Show simple item record

2017-02-28Diskussionpapier DOI: 10.18452/18691
Testing Missing at Random using Instrumental Variables
dc.contributor.authorBreunig, Christoph
dc.date.accessioned2018-01-10T15:47:19Z
dc.date.available2018-01-10T15:47:19Z
dc.date.issued2017-02-28
dc.identifier.urihttp://edoc.hu-berlin.de/18452/19401
dc.description.abstractThis paper proposes a test for missing at random (MAR). The MAR assumption is shown to be testable given instrumental variables which are independent of response given potential outcomes. A nonparametric testing procedure based on integrated squared distance is proposed. The statistic’s asymptotic distribution under the MAR hypothesis is derived. In particular, our results can be applied to testing missing completely at random (MCAR). A Monte Carlo study examines finite sample performance of our test statistic. An empirical illustration analyzes the nonresponse mechanism in labor income questions.eng
dc.language.isoeng
dc.publisherHumboldt-Universität zu Berlin
dc.subjectIncomplete dataeng
dc.subjectmissing-data mechanismeng
dc.subjectselection modeleng
dc.subjectnonparametric hypothesis testingeng
dc.subjectconsistent testingeng
dc.subjectinstrumental variableeng
dc.subjectseries estimationeng
dc.subject.ddc330 Wirtschaft
dc.titleTesting Missing at Random using Instrumental Variables
dc.typeworkingPaper
dc.identifier.urnurn:nbn:de:kobv:11-110-18452/19401-7
dc.identifier.doihttp://dx.doi.org/10.18452/18691
local.edoc.container-titleSonderforschungsbereich 649: Ökonomisches Risiko
local.edoc.pages31
local.edoc.type-nameDiskussionpapier
local.edoc.institutionWirtschaftswissenschaftliche Fakultät
local.edoc.container-typeseries
local.edoc.container-type-nameSchriftenreihe
local.edoc.container-volume2017
local.edoc.container-issue7
local.edoc.container-erstkatid2195055-6

Show simple item record