A Comparative Overview of an Observational Study and a Randomized Trials

Abstract

The main purpose of this article is to show that cause-and-effect conclusions cannot generally be made on the basis of an observational study, and that unlike with observational studies, cause-and-effect conclusions can generally be made on the basis of randomized experiments. These results are exhibited analyzing two famous medical investigations: one observational study and the other randomized experiment. This article may be used in teaching an introductory statistics course, because it contributes and supports the recommendations of The American Statistical Association Guidelines for Assessment and Instruction in Statistics Education (GAISE) committee, which made six recommendations (Aliaga et al. [1]) and (Everson [2]) for teaching introductory statistics; and also, the 2016 GAISE College Report ASA Revision Committee. Cause-and-effect conclusions cannot generally be made on the basis of an observational study, and that unlike with observational studies, cause-and-effect conclusions can generally be made on the basis of randomized experiments.