Beyond Baseline and Follow-up : The Case for More T in Experiments

Vista sencilla de ítem
dc.creatorMcKenzie, David
dc.date2012-03-19T18:01:51Z
dc.date2012-03-19T18:01:51Z
dc.date2011-04-01
dc.date.accessioned2026-07-01T01:02:53Z
dc.descriptionThe vast majority of randomized experiments in economics rely on a single baseline and single follow-up survey. If multiple follow-ups are conducted, the reason is typically to examine the trajectory of impact effects, so that in effect only one follow-up round is being used to estimate each treatment effect of interest. While such a design is suitable for study of highly autocorrelated and relatively precisely measured outcomes in the health and education domains, this paper makes the case that it is unlikely to be optimal for measuring noisy and relatively less autocorrelated outcomes such as business profits, household incomes and expenditures, and episodic health outcomes. Taking multiple measurements of such outcomes at relatively short intervals allows the researcher to average out noise, increasing power. When the outcomes have low autocorrelation, it can make sense to do no baseline at all. Moreover, the author shows how for such outcomes, more power can be achieved with multiple follow-ups than allocating the same total sample size over a single follow-up and baseline. The analysis highlights the large gains in power from ANCOVA rather than difference-in-differences when autocorrelations are low and a baseline is taken. The paper discusses the issues involved in multiple measurements, and makes recommendations for the design of experiments and related non-experimental impact evaluations.
dc.formatapplication/pdf
dc.formattext/plain
dc.identifierhttp://www-wds.worldbank.org/external/default/main?menuPK=64187510&pagePK=64193027&piPK=64187937&theSitePK=523679&menuPK=64187510&searchMenuPK=64187283&siteName=WDS&entityID=000158349_20110425104143
dc.identifierhttps://hdl.handle.net/10986/3403
dc.identifier10.1596/1813-9450-5639
dc.identifier.urihttp://hdl.handle.net/123456789/414667
dc.languageEnglish
dc.relationPolicy Research working paper ; no. WPS 5639
dc.rightsCC BY 3.0 IGO
dc.rightshttp://creativecommons.org/licenses/by/3.0/igo/
dc.rightsWorld Bank
dc.subjectAUTOCORRELATION
dc.subjectBOOTSTRAP
dc.subjectCHOLESTEROL
dc.subjectCLINICAL TRIALS
dc.subjectCONFIDENCE INTERVALS
dc.subjectCORRELATIONS
dc.subjectCOVARIANCE
dc.subjectDEVELOPMENT ECONOMICS
dc.subjectDEVELOPMENT POLICY
dc.subjectDEVELOPMENT RESEARCH
dc.subjectDIARRHEA
dc.subjectECONOMETRICS
dc.subjectECONOMIC OUTCOMES
dc.subjectECONOMICS
dc.subjectECONOMICS RESEARCH
dc.subjectEQUATIONS
dc.subjectESTIMATORS
dc.subjectEXPERIMENTAL IMPACT EVALUATION
dc.subjectEXPERIMENTAL IMPACT EVALUATIONS
dc.subjectEXPERIMENTAL STUDIES
dc.subjectEXPERIMENTS
dc.subjectEXTERNALITIES
dc.subjectFIELD EXPERIMENTS
dc.subjectFINANCIAL CRISIS
dc.subjectFIXED COSTS
dc.subjectHEADACHES
dc.subjectHYPOTHESES
dc.subjectINCOME
dc.subjectINVENTORY
dc.subjectLAW OF LARGE NUMBERS
dc.subjectLEAST SQUARES REGRESSION
dc.subjectMARGINAL COST
dc.subjectMEASUREMENT ERRORS
dc.subjectMEDICINE
dc.subjectPHYSICAL HEALTH
dc.subjectPRECISION
dc.subjectRANDOMIZATION
dc.subjectRESEARCH METHODOLOGY
dc.subjectRESEARCH WORKING PAPERS
dc.subjectRESEARCHERS
dc.subjectSAMPLE SIZE
dc.subjectSIGNIFICANCE LEVEL
dc.subjectSTANDARD DEVIATION
dc.subjectSTATA
dc.subjectTIME SERIES
dc.subjectTREATMENT
dc.subjectVALIDITY
dc.subjectVARIABILITY
dc.subjectWATER TREATMENT
dc.subjectWEALTH
dc.titleBeyond Baseline and Follow-up : The Case for More T in Experiments

Archivos

Colecciones

AgroKnow