Project

General

Profile

Support #1921

Non-Covid affected data

Added by Pauline Bucher 11 months ago. Updated 5 months ago.

Status:
Resolved
Priority:
Normal
Category:
Data releases
Start date:
06/10/2023
% Done:

100%


Description

Hi team,

If I want the most recent data unaffected by Covid, what wave should I use? I started using 2019-2020 but realised that some respondents may have answered after March 2019 (is that correct?)...What wave should I use (where no respondents would have answered AFTER/DURING March 2020)?

#1

Updated by Understanding Society User Support Team 11 months ago

  • Status changed from New to In Progress
  • % Done changed from 0 to 70
  • Private changed from Yes to No

Hi,

In wave 10 there 145 respondents (j_indresp, count if j_ienddaty==2020 & j_ienddatm>=3) who completed their interview in March 2020 or later. So, you can use wave 9 or exclude these 145 cases. I will check with my colleague if doing the latter would require any changes to weights and get back to you.

Best wishes,
Piotr
UKHLS User Support

#2

Updated by Pauline Bucher 11 months ago

I am actually confused about the weights?

What is wrong/what happens if I use for example Wave 11's data only without any weights?

#3

Updated by Understanding Society User Support Team 11 months ago

  • Status changed from In Progress to Feedback

When you don't weight our data your estimates will be biased in certain ways, please see the weighting section of the user guide for details: https://www.understandingsociety.ac.uk/documentation/mainstage/user-guides/main-survey-user-guide/why-use-weights
We always recommend to use an appropriate weight and take into account clustering (psu variable) and stratification (strata variable) of the sample, you can do that using svy suite in Stata. Due to the fieldwork design, excluding respondents from certain sample months might affect the sample representativeness, please see https://www.understandingsociety.ac.uk/documentation/mainstage/user-guides/main-survey-user-guide/how-to-use-weights-analysis-guidance-for-weights-psu-strata However, in this case, excluding these 145 case should have only a negligible effect, so you don't need to worry about this.

Best wishes,
Piotr
UKHLS User Support

#4

Updated by Understanding Society User Support Team 5 months ago

  • Status changed from Feedback to Resolved
  • % Done changed from 70 to 100

Also available in: Atom PDF