Annual Population Survey, October 2019 - September 2020

The <i>Annual Population Survey</i> (APS) is a major survey series, which aims to provide data that can produce reliable estimates at local authority level. Key topics covered in the survey include education, employment, health and ethnicity. The APS comprises key variables from the <i>Labour Force Survey</i> (LFS) (held at the UK Data Archive under GN 33246), all its associated LFS boosts and the APS boost. Thus, the APS combines results from five different sources: the LFS (waves 1 and 5); the English <i>Local Labour Force Survey</i> (LLFS), the <i>Welsh Labour Force Survey</i> (WLFS), the <i>Scottish Labour Force Survey</i> (SLFS) and the <i>Annual Population Survey Boost Sample</i> (APS(B) - however, this ceased to exist at the end of December 2005, so APS data from January 2006 onwards will contain all the above data apart from APS(B)). Users should note that the LLFS, WLFS, SLFS and APS(B) are not held separately at the Archive. For further detailed information about methodology, users should consult the <i>Labour Force Survey User Guide</i>, selected volumes of which have been included with the APS documentation for reference purposes (see 'Documentation' table below).<br> <br> The APS aims to provide enhanced annual data for England, covering a target sample of at least 510 economically active persons for each Unitary Authority (UA)/Local Authority District (LAD) and at least 450 in each Greater London Borough. In combination with local LFS boost samples such as the WLFS and SLFS, the survey provides estimates for a range of indicators down to Local Education Authority (LEA) level across the United Kingdom.<br><br><span style="font-weight: bold;">New reweighting policy</span><br>Following the <a href="http://doc.ukdataservice.ac.uk/doc/8343/mrdoc/pdf/biennial_lfs_aps_reweighting_policy.pdf" target="_blank" style="background-color: rgb(255, 255, 255);">new reweighting policy</a><a href="http://doc.ukdataservice.ac.uk/doc/8343/mrdoc/pdf/biennial_lfs_aps_reweighting_policy.pdf" target="_blank" style="background-color: rgb(255, 255, 255);"></a> ONS has reviewed the latest population estimates made available during 2019 and have decided not to carry out a 2019 LFS and APS reweighting exercise. Therefore, the next reweighting exercise will take place in 2020. These will incorporate the 2019 Sub-National Population Projection data (published in May 2020) and 2019 Mid-Year Estimates (published in June 2020). It is expected that reweighted Labour Market aggregates and microdata will be published towards the end of 2020/early 2021.<br> <br> <b>End User Licence and Secure Access APS data</b><br> Users should note that there are two versions of each APS dataset. One is available under the standard End User Licence (EUL) agreement, and the other is a Secure Access version. The EUL version includes Government Office Region geography, banded age, 3-digit SOC and industry sector for main, second and last job. The Secure Access version contains more detailed variables relating to:<ul><li>age: single year of age, year and month of birth, age completed full-time education and age obtained highest qualification, age of oldest dependent child and age of youngest dependent child</li><li>family unit and household: including a number of variables concerning the number of dependent children in the family according to their ages, relationship to head of household and relationship to head of family</li><li>nationality and country of origin</li><li>geography: including county, unitary/local authority, place of work, Nomenclature of Territorial Units for Statistics 2 (NUTS2) and NUTS3 regions, and whether lives and works in same local authority district</li><li>health: including main health problem, and current and past health problems</li><li>education and apprenticeship: including numbers and subjects of various qualifications and variables concerning apprenticeships</li><li>industry: including industry, industry class and industry group for main, second and last job, and industry made redundant from</li><li>occupation: including 4-digit Standard Occupational Classification (SOC) for main, second and last job and job made redundant from</li><li>system variables: including week number when interview took place and number of households at address</li></ul>The Secure Access data have more restrictive access conditions than those made available under the standard EUL. Prospective users will need to gain ONS Accredited Researcher status, complete an extra application form and demonstrate to the data owners exactly why they need access to the additional variables. Users are strongly advised to first obtain the standard EUL version of the data to see if they are sufficient for their research requirements.