Researchers looked at studies that were reported in newspapers with the goal of determining whether initial studies had results that could be reproduced. Reproducibility of results means that subsequent analysis confirms the conclusion of the original study. Primary studies are studies where the researchers come up with a research objective, clearly state the goals of the study and population, describe the research method, test the research hypotheses, and draw conclusions.
(a) Among the 156 primary studies reported by newspapers, 76 had results that were validated by subsequent analysis. Does this suggest less than a majority of initial studies reported by newspapers have their results validated by subsequent analysis?
(b) In the article, a null effect is defined as any study where the evidence is not in favor of the research (alternative) hypothesis. Put another way, a null effect means the null hypothesis of “no effect” or “no difference” is not rejected. Among 1475 studies reported in newspapers, 75 reported a null effect. Estimate with 95% confidence the proportion of studies in which there is a null effect (such as a particular behavior does not result in a higher risk of disease).
(c) What does the result in part (b) suggest about the likelihood of a research study being published with a null effect? Include a discussion of the incentive to have studies that are in favor of the research (alternative) hypothesis.