assignee set to Redmine Admin
  • Target version set to M2
  • % Done changed from 0 to 20

That seems fine. If you look at the sample origin (w_hhorig), you will find that most with zero weights were from BHPS.
Jakob

Actions
Copy link
 #2

Updated by Redmine Admin over 11 years ago

  • Status changed from New to Closed
  • % Done changed from 20 to 100
Actions
Copy link

Also available in: Atom PDF