<br> <br> <b>Documentation and coding frames</b><br> The APS is compiled from variables present in the LFS. For variable and value labelling and coding frames that are not included either in the data or in the current APS documentation (e.g. coding frames for education, industrial and geographic variables, which are held in LFS User Guide Vol.5, Classifications), users are advised to consult the latest versions of the LFS User Guides, which are available from the ONS <a href="https://www.ons.gov.uk/employmentandlabourmarket/peopleinwork/employmentandemployeetypes/methodologies/labourforcesurveyuserguidance" title="Labour Force Survey - User Guidance" target="_blank">Labour Force Survey - User Guidance</a> webpages.<br> <br> <b>APS Well-Being Datasets</b><br> From 2012-2015, the ONS published separate APS datasets aimed at providing initial estimates of subjective well-being, based on the <i>Integrated Household Survey</i>. In 2015 these were discontinued. A separate set of well-being variables and a corresponding weighting variable have been added to the April-March APS person datasets from A11M12 onwards. <b>Users should no longer use the bespoke well-being datasets (SNs 6994, 6999, 7091, 7092, 7364, 7365, 7565 and 7566, but should now use the variables included on the April-March APS person datasets instead</b>. Further information on the transition can be found on the <a href="https://www.ons.gov.uk/peoplepopulationandcommunity/wellbeing/bulletins/measuringnationalwellbeing/2015to2016" title="Personal well-being in the UK: 2015 to 2016" target="_blank">Personal well-being in the UK: 2015 to 2016</a><br> <br> <b>Disability variables from 2013 onwards - LFS and APS</b><br> ONS have provided some information on changes since 2013 to the disability variables available on the LFS and APS. The Disability Discrimination Act (DDA) disabled (current disability) category within the historic DISCURR variable no longer corresponds with the advised legal definition of 'current disability'. DISCURR should only be available on LFS microdata from Spring 1998 to January-March 2013 (JM13); beyond that point users should ignore or delete it. In addition, the same 'DDA disabled (current disability)' category within variable DISCURR13 is also not the most appropriate variable to use because a) it is not comparable to the corresponding category in variable DISCURR due to question changes, and b) it no longer measures either the DDA definition of disability or the latest Equality Act definition of disability. However, DISCURR13 is available from the April-March 2013 quarter (AJ13) onwards and was introduced to demonstrate that the variables used to compile DISCURR had also changed from that quarter. Therefore, users are advised to use the disability variable DISEA from AJ13 onwards, which reflects the Equality Act 2010 legal definition of 'disabled', measured according to the <a href="http://www.ons.gov.uk/ons/guide-method/harmonisation/primary-set-of-harmonised-concepts-and-questions/long-lasting-health-conditions-and-illnesses--impairments-and-disability.pdf" title="GSS Harmonised Standard" target="_blank">GSS Harmonised Standard</a> on health conditions and illnesses. The harmonised disability variables DISEA and DISCURR13 should both be present on the APS person microdata from April 2013-March 2014 (A13M14) onwards. This ensures that APS users have a complete 12 months' data on which to base analysis of the variables. DISCURR should only be present on APS microdata up to and including April 2012-March 2013 (A12M13).<br> <br> <b>Variables DISEA and LNGLST</b><br> Dataset A08 (Labour market status of disabled people) which ONS suspended due to an apparent discontinuity between April to June 2017 and July to September 2017 is now available. As a result of this apparent discontinuity and the inconclusive investigations at this stage, comparisons should be made with caution between April to June 2017 and subsequent time periods. However users should note that the estimates are not seasonally adjusted, so some of the change between quarters could be due to seasonality. Further recommendations on historical comparisons of the estimates will be given in November 2018 when ONS are due to publish estimates for July to September 2018. <br> <br> An article explaining the quality assurance investigations that have been conducted so far is available on the <a href="https://www.ons.gov.uk/employmentandlabourmarket/peopleinwork/employmentandemployeetypes/methodologies/analysisofthediscontinuityinthelabourforcesurveydisabilitydataapriltojune2017tojulytoseptember2017" target="_blank">ONS Methodology</a> webpage. For any queries about Dataset A08 please email [e-mail].<br> <br> <p><span style="font-weight: bold;">Latest edition information</span><br></p><p>For the fourth edition (September 2021) the new 2020 weights PWTA20 and PIWTA20 were added to the study. These latest weights use updated population data to better reflect changes in international migration and other impacts as a result of the coronavirus (COVID-19) pandemic. More information on the method for these weights can be found in the article <a href="https://www.ons.gov.uk/employmentandlabourmarket/peopleinwork/employmentandemployeetypes/methodologies/labourforcesurveyweightingmethodology">Labour Force Survey weighting methodology</a>. <br></p>

