Project

General

Profile

Support #713

Weighting for longitudinal analysis of USOC waves 2 to 5

Added by Jane Lakey about 7 years ago. Updated about 7 years ago.

Status:
Closed
Priority:
Urgent
Assignee:
Category:
Weights
Start date:
01/31/2017
% Done:

100%


Description

Hi, I just wanted to clarify which weight I should use for a longitudinal analysis of USOC waves 2 to 5 please, in order to specify the inclusion of the BHPS, EMBS and GPS samples in this cohort. Would the best weight be indinub_lw, which becomes available at wave 3 (presumably indscub_lw in analyses which use self-completion data) or should we be using indinus_lw and indscus_lw?
If our analysis using self-completion data in some parts but not others, is it best to always use the self-completion weight, for consistency or better to use the indinub/indinus weight when no self-completion variables are involved?

#1

Updated by Victoria Nolan about 7 years ago

  • Status changed from New to In Progress
  • Assignee changed from Olena Kaminska to Jane Lakey
  • % Done changed from 0 to 10
  • Private changed from Yes to No

Dear Jane,

Many thanks for your query, which has been passed on to the weighting team to look into.

Best wishes, Victoria.

#2

Updated by Peter Lynn about 7 years ago

Jane,

Always use the "ub" weights (not "us") for longitudinal analysis starting at wave 2, otherwise the BHPS samples will get excluded.

Whether sticking with the "sc" weights for consistency is preferable really depends on the nature of your analyses, e.g. how closely related (substantively) are the analyses that use only interview data to the ones that use self-comp too. You should get more precise estimates of the former type if you use the "in" weights.

Peter

#3

Updated by Victoria Nolan about 7 years ago

  • Status changed from In Progress to Feedback
  • % Done changed from 10 to 80
#4

Updated by Victoria Nolan about 7 years ago

  • Status changed from Feedback to Closed
  • % Done changed from 80 to 100

Also available in: Atom PDF