Click here for search results
Attrition in longitudinal household survey data - some tests for three developing-country samples, Volume 1
Author:Alderman, Harold; Behrman, Jere R.; Kohler, Hans-Peter; Maluccio, John A.; Cotts Watkins, Susan; Country:Kenya; Bolivia; South Africa;
Date Stored:2000/11/04Document Date:2000/09/30
Document Type:Policy Research Working PaperSubTopics:Scientific Research & Science Parks; Science Education; Poverty Assessment; Health Monitoring & Evaluation; Statistical & Mathematical Sciences; Public Health Promotion; Educational Sciences
Language:EnglishMajor Sector:(Historic)Multisector
Region:Africa; Latin America & CaribbeanReport Number:WPS2447
Sub Sectors:Non-Sector SpecificCollection Title:Policy, Research working paper ; no. WPS 2447
Volume No:1  

Summary: For capturing dynamic demographic relationships, longitudinal household data can have considerable advantages over more widely used cross-sectional data. But because the collection of longitudinal data may be difficult and expensive, analysts must assess the magnitudes of the problems, specific to longitudinal, but not to cross-sectional data. One problem that concerns many analysts is that sample attrition may make the interpretation of estimates problematic. Such attrition may be especially severe where there is considerable migration between rural, and urban areas. And attrition is likely to be selective on such characteristics as schooling, so high attrition is likely to bias estimates. The authors consider the extent, and implications of attrition for three longitudinal household surveys from Bolivia, Kenya, and South Africa that report very high annual attrition rates between survey rounds. Their estimates indicate that: 1) the means for a number of critical outcome, and family background variables differ significantly between those who are lost to follow-up, and those who are re-interviewed. 2) A number of family background variables are significant predictors of attrition. 3) Nevertheless, the coefficient estimates for standard family background variables in regressions, and probit equations for the majority of outcome variables in all three data sets, are not significantly affected by attrition. So attrition is apparently not a general problem for obtaining consistent estimates of the coefficients of interest for most of these outcomes. These results, which are very similar to those for industrial countries, suggest that multivariate estimates of behavioral relations may not be biased because of attrition. This wold support the collection of longitudinal data.

Official Documents
Official, scanned versions of documents (may include signatures, etc.)
File TypeDescriptionFile Size (mb)
PDF 46 pagesOfficial version*3.22 (approx.)
TextText version**
How To Order
Light-Weight Documents
Lighter (less MB) documents which may or may not be the final, official version
File TypeDescriptionFile Size (mb)
PDF 42 pagesWPS24470.19

* The official version is derived from scanning the final, paper copy of the document and is the official,
archived version including all signatures, charts, etc.
** The text version is the OCR text of the final scanned version and is not an accurate representation of the final text.
It is provided solely to benefit users with slow connectivity.

Permanent URL for this page: