Volume 5 - Article 4 | Pages 79-124

Attrition in Longitudinal Household Survey Data: Some Tests for Three Developing-Country Samples

By Harold Alderman, Jere Behrman, Hans-Peter Kohler, John A. Maluccio, Susan Watkins

Print this page  Facebook  Twitter


Date received:04 Apr 2001
Date published:13 Nov 2001
Word count:7480
Keywords:attrition, developing countries, longitudinal surveys, panel data


Longitudinal household data can have considerable advantages over much more widely used cross-sectional data for capturing dynamic demographic relationships. Because the collection of longitudinal data may be difficult and expensive, analysts need to assess the magnitude of the particular problems associated with longitudinal but not with cross-sectional data. One problem that has concerned many analysts is that sample attrition may make the interpretation of estimates problematic.
Such attrition may be particularly severe in areas where there is considerable migration between rural and urban areas. Many analysts share the intuition that attrition is likely to be selective on characteristics such as schooling and thus that high attrition is likely to bias estimates. This paper considers the extent and implications of attrition for three longitudinal household surveys from Bolivia, Kenya, and South Africa that report very high per-year attrition rates between survey rounds.
Our estimates indicate that: (a) 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; (b) a number of family background variables are significant predictors of attrition; but (c) nevertheless, the coefficient estimates for standard family background variables in regressions and probit equations for the majority of the outcome variables in all three data sets are not affected significantly by attrition.
Therefore, attrition apparently is 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 developed countries, suggest that multivariate estimates of behavioral relations may not be biased due to attrition and thus support the collection of longitudinal data.

Author's Affiliation

Harold Alderman - World Bank, United States of America [Email]
Jere Behrman - University of Pennsylvania, United States of America [Email]
Hans-Peter Kohler - University of Pennsylvania, United States of America [Email]
John A. Maluccio - International Food Policy Research Institute (IFPRI), United States of America [Email]
Susan Watkins - University of Pennsylvania, United States of America [Email]

Other articles by the same author/authors in Demographic Research

» The population-level impact of public-sector antiretroviral therapy rollout on adult mortality in rural Malawi
Volume 36 - Article 37

» Intergenerational Transfers in the Era of HIV/AIDS: Evidence from Rural Malawi
Volume 27 - Article 27

» Out of Sync? Demographic and other social science research on health conditions in developing countries
Volume 24 - Article 2

» Asking God about the date you will die: HIV testing as a zone of uncertainty in rural Malawi
Volume 23 - Article 32

» The Likoma Network Study: Context, data collection and initial results
Volume 21 - Article 15

» Subjective expectations in the context of HIV/AIDS in Malawi
Volume 20 - Article 31

» The Malawi Diffusion and Ideational Change Project 2004-06: Data collection, data quality, and analysis of attrition
Volume 20 - Article 21

» Overestimating HIV infection: The construction and accuracy of subjective probabilities of HIV infection in rural Malawi
Volume 20 - Article 6

» A summary of Special Collection 1: Social Interactions and HIV/AIDS in Rural Africa
Volume 9 - Article 12

» The Fertility Pattern of Twins and the General Population Compared: Evidence from Danish Cohorts 1945-64
Volume 6 - Article 14

» Tempo-Adjusted Period Parity Progression Measures: Assessing the Implications of Delayed Childbearing for Cohort Fertility in Sweden, the Netherlands and Spain
Volume 6 - Article 7

» Tempo-Adjusted Period Parity Progression Measures, Fertility Postponement and Completed Cohort Fertility
Volume 6 - Article 6

» Frailty Modelling for Adult and Old Age Mortality: The Application of a Modified DeMoivre Hazard Function to Sex Differentials in Mortality
Volume 3 - Article 8

» Empirical Assessments of Social Networks, Fertility and Family Planning Programs: Nonlinearities and their Implications
Volume 3 - Article 7

» Gender Preferences for Children in Europe: Empirical Results from 17 FFS Countries
Volume 2 - Article 1

» Introduction to "Research on Demographic Aspects of HIV/AIDS in Rural Africa"
Special Collection 1 - Article 1

» How do we know we need to control for selectivity?
Special Collection 1 - Article 4

» "Moving" and Marrying: Modelling HIV Infection among Newly-weds in Malawi
Special Collection 1 - Article 7

» Talking about AIDS: The influence of communication networks on individual risk perceptions of HIV/AIDS infection and favored protective behaviors in South Nyanza District, Kenya
Special Collection 1 - Article 13

Most recent similar articles in Demographic Research

» The long-term determinants of marital fertility in the developed world (19th and 20th centuries): The role of welfare policies
Volume 36 - Article 42    | Keywords: panel data

» Functional limitation trajectories and their determinants among women in the Philippines
Volume 36 - Article 30    | Keywords: developing countries

» Multiple imputation for demographic hazard models with left-censored predictor variables: Application to employment duration and fertility in the EU-SILC
Volume 35 - Article 38    | Keywords: panel data

» Attrition in the Austrian Generations and Gender Survey: Is there a bias by fertility-relevant aspects?
Volume 31 - Article 16    | Keywords: attrition

» Investigating healthy life expectancy using a multi-state model in the presence of missing data and misclassification
Volume 30 - Article 42    | Keywords: panel data