Topics and controversies in biostatistics
← vista completaPublished on February 4, 2015 | http://doi.org/10.5867/medwave.2015.01.6075
Logistic regression against a divergent Bayesian network
La regresión logística frente a una red bayesiana divergente
Abstract
This article is a discussion about two statistical tools used for prediction and causality assessment: logistic regression and Bayesian networks. Using data of a simulated example from a study assessing factors that might predict pulmonary emphysema (where fingertip pigmentation and smoking are considered); we posed the following questions. Is pigmentation a confounding, causal or predictive factor? Is there perhaps another factor, like smoking, that confounds? Is there a synergy between pigmentation and smoking? The results, in terms of prediction, are similar with the two techniques; regarding causation, differences arise. We conclude that, in decision-making, the sum of both: a statistical tool, used with common sense, and previous evidence, taking years or even centuries to develop; is better than the automatic and exclusive use of statistical resources.
