Data and Metadata Harmonization for the RAND Survey Meta Data Repository

  • Published on
    03-Jan-2016

  • View
    26

  • Download
    2

DESCRIPTION

Data and Metadata Harmonization for the RAND Survey Meta Data Repository. Alerk Amin April 3, 2013. Outline. About the studies RAND work Repository Website Import metadata RAND harmonized datasets How DDI could help. Health and Retirement Study. University of Michigan - PowerPoint PPT Presentation

Transcript

RAND Survey Meta Data Repository

Data and Metadata Harmonization for the RAND Survey Meta Data Repository Alerk AminApril 3, 2013Survey Meta Data Repository-# April 3 2013#OutlineAbout the studiesRAND workRepository WebsiteImport metadataRAND harmonized datasetsHow DDI could helpSurvey Meta Data Repository-# April 3 2013Health and Retirement StudyUniversity of MichiganLongitudinal panel study of Americans age 50+Biennially since 1992Survey Meta Data Repository-# April 3 2013#HRS Worldwide Family

Survey Meta Data Repository-# April 3 2013HRS familyHealth and Retirement Study (HRS) since 1992Mexican Health and Aging Study (MHAS) since 2001English Longitudinal Study of Ageing (ELSA) since 2002Survey of Health, Ageing and Retirement in Europe (SHARE) since 2004Korean Longitudinal Study on Aging (KLoSA) since 2006Japanese Study of Aging and Retirement (JSTAR) since 2007Indonesian Family Life Survey (IFLS), modified in 2007China Health and Retirement Study (CHARLS) since 2008Irish Longitudinal study on Ageing (TILDA) since 2010Longitudinal Aging Study in India (LASI) since 2010Study on Global Ageing and Adult Health (SAGE), since 2010Survey Meta Data Repository-# April 3 2013#Repository GoalsMake it easier for researchers toFind appropriate data across the different studiesCross-country analysisSurvey Meta Data Repository-# April 3 2013Repository Item

Survey Meta Data Repository-# April 3 2013#Repository Questionnaire Routing

Survey Meta Data Repository-# April 3 2013#Repository Codebook

Survey Meta Data Repository-# April 3 2013#Metadata HarmonizationMetadata import from each studyCreate links across studies to aid researchersSurvey Meta Data Repository-# April 3 2013Importing Survey MetadataOnly IFLS provides DDI (v 1.2.2) metadataStudies using MMIC can be imported via scriptsOther studies involve a lot of work by handSometimes CSV files are available for importOtherwise, cut-and-paste from codebookRouting is entered by hand, based on codebookSurvey Meta Data Repository-# April 3 2013Linking Questions to VariablesVariables are imported via Stata filesQuestions are linked to Variablesusually via CSV importSurvey Meta Data Repository-# April 3 2013Linking Questions to ConceptsRAND Working Paper Series, WR861-1/7 A set of domain-specific user guides onChronic medical conditionsFinancial transferExpectationEmployment and retirementIncomeWealthCognitionSurvey Meta Data Repository-# April 3 2013Linking Questions to ConceptsOne wave of concepts is available from working papersConcept-Questions are entered by handMore work is done to then link other waves

Survey Meta Data Repository-# April 3 2013How DDI Could HelpIf studies provided metadata in DDI3 formatImport Questions, Variables, Routing

Survey Meta Data Repository-# April 3 2013Importing Published DDIOther studies copy concepts, questions from HRSIDEAL - all studies link Questions to a common ConceptSchemeREALISTIC all studies link Questions to HRS Questions

