Understanding Society User Support: Issueshttps://iserredex.essex.ac.uk/support/https://iserredex.essex.ac.uk/support/support/favicon.ico?15995719382012-06-19T15:08:52ZUnderstanding Society User Support
Redmine Support #66 (Closed): Weights - Longitudinal BHPShttps://iserredex.essex.ac.uk/support/issues/662012-06-19T15:08:52ZDavid Baylissdavid.bayliss-2@postgrad.manchester.ac.uk
<p>Dear support team,</p>
<p>I was intending on using the BHPS sub-sample in wave 2 as the final wave of a longitudinal study along with data from wave 15-18 of the BHPS. Are weights available that will allow me to use the BHPS sub-sample in wave 2 in this way (I was looking for something along the lines of ‘b_indscbh_lw’ following the documentation, but I cannot find it), given that weights for the final wave of the study are required?</p>
<p>Kind regards,<br />David</p> Support #64 (Closed): weighting youth datahttps://iserredex.essex.ac.uk/support/issues/642012-06-13T13:26:41ZKareena McAloneykareena.mcaloney@york.ac.uk
<p>I have a quick query regarding the analysis of the UKHLS data - I have been running analysis using the sample weightings provided in the dataset, but have received a query over whether I also need to include variables to account for clustering, and stratification in the sample. Do the sample weightings provided account for these factors, or do they need to be taken account of separately? (I am running an analysis of the youth self-completion data.</p> Support #62 (Closed): Questionnaire content - Olympicshttps://iserredex.essex.ac.uk/support/issues/622012-06-08T16:22:14ZAlison Stoutalison.stout@scotland.gsi.gov.uk
<p>Are there are plans to use Understanding Society to assess what the legacy of the Olympics (e.g. on physical activity, sports participation, cultural engagement) has been? I understand from Peter Lynn that there are questions related to the Olympics in the wave 4 questionnaire.</p> Support #59 (Closed): Linking BHPS - Understanding Societyhttps://iserredex.essex.ac.uk/support/issues/592012-05-30T13:46:19ZMelanie Luhrmannm.luhrmann@ifs.org.uk
<p>I am using BHPs data and wish to link it a) to the BHPS sample households in Understanding Society, and b) use a pooled sample of BHPS and Understanding Society data as a repeated cross-section of households.</p>
<p>May I ask two questions about this?</p>
<p>1. Is there any documentation that allows me to easily check whether a BHPS variable is available in Understanding Society as well and to find out what the corresponding variable name in US is?<br />2. I am trying to link some information about mothers (from indresp) to their children (birthweight, date of birth...). I am having a hard time getting the kids data together because part of it seems to be located in nat_child and part in child. Is this correct?<br />3. With which identifiers do I merge data on mothers with their kids?</p>
<p>Thank you very much for your help.</p>
<p>Best,<br />Melanie</p> Support #58 (Closed): Youth Wave 1 datahttps://iserredex.essex.ac.uk/support/issues/582012-05-30T08:21:26ZAlicia Heptinstallalicia.heptinstall@education.gsi.gov.uk
<p>Hello. I have downloaded the Wave 1 youth dataset and have 4,899 individuals. This total does not marry up with the figures I received for Youth responses at a recent RSS USoc event, so I just wondered exactly who were included in the W1 Youth module e.g. does it include the innovation panel? the EM boost? etc.<br />Many thanks for any help that can be provided.</p> Support #57 (Closed): urban rural coding issuehttps://iserredex.essex.ac.uk/support/issues/572012-05-29T09:49:08ZIAN ALCOCKi.alcock@exeter.ac.uk
<p>I am trying to continue analyses I have carried out with the 18 waves of BHPS with the inclusion of the BHPS incorporation sample in US w2. A key variable is urbanity. The urban/rural variable for all bhps (England and Wales) URINDEW is availble under conditional access (SN 6032) rather than being in the main release, whereas there is a variable available directly in the US main release 6614, b_urindew_dv. So, I want to extend analyses of outcomes in relation to urbanity using the bhps incorporation cases in SN 6614. The problem: the variable b_urindew_dv is coded differently from the bhps variable urindew. Urindew is comprised of 8 categories: 1 and 5 are urban (>=50% of LSOA population in settlement of >=10,000, 1 with sparsely populated surrounding area and 5 less sparsely populated); 2 and 6 are town and fringe; 3 and 7 village; 4 and 8 hamlet - again distinguished by nature of surrounding area. BUT!!! b_urindew_dv is coded 1=urban and 2=rural - I guess, though this is not made clear, that 1 and 5 are collapsed to urban, and 2-4,6-8 are collapsed to rural. It is clear from the codebook that the intention is to code the variable exactly as it is coded for bhps, see <a class="external" href="https://www.understandingsociety.ac.uk/documentation/mainstage/dataset-documentation/wave/1/datafile/a_indresp/variable/a_urindew_dv">https://www.understandingsociety.ac.uk/documentation/mainstage/dataset-documentation/wave/1/datafile/a_indresp/variable/a_urindew_dv</a> but this has not been done for wave one either, as a_urindew_dv is also binary. It appears that the data depositor has deposited the variable in a collapsed form, contra the codebook. I need the 8 part coding for my work - I need to distinguish 1/5 from 3/4/7/8 and remove the cases that are neither strongly urban nor strongly rural. Please advise me. Thanks in advance.