A two-part meta-analysis of studies examining the relationship of vitamin A supplementation and child mortality. We identified studies by searching the MEDLARS database from 1966 through 1992 and by scanning Current Contents and bibliographies of pertinent articles. All 12 vitamin A controlled trials with data on mortality identified in the search were used in the analysis. Data were independently extracted by two investigators who also assessed the quality of each study using a previously described method. We formally tested for heterogeneity across studies. We pooled studies using the Mantel-Haenszel and the DerSimonian and Laird methods and adjusted for the effect of cluster assignment of treatment groups in community-based studies. Vitamin A supplementation to hospitalized measles patients was highly protective against mortality (DerSimonian and Laird odds ratio, 0.39; 95% confidence interval, 0.22 to 0.66; P = .0004) (part 1 of the meta-analysis). Supplementation was also protective against overall mortality in community-based studies (DerSimonian and Laird odds ratio, 0.70; clustering-adjusted 95% confidence interval, 0.56 to 0.87; P = .001) (part 2 of the meta-analysis). Vitamin A supplements are associated with a significant reduction in mortality when given periodically to children at the community level. Factors that affect the bioavailability of large doses of Vitamin A need to be studied further. Vitamin A supplements should be given to all measles patients in developing countries whether or not they have symptoms of vitamin A deficiency.