Ré suméA-t-on né cessairement besoin de donné es longitudinales pour infé rer des relations causales ? Il est généralement admis que les causes précèdent leurs effets dans le temps. Cela justifie usuellement la préférence pour les études longitudinales par rapport aux études transversales, parce que les premières permettent la modè-lisation du processus dynamique engendrant le résultat, tandis que les secondes ne le peuvent pas. Les partisans de l'approche longitudinale proposent deux justifications interdépendantes : (i) l'inférence causale nécessite le suivi des mêmes personnes au fil du temps, et (ii) aucune inférence causale ne peut être tirée de données transversales. Dans cet article, nous remettons en question ce point de vue et proposons des objections à ces deux arguments. Nous soutenons également que la possibilité d'établir des relations de cause à effet ne dépend pas tant de l'utilisation de données longitudinales ou transversales, mais plutô t de savoir si la stratégie de modélisation est d'ordre structurel ou non.
AbstractIt is generally admitted that causes precede their effects in time. This usually justifies the preference for longitudinal studies over cross-sectional ones, because the former allow
"Differential mortality in Norway has been studied on the basis of a sample of data derived from the linkage of the 1960, 1970, and 1980 censuses to vital registration records. Based on the hypothesis that the determinants of survival act in interaction, two models are proposed. The first is based on states defined at each observation period by the conjunction of attributes characterizing each individual. The second model considers the chronological order of the states. Logistic regression applied to the latter shows that the most favourable male and female life trajectories are those for married people belonging to rather privileged categories. There are however some differences by sex, as favourable trajectories concern both economically inactive females and employees." (SUMMARY IN FRE)
This paper deals both with the issues of confounding and of control, as the definition of a confounding factor is far from universal and there exist different methodological approaches, ex ante and ex post, for controlling for a confounding factor. In the first section the paper compares some definitions of a confounder given in the demographic and epidemiological literature with the definition of a confounder as a common cause of both treatment/exposure and response/outcome. In the second section, the paper examines confounder control from the data collection viewpoint and recalls the stratification approach for ex post control. The paper finally raises the issue of controlling for a common cause or for intervening variables, focusing in particular on latent confounders.
This study presents some new results on parental age as a risk factor for child survival. The study is based on individual registration forms for live births and infant deaths collected in Hungary from 1984 to 1988. Logistic regression models have been fitted for early neonatal and neonatal mortality on the one hand, and post-neonatal mortality on the other hand. Children of older males and females have significantly higher early neonatal and neonatal mortality rates compared to those of younger males and females. The impact of age of both parents remains, however, slighter than that of other biological characteristics such as previous number of fetal deaths, induced abortions, or live births. The authors discuss possible biological explanations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.