Understanding Society User Support: Issueshttps://iserredex.essex.ac.uk/support/https://iserredex.essex.ac.uk/support/support/favicon.ico?15995719382024-03-13T15:36:15ZUnderstanding Society User Support
Redmine Support #2075 (In Progress): Using UKHLS to look at trends across calendar months https://iserredex.essex.ac.uk/support/issues/20752024-03-13T15:36:15ZJames Laurence
<p>Hi there,</p>
<p>I am interested in looking at calendar month trends in whether someone wants to move home or not (which is available in every wave): lkmove. Ideally, I would like to look at trends using all waves (1-13). However, if it is easier to look at trends from some other start point, e.g.. 2016 or 2017, then I am flexible. I am also flexible as to whether the BHPS sample is included or not. This will be cross-sectional analysis, so I hope to treat each calendar month as a cross-section (I won’t be doing any longitudinal analysis).</p>
<p>I have been reading the helpful notes on ‘Running analysis on a calendar year or month’ (<a class="external" href="https://www.understandingsociety.ac.uk/documentation/mainstage/user-guides/main-survey-user-guide/how-to-use-weights-analysis-guidance-for-weights-psu-strata/">https://www.understandingsociety.ac.uk/documentation/mainstage/user-guides/main-survey-user-guide/how-to-use-weights-analysis-guidance-for-weights-psu-strata/</a>). However, I just had some questions and was hoping to see if where I’d got to so far looked right.</p>
<p>I have been using the w_month and wave variables to generate a new date variable of year-month. To capture calendar year, I have used the wave and w_month variables in the following manner:</p>
<p>gen year = 2009 if wave==1 & (month>0 & month<13)<br />replace year = 2010 if wave==1 & (month>12 & month<25)<br />replace year = 2010 if wave==2 & (month>0 & month<13)<br />replace year = 2011 if wave==2 & (month>12 & month<25)<br />replace year = 2011 if wave==3 & (month>0 & month<13)<br />…<br />replace year = 2021 if wave==13 & (month>0 & month<13)<br />replace year = 2022 if wave==13 & (month>12 & month<25)</p>
<p>To measure calendar month, I have recoded the w_month variable, combining the two monthly measures into one. So, in the w_month variable, it tells us whether someone was sampled in January in the year 1 sample or January in the year 2 sample. I’ve now combined these into a single category of whether someone was sampled in January. For example, ‘jan yr1’ and jan yr2’ are now just ‘jan’; ‘feb yr1’ and ‘feb yr2’ are now just ‘feb, etc.</p>
<p>With these new calendar year and calendar month variables, I have now created a new measure of calendar year-month, which looks like this (I hope this is correct so far):</p>
<pre><code>2009 Jan = 1<br /> 2009 Feb = 2<br /> 2009 Mar = 3<br /> 2009 Apr = 4<br /> 2009 May = 5<br /> 2009 June = 6<br /> 2009 July = 7<br />…<br /> 2022 June = 162<br /> 2022 July = 163<br /> 2022 Aug = 164<br /> 2022 Sep = 165<br /> 2022 Oct = 166<br /> 2022 Nov = 167<br /> 2022 Nov = 168</code></pre>
<p>I understand that whatever weight I choose to use I need to correct it due to Northern Ireland only being sampled in issue month 1-12 (and not 13-24). Therefore, I will apply the following adjustment to the weight (gen adj=1, replace adj=0.5 if w_country==4, gen weight=w_xxxyyus_lw*adj 8) as outlined in the online notes.</p>
<p>However, where I’ve become a little lost is what weights to initially use. In the notes, it states due to exceptions in sample selection ‘we recommend use of the us_lw weight in analysis’. Given my intention to look at calendar months up to wave 13, does this mean I should use the m_indpxus_lw weight? Is this the case, even if I just want to look at the data cross-sectionally (treat every calendar month as a cross-sectional picture of lkmove)? Because it seems that if I use m_indpxus_lw then it substantially reduces the sample size (due to these longitudinal weights requiring someone to have participated in every wave). Is it possible to use the cross-sectional weights for my aims, while excluding the BHPS and IEMB, as is suggested that one needs to do for this kind of calendar month analysis in the online notes? Or, do I need to use longitudinal weights for my intended analysis?</p>
<p>I was also just trying to get my head around the issue of scaling discussed in the online notes: ‘The weights provided are not designed directly for pooling data across waves as they are scaled to a mean value of 1.0 within each wave, and therefore produce different weighted sample sizes in each wave’, under the section ‘Pooling data from different waves for cross-sectional analysis.’ Firstly, I just wanted to confirm this applies to my case of doing monthly trends?</p>
<p>And secondly, if so, from what I can see, the syntax kindly provided is intended to produce an accurate weight to look at the variable jbstat for the calendar year 2011, using months 13-24 of wave 2 and 1-12 of wave 3. At the end, we get the weight variable weight2011, to use for weighting calendar year 2011. In my situation, I would like to do a longer running trend of values of lkmove by months. Would I need to create these weights for each calendar year I look at? So, for 2014, I would need to create a new cross-sectional weight using e_indpxub_xw and f_indpxub_xw (waves 5 and 6). For 2015, I would need to create a new cross-sectional weight using f_indpxub_xw and g_indpxub_xw (waves 6 and 7). For 2016, I would need to create a new cross-sectional weight using g_indpxub_xw and h_indpxub_xw (waves 7 and 8). And to follow this all the way to my last calendar year. Then, to look at monthly trends, treating the data as pooled cross-sectional, I would have my data in long-format and have a new weight variable made up of all these new calendar year weights I’ve created?</p>
