Dealing with earnings bracket responses in household surveys - How sharp are midpoint imputations?

Simple item page
dc.contributor.authorvon Fintel D.
dc.date.accessioned2011-05-15T15:57:40Z
dc.date.available2011-05-15T15:57:40Z
dc.date.issued2007
dc.description.abstractEarnings functions form the basis of numerous labour market analyses. Non-response (particularly among higher earners) may, however, lead to the exclusion of a significant proportion of South Africa's earnings base. Earnings brackets built into surveys intend to maintain response rates. Econometric tools to incorporate brackets vary from "simplistic" imputation to interval regressions. Coefficient differences are investigated here to establish reliable remedies. Monte-Carlo simulations suggest that "simple" methods fail only under extreme skewness and when a substantial number of right-censored observations appear in the sample. Testing procedures applied to LFS data reveal that in practice coefficients are virtually invariant to the proposed methods. © 2007 The Author; Journal compilation © Economic Society of South Africa 2007.
dc.description.versionArticle
dc.identifier.citationSouth African Journal of Economics
dc.identifier.citation75
dc.identifier.citation2
dc.identifier.issn382280
dc.identifier.other10.1111/j.1813-6982.2007.00122.x
dc.identifier.urihttp://hdl.handle.net/10019.1/10528
dc.subjectdata processing
dc.subjecteconometrics
dc.subjecthousehold survey
dc.subjectlabor market
dc.subjectMonte Carlo analysis
dc.subjectsimulation
dc.subjectAfrica
dc.subjectSouth Africa
dc.subjectSouthern Africa
dc.subjectSub-Saharan Africa
dc.titleDealing with earnings bracket responses in household surveys - How sharp are midpoint imputations?
dc.typeArticle
Files
Collections
Stellenbosch University - Scopus Publications