Understanding Society User Support: Issueshttps://iserredex.essex.ac.uk/support/https://iserredex.essex.ac.uk/support/support/favicon.ico?15995719382024-02-20T14:23:07ZUnderstanding Society User Support
Redmine Support #2056 (Feedback): Which weights to use when combining the mainstage and Covid-19 waves of...https://iserredex.essex.ac.uk/support/issues/20562024-02-20T14:23:07ZJames Laurence
<p>Hi there,</p>
<p>I have been reading through the forum support on weighting when using the Covid-19 data and Mainstage data combined, but I was hoping to just get some clarification on a couple of points.</p>
<p>I am conducting a study which looks at trends over time in adult mental health across UKHLS Mainstage surveys 2, 3, 4, 5, 6, 7, 8 and 9, and the Covid-19 survey 1, 2, 3, 4, 5, 6, 7, 8 (only the web survey). I end at Mainstage survey wave 9 (survey period Jan 2017-May 2019) as that appears to be the last Mainstage wave that doesn’t cover the pandemic period. My data is in long format and I’m using Stata.</p>
<p>However, I am unsure of which weights to use precisely for my aims.</p>
<p>The first thing I would like to do is to treat the data as pooled cross-sectional data to look at how mental health changes over time (between wave 2 of the mainstage and wave 8 of the Covid survey). So, I’d like to see the level of mental health in the UK at each wave of the UKHLS. Ideally, I would like to model all the waves together. Am I right in thinking that to do so I would need to create a new ‘weight’ variable, which is the self-completion cross-sectional weight for each wave? I’ll explain below…</p>
<p>So, for wave 2 of the Mainstage survey, the new ‘weight’ variable would have the value of b_indscub_xw<br />For wave 3 it would have the value of: c_indscub_xw<br />For wave 4 it would have the value of: d_indscub_xw<br />For wave 5 it would have the value of: e_indscub_xw<br />For wave 6, it seems there are two self-completion, cross-sectional weights (_ub and _ui): would it be <br />f_indscub_xw or f_indscui_xw?<br />For wave 7 it would have the value of: g_indscui_xw (as there is no _ub version)<br />For wave 8 it would have the value of: h_indscui_xw (again, as there is no _ub version)<br />For wave 9 it would have the value of: i_indscui_xw (again, as there is no _ub version)</p>
<p>Then, turning to filling in the COVID-19 survey values of the new ‘weight’ variable it would be:<br />For wave 1 of the COVID-19 survey it would have the value of: ca_betaindin_xw <br />For wave 2 of the COVID-19 survey it would have the value of: cb_betaindin_xw <br />…<br />For wave 8 of the COVID-19 survey it would have the value of: ch_betaindin_xw<br />For wave 9 of the COVID-19 survey it would have the value of: ci_betaindin_xw</p>
<p>So, the Stata code would look something like this to give you an idea of what I mean:</p>
<p>gen weight = b_indscub_xw if mainstage_wave==2<br />replace weight = c_indscub_xw if mainstage_wave==3<br />replace weight = d_indscub_xw if mainstage_wave==4<br />…<br />replace weight = i_indscui_xw if mainstage_wave==9<br />replace weight = ca_betaindin_xw fi cv19survey_wave==1<br />…<br />replace weight = ch_betaindin_xw fi cv19survey_wave==8<br />replace weight = ci_betaindin_xw fi cv19survey_wave==9</p>
<p>So, it would be one new ‘weight’ variable, where each wave within each pidp had a weight value which corresponds to the cross-sectional weight for that wave.</p>
<p>- Is that the correct approach to take in to treat the data as repeated cross-section data and look at levels of mental health in each wave? <br />- Am I handling the COVID-19 weights correctly, and can I combine the Mainstage (waves 1-9) and Covid-19 surveys (waves 1-9) in this way?<br />- I’m not sure I fully understand the switch between _ub (waves 1-6 mainstage) and _ui (waves 7-9 mainstage). I can only use _ub up to wave 5 and only _ui from waves 7 to 9. Is it correct to take the approach I’ve outlined above, looking at _ui in some waves and _wub in others? <br />- Also, for wave 6, which self-completion cross-sectional weights should I use? The _ui or _ub?</p>
<p>I hope this makes sense and please do let me know if you require any further clarifications.</p>
