Project

General

Profile

Actions

Support #1973

open

Family matrix

Added by Alvertos Konstantinis about 1 year ago. Updated 10 months ago.

Status:
Resolved
Priority:
Normal
Assignee:
-
Category:
Data management
Start date:
09/13/2023
% Done:

100%


Description

Dear all,

My name is Alvertos Konstantinis, and I am a PhD researcher at the University of Groningen, Faculty of Spatial Sciences, Department of Economic Geography. My PhD thesis is about Precarious employment and wellbeing in the UK. In that regard, one of my research questions is the hypothesis that precarity affects social mobility. Consequently, I recently discovered the family matrix you published for the BHPS-UKHLS. Could you help me with the following issue: I run my analysis on Stata. In its current form, I indicate whether or not people living under the same roof as you are precarious employees and how this affects you. Ideally, I would like to recognize the relationship within this household (are they friends, family, just roommates), etc. Please give some tips on that issue. Thank you so much in advance for your help :)

Kind regards,
Alvertos


Files

Worksheet ex 8 Stata.pdf (210 KB) Worksheet ex 8 Stata.pdf Understanding Society User Support Team, 09/13/2023 01:36 PM
Actions #1

Updated by Understanding Society User Support Team about 1 year ago

Dear Alvertos,

Have you considered using the w_relationship_dv variable available in w_egoalt files? https://www.understandingsociety.ac.uk/documentation/mainstage/dataset-documentation/variable/relationship_dv In the egoalt file each row identifies the relationship between the person of reference (called ego) and one other member in the same household (called alter). The file includes all possible combinations for each households. You can link a egoalt file to other data files using pidp or a combination of w_hidp and w_pno. For further details about the egoalt file please check the attached file.

I hope this helps.

Best wishes,
Piotr Marzec,
UKHLS User Support

Actions #2

Updated by Alvertos Konstantinis about 1 year ago

Dear Piotr,

Thank you very much for your reply. It is very informative indeed. I have checked the egoalt files but I am struggling with the stata syntax part because the merge needs to be 1:m; Each individual have multiple entries in the egoal file (normal). After the merging tho with the "indersp" file how should we treat it? Thank you very much again for your time

Best,
Alvertos

Actions #3

Updated by Understanding Society User Support Team about 1 year ago

Hello Alvertos,

The approach you should take depends on the specific analysis you intend to conduct. However, assuming you want to maintain unique observations by row, particularly when working with "indresp," you'll need to reshape your dataset into a wide format to create distinct variables for all potential relationships. While there are several methods to accomplish this, I'll outline the following steps:
1. Begin by merging "indresp" and "egolat" using a one-to-many (1:m) merge, retaining only the "egolat" variables.
2. Reshape the dataset into a wide format, generating new variables for different relationship types.
3. Finally, perform another merge to reintegrate all "indresp" variables into your dataset.

This process should help you achieve your desired dataset structure.

I hope this information is helpful.

Best wishes,
Roberto Cavazos
Understanding Society User Support Team

Actions #4

Updated by Understanding Society User Support Team 10 months ago

  • Status changed from Feedback to Resolved
  • % Done changed from 80 to 100
Actions

Also available in: Atom PDF