<i>年度人口调查（Annual Population Survey, APS）</i>是一套核心调查系列，旨在提供可用于生成地方政府层级可靠估算数据的调研结果。该调查涵盖的核心主题包括教育、就业、健康与族裔。

APS整合了<i>劳动力调查（Labour Force Survey, LFS）</i>（由英国数据档案馆以编号GN 33246存档）的核心变量、所有配套的LFS增补样本，以及APS自身的增补样本。换言之，APS由五类不同来源的数据合并而成：LFS（第1、5波）、英格兰<i>地方劳动力调查（Local Labour Force Survey, LLFS）</i>、威尔士劳动力调查（Welsh Labour Force Survey, WLFS）、苏格兰劳动力调查（Scottish Labour Force Survey, SLFS），以及<i>年度人口调查增补样本（Annual Population Survey Boost Sample, APS(B)）</i>——但该增补样本于2005年12月底停止运行，因此2006年1月及之后的APS数据不再包含APS(B)。需注意，LLFS、WLFS、SLFS与APS(B)并未在档案馆单独存档。如需获取详细的方法论信息，用户可参考<i>劳动力调查用户指南（Labour Force Survey User Guide）</i>，该指南的部分选卷已随APS文档一并提供以供参考（详见下文“文档”表格）。

APS旨在为英格兰提供优化后的年度数据，目标为每个单一管理区（Unitary Authority, UA）/地方行政区（Local Authority District, LAD）至少采集510名经济活动人口样本，大伦敦自治市则至少采集450名。结合WLFS、SLFS等地方LFS增补样本，该调查可针对英国范围内的地方教育当局（Local Education Authority, LEA）层级的各类指标提供估算值。

<b>新的重新加权政策</b>
根据<a href="http://doc.ukdataservice.ac.uk/doc/8343/mrdoc/pdf/biennial_lfs_aps_reweighting_policy.pdf" target="_blank" style="background-color: rgb(255, 255, 255);">新的重新加权政策</a>，英国国家统计局（Office for National Statistics, ONS）审阅了2019年期间发布的最新人口估算数据，并决定不开展2019年度LFS与APS的重新加权工作。下一次重新加权工作将于2020年启动，将纳入2019年次国家级人口预测数据（2020年5月发布）与2019年年中人口估算数据（2020年6月发布）。预计重新加权后的劳动力市场汇总数据与微观数据将于2020年末/2021年初发布。

<b>最终用户许可与安全访问版APS数据</b>
用户需注意，每份APS数据集均包含两个版本：其一遵循标准最终用户许可（End User Licence, EUL）协议发布，其二为安全访问版本。标准EUL版本包含政府办公室区域地理信息、分档年龄、主/第二职业/最后一份工作的3位标准职业分类（Standard Occupational Classification, SOC）代码与行业分类。安全访问版本则包含更多详细变量，涉及：
<ul>
<li>年龄：单一年龄、出生年份与月份、完成全日制教育的年龄、获得最高学历的年龄、最大受抚养子女年龄与最小受抚养子女年龄</li>
<li>家庭单元与住户：包括按年龄划分的受抚养子女数量、与住户户主及家庭户主的关系等多项家庭相关变量</li>
<li>国籍与原籍国</li>
<li>地理信息：包括县、单一管理区/地方行政区、工作地点、统计区域命名规范2级（Nomenclature of Territorial Units for Statistics 2, NUTS2）与3级（NUTS3）区域，以及是否在同一地方行政区内居住与工作</li>
<li>健康：包括主要健康问题、当前与既往健康问题</li>
<li>教育与学徒制：包括各类资质的数量与科目，以及与学徒制相关的变量</li>
<li>行业：包括主/第二职业/最后一份工作以及被裁员时所在行业的行业分类、行业类别与行业组别</li>
<li>职业：包括主/第二职业/最后一份工作以及被裁员时所从事岗位的4位标准职业分类（SOC）代码</li>
<li>系统变量：包括访谈所属周数与住址内的住户数量</li>
</ul>
安全访问数据的访问限制远严于标准EUL版本。潜在用户需获得ONS认证研究员资格，填写额外的申请表，并向数据所有者明确说明需要访问额外变量的具体原因。我们强烈建议用户先获取标准EUL版本的数据，以确认其是否满足研究需求。

<b>文档与编码框架</b>
APS的数据源自LFS中的变量。对于未包含在数据集或当前APS文档中的变量、值标签与编码框架（例如教育、行业与地理变量的编码框架，存于《LFS用户指南》第5卷《分类》中），建议用户查阅最新版的LFS用户指南，该指南可从ONS的<a href="https://www.ons.gov.uk/employmentandlabourmarket/peopleinwork/employmentandemployeetypes/methodologies/labourforcesurveyuserguidance" title="劳动力调查 - 用户指南" target="_blank">劳动力调查用户指南</a>网页获取。