<p>I was also wondering if it would be possible to include monthly lkmove data from the calendar year 2022 (using wave 13 of the UKHLS mainstage). As I understand things, previous calendar years (e.g., 2018) are composed of samples from two waves (waves 9 and 10 of the mainstage). However, for the calendar year of 2022, it is only composed of the sample from wave 13. Is it still possible to look at calendar month trends in lkmove for 2022? If so, would I need to make other sample restrictions to the other calendar years, for example, drop the IEMB sample from the trends? And would I need to make other adjustments to the weights? Or, is it not possible yet to look at monthly trends until wave 14 comes out)? I think from the online notes this is mentioned: ‘The analysis sample is only representative when all 24 monthly samples are combined in equal measure.’ Does this point refer to my question?</p>
<p>I am also interested in potentially looking at quarterly trends (Jan-Mar, Apr-Jun, etc.), instead of monthly trends (using the x_quarter variable). To do so, can I take the same approach as above? So, create a new time variable which is years divided into quarters (e.g., 2013 Jan-Mar, 2013 Apr-Jun, 2013 July-Sep, 2013 Oct-Dec, 2014 Jan-Mar, 2014 Apr-June…2022 Jul-Sep, 2022 Oct-Dec). Do I need to do anything different with the weights?</p>
<p>I hope this all makes sense.</p>
<p>Thanks so much in advance.</p>
<p>James</p> Support #1942 (In Progress): Bornuk_dv missing datahttps://iserredex.essex.ac.uk/support/issues/19422023-07-19T13:19:05ZLuis Ortiz
<p>Dear colleagues,</p>
<p>I have observed that the derived variable "Born in UK" reports a substantial number (8.61% of observations, if I'm not wrong) of 'missing values'. The other two values are obviously 'born in UK' and 'not born in UK'. Is there any specific reason / pattern explaining these missing values.</p>
<p>Many thanks for your attention</p>
<p>And best wishes</p>
<p>Luis Ortiz Gervasi</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 #1890 (In Progress): Extracting PSU and Individual-Level Weights for a Multilevel Modelhttps://iserredex.essex.ac.uk/support/issues/18902023-04-11T16:35:50ZLaurence Rowley-Abel
<p>Dear Understanding Society team,<br />I am running a multilevel model using individuals nested within census areas (LSOAs) in Waves 9, 10, 11 and 12. To account for clustering I am using the following levels in my multilevel model: individuals at the first level, PSUs at the second level and LSOAs at the third level. Therefore, from the provided weights, I need to extract separate weights for individuals and for PSUs. Having read your response here [[<a class="external" href="https://iserredex.essex.ac.uk/support/issues/1572">https://iserredex.essex.ac.uk/support/issues/1572</a>]], I am wondering if the below would be the correct approach:</p>
<p>- For the individual level, I would divide l_psnenus_xw by a_psnenus_xd (from the l_indall.dta and the a_indall.dta files respectively)<br />- For the PSU level, I would use a_psnenus_xd (from the a_indall.dta file)<br />- For the LSOA level, I would not be able to calculate a weight as it is not part of the sampling design. I would set this weight to 1 for all respondents.</p>
<p>Would this be correct? Additionally, would this mean I could only include respondents who were included at Wave 1, since I need to use the design weight (a_psnenus_xd) from Wave 1?</p>
<p>Many thanks for your help.</p>
<p>Best wishes,<br />Laurence</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 #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 #1490 (In Progress): Top-coding of net incomehttps://iserredex.essex.ac.uk/support/issues/14902021-01-24T12:22:44ZLeilah Plant-Tchenguiz
<p>Hi, how would I find out if observations of the following variables have been top-coded?:<br />fimnnet_dv<br />fimnmisc_dv<br />fimnprben_dv<br />fimninvnet_dv<br />fimnpen_dv<br />fimnsben_dv</p>
<p>I have read the documentation but can't seem to find information specifically on the top-coding of these variables.</p> Support #1279 (In Progress): Wave 9 chmain filehttps://iserredex.essex.ac.uk/support/issues/12792019-11-21T15:20:53ZCharlotte Edneyc.edney@lancaster.ac.uk
<p>Hi,</p>
<p>I've just downloaded wave 9 of Understanding Society to add another wave of child maintenance data (chmain file) to my analysis.<br />I was quite surprised that there are only 456 entries in the i_chmain file, compared with over 3,000 in waves 3, 5 and 7. <br />Do you know why there are so few entries in this wave? <br />I noticed in the questionnaire documentation something written about a script error for some of the variables in the file and am wondering if this has anything to do with it?</p>
<p>Best,<br />Charlotte</p> Support #1258 (In Progress): Housing costs in BHPShttps://iserredex.essex.ac.uk/support/issues/12582019-10-09T13:17:22ZLindsay Judge
