<?xml version="1.0" encoding="UTF-8"?>
<codeBook version="2.5" ID="ZAF_2000-2016_ALPHA-HIV-IM_v01_M" xml-lang="en" xmlns="ddi:codebook:2_5" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="ddi:codebook:2_5 http://www.ddialliance.org/Specification/DDI-Codebook/2.5/XMLSchema/codebook.xsd">
<docDscr>
  <citation>
    <titlStmt>
      <IDNo>DDI_ZAF_2000-2016_ALPHA-HIV-IM_v01_M</IDNo>
    </titlStmt>
    <prodStmt>
      <producer abbr="AHRI" role="Metadata creator">Africa Health Research Institute</producer>
      <producer abbr="ALPHA" affiliation="London School of Hygiene and Tropical Medicine" role="Metadata creator">Network for Analysing Longitudinal Population HIV/ AIDS data on Africa</producer>
      <producer affiliation="University of Cape Town" role="Metadata creator">DataFirst</producer>
      <producer abbr="DECDG" affiliation="World Bank Group" role="Metadata adapted for World Bank Microdata Library">Development Data Group</producer>
      <prodDate date="2024-08-23">2024-08-23</prodDate>
      <software version="beta">MetadataEditor</software>
    </prodStmt>
    <verStmt>
      <version>Identical to a metadata (zaf-alpha-himu-2000-2016-v1) published on DataFirst microdata repository (https://www.datafirst.uct.ac.za/dataportal/index.php/catalog). Some of the metadata fields have been edited.</version>
    </verStmt>
  </citation>
</docDscr>
<stdyDscr>
  <citation>
    <titlStmt>
      <titl>ALPHA HIV Incidence and Mortality Data 2000-2016, uMkhanyakude</titl>
      <altTitl>ALPHA-HIV-IM 2000-2016</altTitl>
      <IDNo>ZAF_2000-2016_ALPHA-HIV-IM_v01_M</IDNo>
    </titlStmt>
    <rspStmt>
      <AuthEnty>Africa Health Research Institute</AuthEnty>
      <AuthEnty affiliation="London School of Hygiene and Tropical Medicine">Network for Analysing Longitudinal Population HIV/ AIDS data on Africa</AuthEnty>
      <othId role="Director of Population Science" affiliation="AHRI">
        <p>Dr Kobus Herbst</p>
      </othId>
      <othId role="Data Scientist" affiliation="AHRI">
        <p>Dickman Gareta</p>
      </othId>
    </rspStmt>
    <prodStmt>
      <software version="beta" date="2026-05-29">MetadataEditor</software>
      <fundAg role="Funding agency">Wellcome Trust</fundAg>
      <fundAg role="Funding agency">Bill and Melinda Gates Foundation</fundAg>
    </prodStmt>
    <serStmt>
      <serName>Other Household Survey [hh/oth]</serName>
      <serInfo><![CDATA[The ALPHA (Analysing Longitudinal Population-based HIV/AIDS Data in Africa) Network is a collaboration among 10 longitudinal studies in sub-Saharan Africa. These studies collect data on HIV infection alongside demographic, behavioural, socio-economic and clinical data from residents of the study areas.  The Network harmonises these data and conducts comparable and pooled analyses on HIV-related research questions.The ALPHA HIV Incidence and Mortality data,uMkhanyakude is part of the international data harmonisation and analysis programme of the ALPHA network.]]></serInfo>
    </serStmt>
    <verStmt>
      <version>Version 01: Edited, anonymised data available with restrictions.</version>
    </verStmt>
  </citation>
  <stdyInfo>
    <subject>
                  
                  
    </subject>
    <abstract><![CDATA[This dataset is created from harmonizing longitudinal population-based demographic surveillance and repeated serological survey data collected by the uMkhanyakude study in South Africa. The data harmonization is coordinated by the ALPHA Network which curates individual-level data on demographic surveillance, verbal autopsy interviews, serological and sexual behavior surveys, and individually-linked data from HDSS and medical facilities.

The data from the Umkhanyakude site in South Africa includes two data files:
- HIV incidence data
This file includes data on resident study participants aged 15-49 who have had one negative HIV test and at least one subsequent HIV test done within the study for research purposes. Data may be split into multiple observations for each person to describe time spent in different residencies, different age groups, and different calendar year periods. All timings are given as age at event, instead of dates.  Dates of birth are rounded to the 15th of the month, and all other dates are offset by the same amount and the time elapsed between the rounded dates is used as the age at event. To enable multiple imputation of seroconversion dates the times (ages) of last negative test and first positive test have been provided.