</p> Support #56 (Closed): BHPS Variable problemhttps://iserredex.essex.ac.uk/support/issues/562012-05-25T12:47:33ZIAN ALCOCKi.alcock@exeter.ac.uk
<p>I have a problem understanding the data for the BHPS variable on asthma, wHLPRXE, which is available for waves K and P only. This variable is routed through the all waves variable on Health problems: Chest/breathing wHLPRBE.</p>
<p>At wave K the asthma variable KHLPRXE is routed: if KMEMORIG==1-4 & KHLPRBE==1; if from the BHPS/ECHP sample and R has chest/breathing problems. KHLPRXE has 1404 valid yes/no response (+ 3 cases missing). BUT, KHLPRBE has 1464 cases which meet the condition for being routed to KHLPRXE; i.e. there are 1464 cases KMEMORIG=1-4 & KHLPRBE=1. (A cross tab of KMEMORIG and KHLPRBE if KHLPRBE==1 shows that of the 2542 cases KHLPRBE=1, OS=1172, and ECHP categories=143, 126 and 23; total=1464.) So where are the other 60 (or perhaps 57) who do not have a response to KHLPRBE?</p>
<p>The numbers do not seem to add up logically at wave P either. At wave P the asthma variable is routed: if PHLPRBE==1; if R has chest/breathing problems. KHLPRXE has 1969 valid yes/no response (+ 2 cases missing / don’t know). BUT PHLPRBE has 2010 cases which meet the condition for being routed to PHLPRXE; i.e. there are 2010 cases PHLPRBE=1. So where are the other 41 (or perhaps 39) who do not have a response to PHLPRXE?</p>
<p>Is this a routing statment problem, or have I missed something? Thanks in advance</p> Support #53 (Closed): "Events" variable BHPShttps://iserredex.essex.ac.uk/support/issues/532012-05-21T09:14:42Znicolet van Dijke
<p>Hello,<br />For my research on repossessions in the UK mortgage market I am studying the BHPS SN 5151 database.<br />In the British Household Panel Survey User Manual is stated, on page App3-101, that from Wave Two onwards, an open ended question was placed as the final question on the individual questionnaire which includes 'Important Events', which includes the event "repossession".<br />However I can only find these variables in waves 2, 3, 4, 5, 9 and 14.<br />Can someone please tell me where to find these variables for the other waves, if they even exist?<br />Thank you in advance!</p>
<p>Best,<br />Nicolet</p> Support #52 (Closed): Components of weighting variable a_indinus_xwhttps://iserredex.essex.ac.uk/support/issues/522012-05-18T00:00:04ZSung Park
<p>Hello:<br />I am considering whether to run my regressions with weight a_indinus_xw vs. running my regressions with unweighted data that includes the input variables that are used in the variable a_indinus_xw as controls. I reviewed the user manual and I was not clear on:<br />1) the estimation procedure and <br />2) input variables that were used (ie: race, sex, income, etc.)</p>
<p>to create the variable a_indinus_xw. Could you please clarify this and whether all these inputs are available in the publicly released data?</p>
<p>Many thanks.</p> Support #51 (Closed): a_indinus_xw weight=0https://iserredex.essex.ac.uk/support/issues/512012-05-16T05:54:48ZSung Park
<p>Hello:<br />I was wondering if you could confirm that that the a_indinus_xw weight variable should contain 3,933 observations (or about 7.71% of the total indresp file )where a_indinus_xw=0? I was analyzing a subpopulation of the data, and noticed that the subpopulation # of obs was lower than expected, due to this weight being zero.</p>
<p>Many thanks for your response.</p> Support #50 (Closed): Comparison to LFShttps://iserredex.essex.ac.uk/support/issues/502012-05-10T09:58:28ZSung Park
<p>Hello: I am looking at the report "APPENDIX: UNDERSTANDING SOCIETY DESIGN OVERVIEW" which I believe is Chapter 15 of the Early Findings Report (<a class="external" href="http://research.understandingsociety.org.uk/findings/early-findings">http://research.understandingsociety.org.uk/findings/early-findings</a>). I was attempting to replicate the Understanding Society column results from Table 8 ("Comparison of Great Britain Labour Force Survey sample and Understanding Society general population sample on key characteristics".</p>
<p>I used the following code to replicate the marital status distribution using the dataset indresp.dta, using the design weight for individuals as described in the report:<br />svyset a_psu_dv [pweight=a_psnenus_xd], strata(a_strata_dv)<br />svy, subpop(if(a_month >0 & a_month<13 & a_emboost==0 & a_xtra5min_dv==0 & a_gpcomp==0 & a_country==1 & a_pmarstat>0 & a_pmarstat<7)):tab a_pmarstat</p>
