This year’s CPRsouth focused on systematic reviews. Completed and in-process studies were presented and a whole day of the Young Scholars’ Program was devoted to the topic. On the last day, I was tasked with moderating a panel of those who had worked on SRs. One reason we did this was to ensure that the weaknesses of the tool, as well as its strengths, were fully explored.
Here is the first question I posed to the panel:
1. Nate Silver achieved fame by correctly predicting the winner of 49 of the 50 states in the 2008 US Presidential election. The only state he missed was Indiana, which went for Barack Obama by one percentage point. He correctly predicted the winner of all 35 U.S. Senate races that year. Silver does not conduct any surveys of his own. He systematically aggregates multiple state-level surveys in ways that reduce the effect of bias in each.
a. Do you see a similarity with SRs?
b. In both cases the screening and selection of eligible surveys is critical. Is the bias in SR hidden in the screens?
The full set is here.