- Mortality  data
This data file was created as described at https://gatesopenresearch.org/articles/1-4]]></abstract>
    <sumDscr>
      <collDate date="2000" event="start" cycle="Incedence data"/>
      <collDate date="2016" event="end" cycle="Incedence data"/>
      <collDate date="2000" event="start" cycle="Mortality data"/>
      <collDate date="2016" event="end" cycle="Mortality data"/>
      <nation abbr="ZAF">South Africa</nation>
      <geogCover>The data covers the uMkhanyakude study area in KwaZulu-Natal, South Africa</geogCover>
      <geogUnit>The data is at the level of village.</geogUnit>
      <anlyUnit><![CDATA[Individuals]]></anlyUnit>
      <dataKind>Event/transaction data [evn]</dataKind>
    </sumDscr>
    <notes><![CDATA[The dataset includes individual-level HIV data from demographic surveillance, verbal autopsy interviews, serological and sexual behaviour surveys, and individually-linked data from HDSS and medical facilities.]]></notes>
  </stdyInfo>
  <method>
    <dataColl>
      <dataCollector>Africa Health Research Institute</dataCollector>
      <collMode>Face-to-face</collMode>
      <collSitu><![CDATA[ALPHA data are harmonised datasets from ALPHA member sites and this dataset is from the Africa Health Research Institute.]]></collSitu>
    </dataColl>
  </method>
  <dataAccs>
    <setAvail>
      <origArch>Karonga (MW011)</origArch>
    </setAvail>
    <useStmt>
      <contact URI="https://data.ahri.org/index.php/catalog/1029">Africa Health Research Institute</contact>
      <citReq><![CDATA[Herbst, K. et al. ALPHA HIV Incidence and Mortality Data, uMkhanyakude 2000-2016 [dataset].Version 1. Africa Health Research Institute [producer and distributor], 2022. https://data.ahri.org/index.php/catalog/1029]]></citReq>
      <conditions><![CDATA[Access under a Creative Commons CC-BY-NC (Attribution, Non-Commercial use only) License]]></conditions>
    </useStmt>
  </dataAccs>
</stdyDscr>
<fileDscr ID="F1">
  <fileTxt>
    <fileName>incidence_uMkhanyakude</fileName>
    <dimensns>
      <caseQnty>0</caseQnty>
      <varQnty>15</varQnty>
    </dimensns>
  </fileTxt>
</fileDscr>
<fileDscr ID="F2">
  <fileTxt>
    <fileName>mortality_uMkhanyakude</fileName>
    <dimensns>
      <caseQnty>0</caseQnty>
      <varQnty>14</varQnty>
    </dimensns>
  </fileTxt>
</fileDscr>
<dataDscr>
<var ID="V1" name="study_name" files="F1" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="1" EndPos="12" width="12" RecSegNo="1"/>
  <labl>Study name</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <catValu>1</catValu>
    <labl>Karonga</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>Kisesa</labl>
  </catgry>
  <catgry>
    <catValu>3</catValu>
    <labl>Manicaland</labl>
  </catgry>
  <catgry>
    <catValu>4</catValu>
    <labl>Masaka</labl>
  </catgry>
  <catgry>
    <catValu>5</catValu>
    <labl>Rakai</labl>
  </catgry>
  <catgry>
    <catValu>6</catValu>
    <labl>uMkhanyakude</labl>
  </catgry>
  <catgry>
    <catValu>7</catValu>
    <labl>Agincourt</labl>
  </catgry>
  <catgry>
    <catValu>8</catValu>
    <labl>Kisumu</labl>
  </catgry>
  <catgry>
    <catValu>9</catValu>
    <labl>Ifakara</labl>
  </catgry>
  <catgry>
    <catValu>10</catValu>
    <labl>Nairobi</labl>
  </catgry>
</var>
<var ID="V2" name="idno" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="13" EndPos="21" width="9" RecSegNo="1"/>
  <labl>Participant ID number</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V3" name="sex" files="F1" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="22" EndPos="33" width="12" RecSegNo="1"/>
  <labl>Sex</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <catValu>1</catValu>
    <labl>Men</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>Women</labl>
  </catgry>
</var>
<var ID="V4" name="fouryear" files="F1" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="34" EndPos="42" width="9" RecSegNo="1"/>
  <labl>Calendar year, grouped in 4 years post 2005</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <labl>1995-99</labl>
  </catgry>
  <catgry>
    <catValu>1</catValu>
    <labl>2000-04</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>2005-08</labl>
  </catgry>
  <catgry>
    <catValu>3</catValu>
    <labl>2009-12</labl>
  </catgry>
  <catgry>
    <catValu>4</catValu>
    <labl>2013-16</labl>
  </catgry>
  <catgry>
    <catValu>5</catValu>
    <labl>2017-20</labl>
  </catgry>
  <catgry>
    <catValu>6</catValu>
    <labl>2021-24</labl>
  </catgry>
</var>
<var ID="V5" name="agegrp" files="F1" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="43" EndPos="51" width="9" RecSegNo="1"/>
  <labl>Five year age group</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <labl>0-4</labl>
  </catgry>
  <catgry>
