#52 Election forecasting models in Germany, with Marcus Gross

Did I mention I like survey data, especially in the context of electoral forecasting? Probably not, as I’m a pretty shy and reserved man. Why are you laughing?? Yeah, that’s true, I’m not that shy… but I did mention my interest for electoral forecasting already!

And before doing a full episode where I’ll talk about French elections (yes, that’ll come at one point), let’s talk about one of France’s neighbors — Germany. Our German friends had federal elections a few weeks ago — consequential elections, since they had the hard task of replacing Angela Merkel, after 16 years in power.

To talk about this election, I invited Marcus Gross on the show, because he worked on a Bayesian forecasting model to try and predict the results of this election — who will get elected as Chancellor, by how much and with which coalition?

I was delighted to ask him about how the model works, how it accounts for the different sources of uncertainty — be it polling errors, unexpected turnout or media events — and, of course, how long it takes to sample (I think you’ll be surprised by the answer). 

We also talked about the other challenge of this kind of work: communication — how do you communicate uncertainty effectively? How do you differentiate motivated reasoning from useful feedback? What were the most common misconceptions about the model?

Marcus studied statistics in Munich and Berlin, and did a PhD on survey statistics and measurement error models in economics and archeology. He worked as a data scientist at INWT, a consulting firm with projects in different business fields as well as the public sector. Now, he is working at FlixMobility.

Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !

Thank you to my Patrons for making this episode possible!

Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Matthew McAnear, Michael Hankin, Cameron Smith, Luis Iberico, Alejandro Morales, Tomáš Frýda, Ryan Wesslen, Andreas Netti, Riley King and Aaron Jones.

Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)

Links from the show:

• German election forecast website: https://www.wer-gewinnt-die-wahl.de/en
• Twitter account of electoral model: https://twitter.com/GerElectionFcst
• German election model code: https://github.com/INWTlab/lsTerm-election-forecast
• LBS #27 -- Modeling the US Presidential Elections, with Andrew Gelman & Merlin Heidemanns: https://www.learnbayesstats.com/episode/27-modeling-the-us-presidential-elections-with-andrew-gelman-merlin-heidemanns