<p>I am keen to create an after housing costs in BHPS but am unclear what is included in the variable xphsg (gross monthly housing costs). I would like to know whether this (i) includes or excludes housing benefit and (ii) includes or excludes the principal payment for those with mortgages. If the principal is included, is there a way to deduct this from xphsg (i.e. a way to split mortgage payments into interest and principal)?</p>
<p>Thanks in advance for any help.</p> Support #1250 (In Progress): Identifying transitions from households to institutions (older adults)https://iserredex.essex.ac.uk/support/issues/12502019-09-30T15:18:13ZTom Snell
<p>I am trying to identify transitions from households to institutions among older people aged 65+ (ideally residential or nursing homes, but otherwise any institutional setting). I'm hoping to identify all respondents known to have moved to an institution, rather than just those that are successfully followed up (<strong>w_dweltyp</strong> and <strong>w_preason</strong> provide a handful of institutional/proxy interviews).</p>
<p>Any advice on other variables to investigate would be gratefully received!</p> Support #1246 (In Progress): Evermar https://iserredex.essex.ac.uk/support/issues/12462019-09-24T09:55:26ZLydia Palumbolvpalu@utu.fi
<p>Hi,</p>
<p>I am interested in understanding what the value = 0 for the variables lmar1y lmar1m means.</p>
<p>It is associated to a value 1 of the variable evermar, but I cannot understand if it refers to a marriage <br />that actually took place (or it is missing) and if it occurred before the entry into the panel.</p>
<p>Thank you and best wishes,<br />Lydia</p> Support #1227 (In Progress): Family sizehttps://iserredex.essex.ac.uk/support/issues/12272019-08-13T10:38:53ZElla Moonan-Howard
<p>To whom it may concern,</p>
<p>I am attempting to generate non-household family size variables for both waves three and six.</p>
<p>I wanted to clarify which variables denote which type of non-residential family member across the waves. In the family life module webpage nrels3 is number of children, nrels4 is number of brothers and sisters, nrels5 is number of grandchildren and nrels6 is number of grandparents - with nrels7 and nrels8 on great grandparents and great grandchildren only being measured at wave 7.</p>
<p>Yet on the details for these variables in wave three, it appears to be different suggesting that in fact, nrels2 is siblings, nrels3 is grandchildren, nrels6 is great grandparents etc.</p>
<p>If you could let me know which is correct, that would be brilliant. Moreover, in either scenario there are types of family member not accounted for in wave three. In the former it is great grandchildren and great grandparents, in the latter it is children. If you could advise me as to potential other variables I could use to account for these gaps that would be incredibly helpful.</p>
<p>thank you</p>
<p>Ella</p> Support #1167 (In Progress): Linking Understanding Society and HESA data https://iserredex.essex.ac.uk/support/issues/11672019-03-21T10:13:19ZInga Steinberg
<p>Hi,</p>
<p>Could you please let me know what the predicted date of completion of the linking of Understanding Society and HESA data is? I am currently writing a proposal for my PhD (I'm in my first year), and want to know if I will be able to use the data for at least one of my papers.</p>
<p>Best wishes,</p>
<p>Inga</p> Support #1111 (In Progress): Data discepancy? Tenure_dv and movdir / plnewhttps://iserredex.essex.ac.uk/support/issues/11112018-12-04T14:37:24ZChris Foye
<p>Hi,</p>
<p>I want to examine the effect of moving from the private rental tenure (PRS) to the social rental sector (SRS) on a range of social outcomes, using the BHPS and USoc. These tenures are generally understood to be physically discrete: to transition from the PRS to the SRS you have to move house. However, my analysis of BHPS/USoc suggests that almost half of those indivduals who (apparently) move from the PRS to the SRS do not (apparently) move house. This does not seem right. Some more details....</p>
<p>To identify individuals who have moved from PRS to SRS (in that direction) I look at I) "tenure_dv" and ii) tenure_dv lagged by one year (l.tenure_dv). If an individuals current tenure is SRS, and their lag tenure is PRS, then I consider them a "new srs tenant"</p>
<p>To identify whether an individual moved house or not, I use 'plnew' for the BHPS and 'movdir' for USoc. If an individual's response is 'yes' ('no) to 'plnew' then I consider them to have (not) moved house. If an individual's response to 'movdir' is 'moved direct' or 'multiple moves' then I consider them to have moved house.</p>
<p>In theory, "new srs tenants" should overwhelmingly have moved house in the previous year. But I am finding that approx' half of "new srs tenants" did not actually report moving house (based on the coding above).</p>
<p>There seem to be four possible explanations for the finding above: I) there is something wrong with my analysis, ii) contrary common knowledge, changing from PRS to SRS does not generally involve moving house (this seems v. unlikely) iii) there is an error with/misreporting of the 'tenure' variable, iv) there is an error with/misreporting of the 'movdir'/'plnew' variable</p>
<p>I'd appreciate your help.</p>
<p>Chris</p>