<p>However, I am getting slightly different percentages than what is shown in the table. Is there something wrong with my criteria/code?</p>
<p>Also, in order to replicate the sex and age distributions, do I need to combine the indresp.dta file with the youth file and use the same weights and criteria above?</p>
<p>Many thanks for your help.</p> Support #48 (Closed): Height variable in wave 16 of BHPShttps://iserredex.essex.ac.uk/support/issues/482012-05-04T19:15:54ZSara Watsonwatson.584@osu.edu
<p>Dear Support Team,</p>
<p>I have a question about the height variables in wave 16 of the BHPS. The height in inches variable (phlhti) has no values for 8 or 9 inches. Based on the wave 14 version of this variable, however, approximately 2000 individuals should have values of 8 or 9 inches. The issue does not seem to be a matter of poorer measurement in wave 16, as the "height<br />in feet" as well as all of the other values for the "height in inches" variable approximate well the wave 14 distribution.</p>
<p>Do you know if this might be a coding error, and if the data might be recoverable?</p>
<p>Thanks,<br />Sara Watson<br />Department of Political Science, The Ohio State University</p> Support #45 (Closed): BHPS year first jobhttps://iserredex.essex.ac.uk/support/issues/452012-04-30T19:17:05ZHannah Zagel
<p>Dear support team,<br />I am looking for the best way to derive the information of 'year of first job' in the BHPS. Am I overlooking any infomration or is the variable indeed not generated in the dataset?<br />I would be grateful for any advice, as I am sure this variable is often used.<br />Thank you and best wishes,<br />Hannah</p> Support #44 (Closed): Weighting on a restricted sample (outcome=110)https://iserredex.essex.ac.uk/support/issues/442012-04-30T13:15:43ZRigmor Nielsen
<p>Dear User Support</p>
<p>I am using the Understanding Society data for poverty analysis and would like to ask you if you can confirm whether I am using the weights correctly. These are the steps of my analysis:</p>
<p>- Restrict the sample to only those households where all individuals have responded(a_outcome=110 in HHSAMP). <br />- Create poverty flag for households below 60% of median income using following stata code:</p>
<p>cap drop poor<br />generate byte poor = .</p>
<p>summarize eq_inchh [aw = a_hhdenus_xw], detail<br /> replace poor = eq_inchh < .6 * r(p50) if !missing(eq_inchh)</p>
<p>- When calculating the median income for household, I used the household level weight (a_hhdenus_xw) from datafile HHRESP.</p>
<p>- Merge household level data with individual level datafile INDALL to obtain variable for dependent children (a_depchl_dv)<br />- Calculate proportion of dependent children living in poor households. When doing this, I use the individual level weight (a_psnenus_xw) from datafile HHRESP.</p>
<p>svyset [pw=a_psnenus_xw]<br />svy: tab poor a_depchl_dv, col</p>
<p>Many thanks,<br />Rigmor</p> Support #43 (Closed): Weighting-related questionshttps://iserredex.essex.ac.uk/support/issues/432012-04-29T23:39:13ZSung Park
<p>Hello: I have various weighting-related questions, which I have tried to list by similarity below:</p>
<p>1) What are the distinctions between the analysis weight and the design weight, as described in the user manual ? For example, what is the distinction between a_ind5mus_xw and a_ind5mus_xd as it relates to individual-level weights? I ask in order to determine whether the design weight is relevant to my analysis (some of which may be inferred from the subsequent questions below).</p>
<p>2) If I am conducting an individual-level analysis of respondents in the ethnic boost sample, but ALL the variables (both independent and dependent variables) I am including in my analysis are NOT specific to the extra 5 minutes of questions (such as sex, # children, household size, employment), would I still use the weight a_ind5mus_xw?</p>
<p>3) I notice that the psu and strata variables (a_psu_dv and a_strata_dv) are available only in the household file (hhresp). If I am doing individual-level analyses, if I just append these variables (psu and strata) to the individual-level (indresp) by merging on a_hidp, is this a valid way to be able to adjust for the sampling design in my analysis which is at an individual-level?</p>
<p>4) If I am combining ethnic respondents from the ethnic boost sample, as well as from the general comparison group (those ethnic minorities who live in low-density areas) for an individual-level analysis, is it sufficient to adjust for sampling design by selecting the a_ind5mus_xw weight, as well as adjusting for sampling, stratification and clustering by a_psu_dv, a_strata_dv and a_hidp, respectively?</p>