Reweighting South African national household survey data to create a consistent series over time: A cross-entropy approach

Simple item page
dc.creatorBranson, Nicola
dc.creatorWittenberg, Martin
dc.date2014-06-04T10:35:09Z
dc.date2014-06-04T10:35:09Z
dc.date2014
dc.date.accessioned2015-05-28T10:06:36Z
dc.date.available2015-05-28T10:06:36Z
dc.date.issued2015-05-28
dc.descriptionIn the absence of established longitudinal panel surveys in South Africa, national cross-sectional household survey data are frequently used to analyse change. When these data are stacked side by side, however, inconsistencies both in time trends and between household- and person-level data are found. This study uses a new set of weights calibrated to the Actuarial Society of South Africa 2003 model projected totals using a cross-entropy estimation approach. These weights are favoured because they produce consistent demographic and geographic trends. The calculated weights are similar to the initial sample weights (and hence retain the survey design benefits) but match to a series of age-sex-race and province marginal totals that are consistent over time. The weights are publicly available for the 14-year period between 1994 and 2007.
dc.identifierBranson, N. and M. Wittenberg (2014). Reweighting South African National Household Survey Data to Create a Consistent Series Over Time: A Cross-Entropy Estimation Approach, South African Journal of Economics, Vol 82(1) pages 19–38.
dc.identifierhttp://onlinelibrary.wiley.com/doi/10.1111/saje.12017/abstract
dc.identifierhttp://hdl.handle.net/11090/699
dc.identifier.ris TY - Journal Article DA - 2015-05-28 DB - OpenUCT DP - University of Cape Town KW - Survey data KW - Household survey data KW - Weights KW - Survey data weights KW - Cross-sectional data KW - Cross-entropy estimation LK - https://open.uct.ac.za PB - University of Cape Town PY - 2015 T1 - Reweighting South African national household survey data to create a consistent series over time: A cross-entropy approach TI - Reweighting South African national household survey data to create a consistent series over time: A cross-entropy approach UR - http://hdl.handle.net/11090/699 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11090/699
dc.languageen
dc.publisherSouth African Journal of Economics
dc.publisher.departmentSALDRUen_ZA
dc.publisher.facultyFaculty of Commerceen_ZA
dc.publisher.institutionUniversity of Cape Town
dc.subjectSurvey data
dc.subjectHousehold survey data
dc.subjectWeights
dc.subjectSurvey data weights
dc.subjectCross-sectional data
dc.subjectCross-entropy estimation
dc.titleReweighting South African national household survey data to create a consistent series over time: A cross-entropy approach
dc.typeJournal Article
uct.type.publicationResearchen_ZA
uct.type.resourceArticleen_ZA
Files
Collections
Reports