<b>APS幸福感数据集</b>
2012年至2015年间，ONS发布了独立的APS数据集，旨在基于<i>综合住户调查（Integrated Household Survey）</i>提供主观幸福感的初步估算值。该类数据集于2015年停止更新。自A11M12周期起，4月至次年3月的APS个人数据集已新增了一套独立的幸福感变量与对应的加权变量。<b>用户不应再使用此前定制化的幸福感数据集（编号SN 6994、6999、7091、7092、7364、7365、7565与7566），而应改用4月至次年3月APS个人数据集中包含的相关变量</b>。关于此次转型的更多信息可参阅<a href="https://www.ons.gov.uk/peoplepopulationandcommunity/wellbeing/bulletins/measuringnationalwellbeing/2015to2016" title="英国个人幸福感：2015年至2016年" target="_blank">《英国个人幸福感：2015年至2016年》</a>。

<b>2013年起的LFS与APS残疾变量</b>
ONS已公布2013年以来LFS与APS中残疾变量的变更信息。历史变量DISCURR中的“《残疾歧视法》（Disability Discrimination Act, DDA）认定的（当前）残疾”类别，已不再符合“当前残疾”的法定推荐定义。DISCURR仅在1998年春季至2013年1-3月（JM13）的LFS微观数据中可用，在此之后的版本中用户应忽略或删除该变量。此外，变量DISCURR13中的“《残疾歧视法》认定的（当前）残疾”类别也并非最适宜的使用变量，原因有二：其一，由于问卷问题变更，该类别与DISCURR中的对应类别不具备可比性；其二，该类别既未遵循《残疾歧视法》的残疾定义，也未采用最新的《平等法》残疾定义。不过，DISCURR13自2013年1-3月周期（AJ13）起可用，其引入旨在表明自该周期起，用于编制DISCURR的变量已发生变更。因此，建议用户自AJ13周期起使用残疾变量DISEA，该变量符合2010年《平等法》中“残疾”的法定定义，其测量标准遵循<a href="http://www.ons.gov.uk/ons/guide-method/harmonisation/primary-set-of-harmonised-concepts-and-questions/long-lasting-health-conditions-and-illnesses--impairments-and-disability.pdf" title="GSS统一标准" target="_blank">GSS统一标准</a>中关于健康状况与疾病的规定。自2013年4月至2014年3月（A13M14）周期起，APS个人微观数据中将同时包含统一后的残疾变量DISEA与DISCURR13，以确保用户可基于完整的12个月数据开展变量分析。DISCURR仅在2012年4月至2013年3月（A12M13）及之前的APS微观数据中可用。

<b>变量DISEA与LNGLST</b>
ONS因2017年4月至6月与2017年7月至9月的数据存在明显间断而暂停发布的数据集A08（残疾人士劳动力市场状况）现已恢复可用。鉴于此次数据间断及现阶段调查结果尚未明确，在对2017年4月至6月与后续时间段的数据进行比较时需格外谨慎。同时需注意，该数据集的估算值未经过季节调整，因此季度间的部分变化可能源于季节因素。ONS将于2018年11月发布2018年7月至9月的估算数据时，针对历史数据比较提供进一步的建议。
一篇介绍截至目前所开展的质量保证调查的文章可在ONS的<a href="https://www.ons.gov.uk/employmentandlabourmarket/peopleinwork/employmentandemployeetypes/methodologies/analysisofthediscontinuityinthelabourforcesurveydisabilitydataapriltojune2017tojulytoseptember2017" target="_blank">方法论</a>网页获取。若对数据集A08有任何疑问，请发送邮件至[e-mail]。

<b>最新版本信息</b>
在2021年9月发布的第四版数据中，研究新增了2020年版权重PWTA20与PIWTA20。该批最新权重采用了更新后的人口数据，以更准确地反映国际移民变化以及新冠病毒（COVID-19）大流行带来的其他影响。关于该批权重的编制方法，可参阅文章<a href="https://www.ons.gov.uk/employmentandlabourmarket/peopleinwork/employmentandemployeetypes/methodologies/labourforcesurveyweightingmethodology">《劳动力调查加权方法论》</a>获取更多信息。