Survey Meta Data Repository-# April 3 2013Data HarmonizationRAND creates harmonized datasetsRAND HRS, RAND ELSA, RAND SHARE, RAND KLoSAComing soon RAND CHARLS, RAND JSTARIdentical/Comparable set of variables across studiesSurvey Meta Data Repository-# April 3 2013 RAND HRS, RAND ELSA, RAND SHARE, RAND KLoSA: Harmonized variables for cross-country, longitudinal study DomainsVariablesIdentifiers, weightsPerson specific identifier; household identifier; couple identifier; spouse identifier; wave status: response indicator; wave status: interview status; sample cohort; whether eligible for sample; sampling weight; person-level analysis weight; household analysis weight (not available for ELSA); country; DemographicsNumber of household respondents; whether couple household; financial respondent; family respondent; whether proxy interview; interview dates; birth date; age at interview (in months and years); place of birth (not available for ELSA); gender; race; education: years of education; education: categorical summary; current marital status: with partnership; current marital status: without partnership; number of marriage; marital history: never married; marital history: number of times divorced; marital history: number of times widowed; marital history: number of times dont know how marriage ended; length of current marriage; length of longest marriage; religion (not available for ELSA); place of birth (not available for ELSA); parental mortality: mother alive; parental mortality: father alive; parental mortality: mothers current age or age at death; parental mortality: fathers current age or age at deathHealth Self-report of health; whether health limits work; activities of daily living (ADLs): some difficulty; instrumental activities of daily living (IADLs): some difficulties; other functional limitations: raw recode; ADL summary: sum ADLs where respondent reports any difficulty; IADL summary: sum IADLs where respondent reports any difficulty; other summary indices: mobility, large muscle, gross fine motor activities; mental health (CESD score); doctor diagnosed health problems: ever have condition; doctor diagnosed health problems: memory-related disease; health behaviors: physical activity or exercise; health behaviors: drinking; health behaviors: smoking (cigarettes); change in health: self-reported health; change in health: functional limitations; change in health: conditions; change in health: memory-related disease; Financial and Housing WealthNet value of business; value of primary residence; value of all mortgage (primary residence); net value of primary residence; net value of real estate; net value of cars; net value of stocks, mutual funds, and investment funds; value of checking, savings, or money market accounts; net value of bonds and bond funds; net value of non-housing financial wealth; total family wealth (respondent & spouse)IncomeIndividual earnings; income from employer pension or annuity; individual income from public pension; individual unemployment benefits or workers compensation (not available for ELSA); family capital income; family government transfer income; total family income (respondent & spouse)Family structureNumber of people living in household; number of children; number of living siblings; number of living parentsEmployment historyCurrently working for pay; whether self-employed; labor force status; hours of work per week at current job; weeks worked per year at job; wage rate; level of physical effort at current job; years of tenure on current job; occupation code for current job; month and year last job endedSurvey Meta Data Repository-# April 3 2013#RAND Harmonized DatasetsOne data file per wavefat format with 1 row per respondentRespondent, Spouse and Household variablesRespondent ID consistent across wavesSurvey Meta Data Repository-# April 3 2013RAND-enhanced Fat Files For Each Interview YearHOUSEHOLD LEVELPreloadCoverscreen (CsR)Family Structure (FamR)Housing (FinR)Assets and Income (FinR)Asset Change (FinR)RESPONDENT LEVELPreloadCoverscreenDemographicsPhysical HealthCognitionParents and SiblingsFunctional LimitationsPhysical MeasuresEmployment (1-6 sections)Health Services and Insurance ExpectationsWidowhood and DivorceWills and Life InsuranceExperimental ModulesEvent History and Social SecurityInterviewer ObservationsRESPONDENT LEVEL FAT FILE FOR 1 YEAR24 Files8 FilesSurvey Meta Data Repository-# April 3 201320#Current Process New StudyThe RAND HRS is the baselineFor each variable in RAND HRSFind the corresponding variable in the new studyIf the variable is exactly equivalentCreate a variable with the same nameIf the variable is not exactly equivalentCreate a related variable and document the differencesSurvey Meta Data Repository-# April 3 2013Current ProcessFor each new wave of dataAll variables are compared with previous waves to see if they are the same or differentIf variable is the sameCreate a variable with the same nameIf variable is differentCreate a related variable and document the differences

Survey Meta Data Repository-# April 3 2013Codebook Sample

Survey Meta Data Repository-# April 3 2013If Studies Distributed DDIHarmonization would be much fasterStudies are based on HRSTheir Questions would already reference HRS, and describe how their questions are differentReference HRS ConceptsWould make it much easier for RAND to evaluate variables and determine if data is comparableSurvey Meta Data Repository-# April 3 2013If RAND Distributed DDICurrentlydistribute a paper codebookuse variable names to show identical/related variablesWith DDIRAND distributes structured metadata describing the differences in variables across studiesTo researchers or back to original studies

Survey Meta Data Repository-# April 3 2013ConclusionIf studies published DDIMetadata and data harmonization would be faster and easierIf RAND published DDIOther researchers/agencies could make better use of RANDs knowledge of the HRS family of studies

Survey Meta Data Repository-# April 3 2013

Survey Meta Data Repository-# April 3 2013#

Recommended

View more >