THE IMPACT OF MISSING LINKAGE DATA IN FAMILY HEALTH RESEARCH: RESULTS FROM THE 1994–1995 NATIONAL HEALTH INTERVIEW SURVEY DISABILITY SUPPLEMENT

Abstract

Family health can be studied using the 1994–1995 National Health Interview Survey Disability Supplement by linking children to their mothers and other family members. However, the data item required to link is missing for 13% of children. We found that unlinked children and their probable mothers differed in many respects from their counterparts who could be linked, and exclusion of these mothers and their children from the analysis could bias results by introducing error due to incomplete coverage of the target population. We developed and validated a simple algorithm to match these children with their probable mother.

Citation

Witt, W.P., Riley, A.W. and Kasper, J.D. (2003), "THE IMPACT OF MISSING LINKAGE DATA IN FAMILY HEALTH RESEARCH: RESULTS FROM THE 1994–1995 NATIONAL HEALTH INTERVIEW SURVEY DISABILITY SUPPLEMENT", Altman, B.M., Barnartt, S.N., Hendershot, G.E. and Larson, S.A. (Ed.) Using Survey Data to Study Disability: Results from the National Health Survey on Disability (Research in Social Science and Disability, Vol. 3), Emerald Group Publishing Limited, Leeds, pp. 73-86. https://doi.org/10.1016/S1479-3547(03)03005-7