The Problem With Replication in Social Science

3min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

A lot of books based on social science are littered with references to studies that didn't replicate. Do you think that was a kind of problem of that era and that we're kind of moved past that now? I'm learning some things that we thought were true before, but don't turn out to be true or don't turned out to be as true as to the extent that they were initially published. That said, the problem is not solved as part of the human condition," he says.

Read the full transcript here.

What makes studying humans harder than studying other parts of the universe? Is social science currently improving its rigor, relevance, and self-reflection? Is it improving its predictive power over time? Why have sample sizes historically been so small in social science studies? Is social science actually able to accumulate knowledge? Have social scientists been able to move the "needle" on real-world problems like vaccine adoption? Is social science becoming more diverse? Specifically, does social science have a political bias? Are universities in crisis? Do the incentive structures in universities make them difficult or even impossible to reform?

Matt Grossmann is Director of the Institute for Public Policy and Social Research and Professor of Political Science at Michigan State University. He is also Senior Fellow at the Niskanen Center and a Contributor at FiveThirtyEight. He has published analysis in The New York Times, The Washington Post, and Politico, and hosts the Science of Politics podcast. He is the author or co-author of How Social Science Got Better, Asymmetric Politics, Red State Blues, The Not-So-Special Interests, Artists of the Possible, and Campaigns & Elections, as well as dozens of journal articles. You can find more about him on his website.

Staff