    <catValu>1</catValu>
    <labl>5-9</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>10-14</labl>
  </catgry>
  <catgry>
    <catValu>3</catValu>
    <labl>15-19</labl>
  </catgry>
  <catgry>
    <catValu>4</catValu>
    <labl>20-24</labl>
  </catgry>
  <catgry>
    <catValu>5</catValu>
    <labl>25-29</labl>
  </catgry>
  <catgry>
    <catValu>6</catValu>
    <labl>30-34</labl>
  </catgry>
  <catgry>
    <catValu>7</catValu>
    <labl>35-39</labl>
  </catgry>
  <catgry>
    <catValu>8</catValu>
    <labl>40-44</labl>
  </catgry>
  <catgry>
    <catValu>9</catValu>
    <labl>45-49</labl>
  </catgry>
  <catgry>
    <catValu>10</catValu>
    <labl>50-54</labl>
  </catgry>
  <catgry>
    <catValu>11</catValu>
    <labl>55-59</labl>
  </catgry>
  <catgry>
    <catValu>12</catValu>
    <labl>60-64</labl>
  </catgry>
  <catgry>
    <catValu>13</catValu>
    <labl>65-69</labl>
  </catgry>
  <catgry>
    <catValu>14</catValu>
    <labl>70-74</labl>
  </catgry>
  <catgry>
    <catValu>15</catValu>
    <labl>75-79</labl>
  </catgry>
  <catgry>
    <catValu>16</catValu>
    <labl>80-84</labl>
  </catgry>
  <catgry>
    <catValu>17</catValu>
    <labl>85-89</labl>
  </catgry>
  <catgry>
    <catValu>18</catValu>
    <labl>90+</labl>
  </catgry>
</var>
<var ID="V6" name="timein" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="52" EndPos="61" width="10" RecSegNo="1"/>
  <labl>Start of episode (age)</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V7" name="timeout" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="62" EndPos="71" width="10" RecSegNo="1"/>
  <labl>End of episode (age)</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V8" name="timelastneg" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="72" EndPos="81" width="10" RecSegNo="1"/>
  <labl>Age at last negative test</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V9" name="timefirstpos" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="82" EndPos="91" width="10" RecSegNo="1"/>
  <labl>Age at first positive test</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V10" name="fail" files="F1" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="92" EndPos="100" width="9" RecSegNo="1"/>
  <labl>Seroconversion occurred at the end of this episode</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <labl>No</labl>
  </catgry>
  <catgry>
    <catValu>1</catValu>
    <labl>Yes</labl>
  </catgry>
</var>
<var ID="V11" name="t0" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="101" EndPos="110" width="10" RecSegNo="1"/>
  <labl>Stata variable: age at start of episode</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V12" name="t" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="111" EndPos="120" width="10" RecSegNo="1"/>
  <labl>Stata variable: age at end of episode</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V13" name="st" files="F1" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="121" EndPos="128" width="8" RecSegNo="1"/>
  <labl>Stata variable: in survival analysis</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V14" name="d" files="F1" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="129" EndPos="136" width="8" RecSegNo="1"/>
  <labl>Stata variable: failure (seroconversion)</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V15" name="collapsegrp" files="F1" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="137" EndPos="145" width="9" RecSegNo="1"/>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V16" name="study_name" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="1" EndPos="12" width="12" RecSegNo="1"/>
  <labl>Study name</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <catValu>1</catValu>
    <labl>Karonga</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>Kisesa</labl>
  </catgry>
  <catgry>
    <catValu>3</catValu>
    <labl>Manicaland</labl>
  </catgry>
  <catgry>
    <catValu>4</catValu>
    <labl>Masaka</labl>
  </catgry>
  <catgry>
    <catValu>5</catValu>
    <labl>Rakai</labl>
  </catgry>
  <catgry>
    <catValu>6</catValu>
    <labl>uMkhanyakude</labl>
  </catgry>
  <catgry>
    <catValu>7</catValu>
    <labl>Agincourt</labl>
  </catgry>
  <catgry>
    <catValu>8</catValu>
    <labl>Kisumu</labl>
  </catgry>
  <catgry>
    <catValu>9</catValu>
    <labl>Ifakara</labl>
  </catgry>
  <catgry>
    <catValu>10</catValu>
    <labl>Nairobi</labl>
  </catgry>
</var>
<var ID="V17" name="idno" files="F2" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="13" EndPos="21" width="9" RecSegNo="1"/>
  <labl>Participant ID number</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V18" name="sex" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="22" EndPos="29" width="8" RecSegNo="1"/>
