Support #2288
open
comparing two single years using Understanding Society
50%
Description
My name is Raffaele Ciula,
some time ago, I asked if I could extract the year 2016 and 2019 from the dataset Understanding Society to compare individual wellbeing of these two years, this was your answer:
"To make yearly comparisons, you’ll need to combine data from two waves. For example, to construct estimates for the year 2019, you should use data from Year 2 of Wave 10 and Year 1 of Wave 11."
and this was your answer:
"UKHLS has calendar year data available for 2020 to 2022, and the 2023 data will be released in the coming months.You can find more details in the “Data Releases” section on the Understanding Society website:https://www.understandingsociety.ac.uk/documentation/data-releases
I also recommend reviewing the User Guide, here’s the latest version:https://doc.ukdataservice.ac.uk/doc/9333/mrdoc/pdf/9333_main_survey_calendar_year_user_guide_2022.pdfIn particular, please refer to Section 3 (Data structure) and Section 4 (Analysis guidance).
You can follow similar steps to create calendar year datasets for earlier years. However, it is important to follow the guidance I mentioned in my previous message regarding weights and sample representativeness.
"
As far as I understood, UKHLS researchers created a procedure to extract single years from 3-year waves. Referring to the year 2022, the researchers created files and variables lmn_xxxx, I read the document you suggested me and I did not understand how to create those variables and files, and how to extract the year 2016 from wave9 and wave10. Are you planning to extract single years from each past wave of UKHLS in the future? I would like to ask you if you can extract the single years 2016 and 2019 for me, I am willing to pay some money if you would like to do that. If you can do this, how much would it be?
If you are not allowed to extract single years from past waves, which waves would be more suitable to compare years 2016 and 2019? Thanks for your help;
Best Regards,
Raffaele Ciula
Updated by Understanding Society User Support Team about 13 hours ago
- Category set to Data documentation
- Status changed from New to Feedback
- % Done changed from 0 to 50
- Private changed from Yes to No
Hello Raffaele,
Access to the data is free of charge as long as you meet the conditions described by the UK Data Service (UKDS). Understanding Society (UKHLS) does not carry out ad hoc data processing, as there is no dedicated staff for that purpose.
The survey sample is collected over two calendar years, and fieldwork usually extends into the first three months of the third year. This happens because some respondents complete their interviews later, so the data collection period overlaps with the next year. Therefore, if you want to compare calendar years, you need to take this overlap between consecutive surveys into account. You would also need to make the necessary adjustments for unequal selection probabilities.
Alternatively, you can use the sample month variable (w_month) to select the years you want to analyse, which helps avoid issues with late respondents. An example of the small adjustments needed can be found in the section “Running analysis on a calendar year or month” at:
https://www.understandingsociety.ac.uk/documentation/mainstage/user-guides/main-survey-user-guide/how-to-use-weights-analysis-guidance-for-weights-psu-strata/
Another option is to compare across waves. For example, 2016 is covered in Wave 7 (year 2) and Wave 8 (year 1), while 2019 is covered in Wave 10 (year 2) and Wave 11 (year 1). Which waves to use will depend on what exactly you want to compare, for instance, you could check the sample size of the variable of interest and decide accordingly.
For more information about the study timeline, please see the “Survey timeline” section at:
https://www.understandingsociety.ac.uk/documentation/mainstage/survey-timeline/
At the moment, there are no plans to produce calendar-year datasets for years prior to 2020.
I hope this information is helpful.
Best wishes,
Roberto Cavazos
Understanding Society User Support Team