<p>Best wishes,</p>
<p>James</p> Support #1914 (In Progress): job title and descriptive information in the covid wavehttps://iserredex.essex.ac.uk/support/issues/19142023-06-06T10:25:52ZShiyu Yuan
<p>To who it may concern,</p>
<p>I am currently using UKHLS covid wave 7,8,9 to conduct research. In the questionnaires, jbsoc variable exists in these three waves, but in the data file, I can only find it in wave 8.</p>
<p>Also, there is no derived industry variable, and I found the question in wave 8 is checking the industry in wave 7 and in wvae 9 is checking either wave 7 and wave8. In this case, can I get the information by firstly derived one industry variable for wave 8 and then another one for wave 9.</p>
<p>The last part is regarding the marriage/cohabitation status. Can I generate a variable based on household relationships? But what if they get married but not living together? According to the way UKHLS suggests finding a partner or spouse, does it mean we can only identify a spouse or partner for couples living together that have the same household address?</p>
<p>Would you mind helping me with this issue, please?</p>
<p>best<br />shiyu</p> Support #1874 (In Progress): Issue with religion variable in wave 12https://iserredex.essex.ac.uk/support/issues/18742023-03-10T11:56:38ZLaurence O'Brien
<p>Hello support forum,</p>
<p>I think there might be an issue with the religion variable (l_oprlg1) in wave 12. I suspect this because nearly all the people who report belonging to both the Bangladeshi and Pakistani ethnic group (l_racel values 10 and 11) have l_oprlg1 = 11, indicating Christian (no specific denomination) religion. This can't be right - in other waves the vast majority of these ethnic groups report being Muslim. There are also some weird patterns for other ethnic groups, but this is the clearest indication of a mistake.</p>
<p>I therefore wonder if there is a coding issue for the values of l_oprlg1. Is this the right place to raise this issue to be looked into?</p>
<p>Many thanks,<br />Laurence</p> Support #1839 (In Progress): Combining individual level files across waves with different variabl...https://iserredex.essex.ac.uk/support/issues/18392023-01-12T14:10:28ZIngrid Storm
<p>I am trying to follow the suggested syntax for appending individual level files across waves into a long format. However I wish to retain some variables that are not available in all the waves.</p>
<p>When I try to use the syntax dofile available on the website (MERGING INDIVIDUAL FILES ACROSS WAVES INTO LONG FORMAT) I get error messages when it encounters variables that are only available in some waves (e.g. "variable a_simrace not found").</p>
<p>I noticed on the moodle course a command called "isvar" was proposed as a solution. However, when I try this I also get an error message, saying that "the command isvar is not recognised" (I am using Stata version 17).</p>
<p>What do you propose?</p>
<p>Thank you very much for your help</p> Support #1673 (In Progress): pensioner_dv seems to be wrong for menhttps://iserredex.essex.ac.uk/support/issues/16732022-03-29T10:29:15ZTom Waters
<p>Hi,</p>
<p>The pensioner_dv variable is supposed to determine whether the respondent is past State Pension Age (SPA). But for men, in wave K, all men aged 64 or younger are defined as not being past SPA, and all men aged 65 or older are. However, men born after 6 December 1953 have a SPA after their 65th birthday (<a class="external" href="https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/310231/spa-timetable.pdf">https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/310231/spa-timetable.pdf</a>)</p>
<p>For women this does not seem to be a problem - at least, there are 65 year old women in wave K for whom the pensioner_dv variable says they are below SPA.</p>
<p>(Though, there are 36 women in wave K who are 60 years old and pensioner_dv indicates that they are past SPA. Presumably that can't be right?)</p> Support #1627 (In Progress): Coding of k_ypfhweve in k_Youthhttps://iserredex.essex.ac.uk/support/issues/16272022-01-10T11:24:40ZAlexandra Turner
<p>Hi,</p>