  <labl>Sex</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <catValu>1</catValu>
    <labl>Men</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>Women</labl>
  </catgry>
</var>
<var ID="V19" name="fouryear" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="30" EndPos="42" width="13" RecSegNo="1"/>
  <labl>Calendar year, grouped in 4 years post 2005</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <labl>earliest-1999</labl>
  </catgry>
  <catgry>
    <catValu>1</catValu>
    <labl>2000-04</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>2005-08</labl>
  </catgry>
  <catgry>
    <catValu>3</catValu>
    <labl>2009-12</labl>
  </catgry>
  <catgry>
    <catValu>4</catValu>
    <labl>2013-16</labl>
  </catgry>
  <catgry>
    <catValu>5</catValu>
    <labl>2017-20</labl>
  </catgry>
  <catgry>
    <catValu>6</catValu>
    <labl>2021-24</labl>
  </catgry>
</var>
<var ID="V20" name="agegrp" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="43" EndPos="51" width="9" RecSegNo="1"/>
  <labl>Five year age group</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <labl>0-4</labl>
  </catgry>
  <catgry>
    <catValu>1</catValu>
    <labl>5-9</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>10-14</labl>
  </catgry>
  <catgry>
    <catValu>3</catValu>
    <labl>15-19</labl>
  </catgry>
  <catgry>
    <catValu>4</catValu>
    <labl>20-24</labl>
  </catgry>
  <catgry>
    <catValu>5</catValu>
    <labl>25-29</labl>
  </catgry>
  <catgry>
    <catValu>6</catValu>
    <labl>30-34</labl>
  </catgry>
  <catgry>
    <catValu>7</catValu>
    <labl>35-39</labl>
  </catgry>
  <catgry>
    <catValu>8</catValu>
    <labl>40-44</labl>
  </catgry>
  <catgry>
    <catValu>9</catValu>
    <labl>45-49</labl>
  </catgry>
  <catgry>
    <catValu>10</catValu>
    <labl>50-54</labl>
  </catgry>
  <catgry>
    <catValu>11</catValu>
    <labl>55-59</labl>
  </catgry>
  <catgry>
    <catValu>12</catValu>
    <labl>60-64</labl>
  </catgry>
  <catgry>
    <catValu>13</catValu>
    <labl>65-69</labl>
  </catgry>
  <catgry>
    <catValu>14</catValu>
    <labl>70-74</labl>
  </catgry>
  <catgry>
    <catValu>15</catValu>
    <labl>75-79</labl>
  </catgry>
  <catgry>
    <catValu>16</catValu>
    <labl>80-84</labl>
  </catgry>
  <catgry>
    <catValu>17</catValu>
    <labl>85-89</labl>
  </catgry>
  <catgry>
    <catValu>18</catValu>
    <labl>90+</labl>
  </catgry>
</var>
<var ID="V21" name="hivstatus_broad" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="52" EndPos="60" width="9" RecSegNo="1"/>
  <labl>HIV status</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <catValu>1</catValu>
    <labl>Negative</labl>
  </catgry>
  <catgry>
    <catValu>2</catValu>
    <labl>Positive</labl>
  </catgry>
  <catgry>
    <catValu>3</catValu>
    <labl>Unknown</labl>
  </catgry>
</var>
<var ID="V22" name="timein" files="F2" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="61" EndPos="70" width="10" RecSegNo="1"/>
  <labl>Start of episode (age)</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V23" name="timeout" files="F2" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="71" EndPos="80" width="10" RecSegNo="1"/>
  <labl>End of episode (age)</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V24" name="fail" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="81" EndPos="89" width="9" RecSegNo="1"/>
  <labl>Seroconversion occurred at the end of this episode</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
  <catgry>
    <labl>No</labl>
  </catgry>
  <catgry>
    <catValu>1</catValu>
    <labl>Yes</labl>
  </catgry>
</var>
<var ID="V25" name="t0" files="F2" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="90" EndPos="99" width="10" RecSegNo="1"/>
  <labl>Stata variable: age at start of episode</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V26" name="t" files="F2" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="100" EndPos="109" width="10" RecSegNo="1"/>
  <labl>Stata variable: age at end of episode</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V27" name="st" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="110" EndPos="117" width="8" RecSegNo="1"/>
  <labl>Stata variable: in survival analysis</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V28" name="d" files="F2" intrvl="discrete">
  <varFormat type="numeric"/>
  <location StartPos="118" EndPos="125" width="8" RecSegNo="1"/>
  <labl>Stata variable: failure (seroconversion)</labl>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
<var ID="V29" name="collapsegrp" files="F2" intrvl="contin">
  <varFormat type="numeric"/>
  <location StartPos="126" EndPos="134" width="9" RecSegNo="1"/>
  <sumStat type="vald"/>
  <sumStat type="invd"/>
</var>
</dataDscr></codeBook>
