RESUMO
Rothman (Epidemiology 1990;1:43-46) recommends against adjustments for multiple comparisons. Implicit in his recommendation, however, is an assumption that the sole objective of the data analysis is to report and scientifically interpret the data. We concur with his recommendation when this assumption is correct and one is willing to abandon frequentist interpretations of the summary statistics. Nevertheless, there are situations in which an additional or even primary goal of analysis is to reach a set of decisions based on the data. In such situations, Bayes and empirical-Bayes adjustments can provide a better basis for the decisions than conventional procedures.
Assuntos
Teorema de Bayes , Métodos Epidemiológicos , El Salvador/epidemiologia , Humanos , Modelos Estatísticos , Prevalência , Risco , Toxoplasmose/epidemiologiaRESUMO
For the period 1973 to 1977, a total of 536 cases of anencephalus and spina bifida were ascertained in Los Angeles County, California, a low-risk area, and compared with a 2 per cent random sample of all live births in the county. Women with Spanish surnames had an elevated risk for anencephalus and to a lesser extent for spina bifida; Blacks were at lowest risk, especially for spina bifida. The occurrence of a previous fetal death was a strong risk factor for anencephalus but there was no association between socio-economic status and either of the defects. Advanced maternal age was a stronger risk factor for spina bifida than for anencephalus but, as in other studies in low-risk areas, no increased risk was observed among teenage mothers. Paternal age did not show any independent association after controlling for mother's age. Finally, the association of high birth-order with the birth defects was weakened greatly after simultaneous adjustment for age and ethnicity.