<p>I have just started looking at the data in Wave K of the youth data file and found that for k_ypfhweve: "During an average week in term time, on how many evenings do you do any homework?" there were 155 cases coded as 9. I was wondering what this code relates to as I cannot find any guidance on how to interpret this data?</p>
<p>Many thanks,<br />Alexandra</p> Support #1604 (Resolved): religiosity variableshttps://iserredex.essex.ac.uk/support/issues/16042021-11-02T15:47:39ZA J
<p>Hi, <br />Can you clarify the key difference between the variable oprlg and the ff_oprlg variable in Wave 2 of the UKHLS? Are they pertaining to responses from different sub-sample participants?</p>
<p>I’m particularly following the BHPS participants through to 2015, and wish to know which religion variables pertain to them and which do not, but as far as I can tell, this is not easy to tell from the documentation. The frequencies of responses are very different for oprlg and ff_oprlg, which makes me think they are responses from different sub-samples, but which ones?</p>
<p>Thanks, <br />A</p> Support #1593 (Resolved): Are the BHPS and UKHLS pidp values unique?https://iserredex.essex.ac.uk/support/issues/15932021-10-13T14:25:49ZA J
<p>Hi,<br />I need to merge CNEF datasets and so cannot use the harmonised BHPS UKHLS dataset. I will, however, use the harmonised dataset to attribute the correct pidp values to the BHPS members.</p>
<p>Can you tell me whether, for every BHPS individual who has a pidp in the harmonised dataset (who will be found using their pid number), are the pidp values distinct from the pidp values for individuals in the UKHLS dataset 2009- onwards?</p> Support #1588 (Resolved): Combining the BHPS and UKHLS CNEF datasetshttps://iserredex.essex.ac.uk/support/issues/15882021-10-07T10:00:09ZA J
<p>Hi,</p>
<p>I'm a new user of the CNEF harmonised datasets, which include the BHPS dataset and the UKHLS from 2009 to 2015. I have read the userguide on the harmonised BHPS UKHLS data, but note that a specific treatment of the CNEF is not found, hence my query.</p>
<p>Since I need to do analyses on the UK sample from 2001-2015, it would be ideal if I could merge the two CNEF datasets to make one dataset. Since the data are already harmonised, I am guessing that this will be straightforward. However, I am not sure if my thinking is correct here or whether there are other issues with the data about which I am not aware. In the absence of a specific help file for merging the CNEF versions of the datasets, can you give some advice about this? Can the two sets be merged?</p> Support #1519 (Resolved): Marital status (marstat_dv) and presence of non-respondent partners (pp...https://iserredex.essex.ac.uk/support/issues/15192021-03-08T09:04:27ZAbigail Dumalus
<p>Hello Alita,</p>
<p>I am wondering if respondents in the indresp file have a marital status (marstat_dv) of being married/civil partner or living as couple and their partners have no ppid/sppid, and livesp_dv=0, can we assume that their partners are non-respondents? I have been checking the indall file for reference but I am still not sure whether this is possible.</p>
<p>Bottom line: How can we know whether their self-reported marital status is correct?</p>
<p>Kind Regards,<br />Abigail</p> Support #1451 (Resolved): Matching household partners to find out who has the higher occupational...https://iserredex.essex.ac.uk/support/issues/14512020-11-23T10:23:53ZAbigail Dumalus
<p>Hello,</p>
<p>Is there a way to use ppid and sppid variables to designate a household's social class? For example, a man who has a middle class job and his partner/spouse has an upper class job... the woman's upper class position would represent an upper class household since they live together. Note that I am referring to current job or most recent job (if current job is missing). Are there other harmonised social class variables based on occupation? Thanks in advance.</p> Support #1394 (Resolved): Follow up on having a “unified” weighting variable for analyzing https://iserredex.essex.ac.uk/support/issues/13942020-08-11T11:46:00ZAbigail DumalusSupport #1380 (Resolved): Calendar month analysis [item 11, weighting FAQ] not making sense to re...https://iserredex.essex.ac.uk/support/issues/13802020-07-16T15:34:09ZAbigail Dumalus
