Support #1441: Reasons for migration - w6 and w7 - Understanding Society User Support

Actions

Copy link

Support #1441

open

Reasons for migration - w6 and w7

Added by Ilona Pinter about 4 years ago. Updated almost 4 years ago.

Status:

Resolved

Priority:

Normal

Assignee:

Category:

Start date:

11/16/2020

% Done:

100%

Description

Hi there,

I'm interested in the question on reasons for migration asked in wave 6 (migrationhistory_iemb1.mreason) and 7 (migrationhistory_w7.mreason).

Firstly in w6 it looks like this question was only asked of the IEMB sample. Who was asked this question in w7? i.e. was this asked of the whole sample or just the IEMB boost sample? My understanding was that the boost sample was only done in wave 6.

Secondly, I've merged the 2 waves using the pidp and in looking at positive responses to mreason6 I've identified 373 respondents altogether who have answered yes to mreason6 in at least one wave; 292 answered yes in both waves; 25 respondents in wave 7 only and 56 in wave 6 only. Is that correct?

I'm wondering why some respondents have a response under both waves: were they asked the question both times or was their answer in wave 7 carried through from w6?

Hope that's clear.
Many thanks,
Ilona

Actions

Copy link

Updated by Alita Nandi about 4 years ago

Status changed from New to In Progress
Assignee set to Alita Nandi
% Done changed from 0 to 10

Many thanks for your enquiry. The Understanding Society team is looking into it and we will get back to you as soon as we can.
Best wishes,
Understanding Society User Support Team

Actions

Copy link

Updated by Alita Nandi about 4 years ago

Private changed from Yes to No

Actions

Copy link

Updated by Alita Nandi about 4 years ago

Assignee changed from Alita Nandi to Ilona Pinter
% Done changed from 10 to 80

Hello Ilona,

In Wave 6, only IEMB sample members not born in the UK were asked this question. In Wave 7, those who were born outside the UK but not part of the IEMB sample were asked this question. There should be no overlap, but in a handful of cases this may happen if the fed forward information used to identify the eligible persons was not correct.

I compared f_mreason6 g_mreason6 and could only find 3 persons who answered the question in both waves and only 1 who responded yes to both waves. Could you please check your syntax again? This is the Stata syntax I used:

use pidp f_mreason6 using f_indresp, clear
merge 1:1 pidp using g_indresp, keepusing(g_mreason6)
ta f_mreason6 g_mreason6

Best wishes,
Understanding Society User Support Team

Actions

Copy link

Updated by Ilona Pinter about 4 years ago

File clipboard-202011301034-8sdrz.png added

Hi Alita,

Thanks for this and sorry for the delayed response. Thanks for clarifying the samples that this question was asked of in waves 6 and 7. That's really helpful!

Re the merged data, I checked the syntax and ran yours as well. I think the only difference in mine was that I wasn't using 'keepusing(g_reason6)' but the rest seems to be the same.

Running your commands, I can see where you get the 1 and 3 from and that makes sense, and overall it does look like there were 292 respondents which had a positive answer to this question in either of the waves based on the individuals that were matched from the two datasets in the merge. But presumably the 'tab' command wouldn't include the individual cases which appear only in one wave? When I tabulated the merge variable with the mreason6 variables it still shows that there were 25 individuals who responded positively in wave 7 only and 56 in wave 6 only, along with the 292 whose record was matched in both waves (giving a total of 373 respondents in total).

Sorry I hope this makes sense. If not, can I send you my tabulated results somehow to verify?

Thanks for your help!
Ilona

Alita Nandi wrote in #note-3:

Hello Ilona,

In Wave 6, only IEMB sample members not born in the UK were asked this question. In Wave 7, those who were born outside the UK but not part of the IEMB sample were asked this question. There should be no overlap, but in a handful of cases this may happen if the fed forward information used to identify the eligible persons was not correct.

I compared f_mreason6 g_mreason6 and could only find 3 persons who answered the question in both waves and only 1 who responded yes to both waves. Could you please check your syntax again? This is the Stata syntax I used:

use pidp f_mreason6 using f_indresp, clear
merge 1:1 pidp using g_indresp, keepusing(g_mreason6)
ta f_mreason6 g_mreason6

Best wishes,
Understanding Society User Support Team