Support #1950
open
Merging w_hhresp for multiple waves
Added by Jelle De Schoenmaeker over 1 year ago.
Updated about 1 year ago.
Description
Hi, I'm currently trying to merge a couple of waves from w_hhresp into one dataset. I'm using stata to do this but when I use the codes that is provided on the website I tend to find some trouble to merge these waves. The provided file to merge only contains information about w_indresp and uses pidp to merge but this variable is not available in the w_hhresp waves. Is there any way to solve this and make one dataset wtih multiple waves instead of w_hhresp for just one wave? Thanks in advance for the response. Kind regards, Jelle.
- Status changed from New to Feedback
- % Done changed from 0 to 50
- Private changed from Yes to No
Hello Jelle
Households are uniquely identified in each wave by w_hidp, a wave-specific variable with a different prefix for each wave. It can be used to link information about a household from different records within a wave but cannot be used to link information across waves. Since the composition of households can change between waves, the data do not include a longitudinal household identifier. For example, a_hhresp can be linked with a_indresp using a_hidp but not with b_hhresp.
Therefore, you will need to merge first household data with individual data and then you will be able to use pidp to merge different waves. For example, a_hhresp vs. a_indresp and b_hhresp vs. b_indresp using w_hidp and then a_hhresp-indresp vs. b_hhresp-indresp by w_pidp.
I hope this information is helpful.
Best wishes,
Roberto Cavazos
Understanding Society User Support Team
Thanks for the help. I succeeded to merge the datasets and waves. Now i'm a bit struggling with putting the data in the right panel format. I would like to do an analysis of households over over the waves. This means I need to have the households with a certain amount of observations across the waves (years). That way I can see how the variables change for a specific household over the years. I can't really find how to do this, I tried to use xhhrel dataset but I couldn't find it. Is this in any wa possible? Thansk in advance for the response. Kind regards Jelle.
Hello Jelle
How to construct a panel will depend on the research you are doing. Could you provide some insight into the variables you intend to use? As previously noted, the individual serves as the focal point for analysing the information across various waves, rather than the household.
For a clear introduction to using panel data in research, I recommend the book A practical guide to using panel data coauthor by Dr. Alita Nandi, Associate Director, Outreach in UKHLS. Here is the link https://uk.sagepub.com/en-gb/eur/a-practical-guide-to-using-panel-data/book237578
If you are based at a University, you might have free access to the online edition.
Best wishes,
Roberto Cavazos
Understanding Society User Support Team
I intend to use the variables: nkids_dv, nemp_dv, npens_dv, nue_dv, hhsize and xpgasy. I used pidp as identifier but I have some trouble reshaping the dataset into a long format. I think it's because the variables are coded with the prefixes a,b,c,... Is there any easy way to solve this?
Kind regards,
Jelle
Hello Jelle,
I suggest reviewing the syntax located in the "Data management syntax files" section. Pay specific attention to the syntax examples for tasks such as merging individual files across waves into wide format, merging individual files across waves into long format, distributing household level information to the individual level and summarising individual level information at the household level. You can access these examples at the following link: https://www.understandingsociety.ac.uk/documentation/mainstage/syntax
I hope this information is helpful.
Best wishes,
Roberto Cavazos
Understanding Society User Support Team
- Status changed from Feedback to Resolved
- % Done changed from 50 to 100
Also available in: Atom
PDF
Updated by 
Updated by