<p>Hello Alita,</p>
<p>I tried following item 11 for doing January 2014 as an example. When I filtered interviews from wave 5, sample month 1 (if wave==22 & month==1) using the data editor on Stata, istrtdaty indicated 2013, istrtdatm ranged from 1 to 6. I am confused why interviews that started in 2013 have to be added under “January 2014” monthly average. Am I doing the filtering in a completely wrong way? It would be helpful if an illustration of January 2014 can be provided, along with the appropriate weighting variable for this month. In order for me to generate 3-month rolling averages/variances, I would need to “create” a period variable that would uniquely identify each pidp within a wave period but in terms of calendar months or years. The command I am trying to do is rangestat on Stata:</p>
<p>rangestat (mean) monthmean_lfsat_3ma = monthmean_lfsat, by(panel_id) interval(panel_month -2 0) —> 3-month moving average of life satisfaction</p> Support #1350 (Resolved): GCSE grade datahttps://iserredex.essex.ac.uk/support/issues/13502020-05-19T18:12:28ZAbigail Batemanabi.batemanx@gmail.com
<p>Hi,</p>
<p>I need some help with my analysis for my undergrad dissertation</p>
<p>I am using the Harmonised BHPS data and my dissertation question revolves around looking at the GCSE grades (English and Maths most likely) of people, based on their socioeconomic class. I will then be looking at if material and cultural factors such as having a computer at home, going to places like the museum, extracurricular activities and having books at home etc. have an affect on the GCSE grades of those from lower socioeconomic classes.</p>
<p>The problems I am having at the moment are:</p>
<p>- I've tried to analyse data from waves 7,8,9 using the variable gcseeng in the indresp datafile. However the response rate is extremely low:<br />e.g. for wave 9: 34,900 cases are 'inapplicable', 1096 are 'proxy', only 8 responses for 'A*' etc.<br />- So even with waves 7,8,9 combined the numbers are too low to use this as my dependent variable</p>
<p>- There aren't variables with respondent's GCSE grades (or equivalent) in older waves. There are variables in a few older BH waves that include respondent's number of GCSE qualifications A-C etc.<br />The problem is that I need to choose either/or - I cannot see a variable for number of GCSE grades in recent waves, and I cannot see specific English and Maths grades attained in older waves - so this means I am unable a the moment to merge the data from different waves together</p>
<p>- This will then prove to be a problem when trying to look at GCSE grade attained in relation to factors such as frequency of visiting a museum</p>
<p>Any help would be very very appreciated</p>
<p>Thanks</p> Support #1242 (Resolved): Data inquiry - BHPS - Month of birth of first child.https://iserredex.essex.ac.uk/support/issues/12422019-09-10T14:24:41ZAnonymous
<p>To whom it may correspond,</p>
<p>My name is Barbara Boggiano and I am a PhD candidate in Economics at the University of Leicester. I am contacting you because I was granted a One Year Research Grant by the DAAD to work on a project using BHPS data at ZEW Mannheim (as a visiting researcher) starting in October 2019.</p>
<p>Our project tries to examine whether seasonality in working hours within the calendar year affects seasonality in fertility, potentially causing delays in fertility. Given the nature of the project, I am looking for data on the month of birth of the first child. This information is the only piece of information we require that it is not available in the publicly available sample and I was wondering about the procedure to be able to get this information.</p>
<p>Do not hesitate to contact me with any questions or concerns. <br />Thank you in advance for your time. <br />Best regards,</p>
<p>Barbara Boggiano<br />PhD Student and Graduate Teaching Assistant<br />Economics Division, School of Business<br />University of Leicester, UK<br />Contact: <a class="email" href="mailto:bb203@leicester.ac.uk">bb203@leicester.ac.uk</a></p>