Skip to content

Peter Ellis on Forecasting Antipodal Elections with Stan

I liked this intro to Peter Ellis from Rob J. Hyndman’s talk announcement:

He [Peter Ellis] started forecasting elections in New Zealand as a way to learn how to use Stan, and the hobby has stuck with him since he moved back to Australia in late 2018.

You may remember Peter from my previous post on his analysis of NZ traffic crashes.

The talk

Speaker: Peter Ellis

Title: Poll position: statistics and the Australian federal election

Abstract: The result of the Australian federal election in May 2019 stunned many in the politics-observing class because it diverged from a long chain of published survey results of voting intention. How surprising was the outcome? Not actually a complete outlier; about a one in six chance, according to Peter Ellis’s forecasting model for Free Range Statistics. This seminar will walk through that model from its data management (the R package ozfedelect, built specifically to support it), the state-space model written in Stan and R that produces the forecasts; and its eventual visualisation and communication to the public. There are several interesting statistical issues relating to how we translate crude survey data into actual predicted seats, and some even more interesting communication issues about how all this is understood by the public. This talk is aimed at those with an interest in one or more of R, Stan, Bayesian modelling and forecasts, and Australian voting behaviour.

Location: 11am, 31 May 2019. Room G03, Learning and Teaching Building, 19 Ancora Imparo Way, Clayton Campus, Monash University [Melbourne, Australia]

The details

Ellis’s blog, Free Range Statistics, has the details of the Australian election model and much much more.

You can also check out his supporting R package, ozfedelect, on GitHub.

From hobbyist to pundit

Ellis’s hobby led to his being quoted by The Economist in a recent article, Did pollsters misread Australia’s election or did pundits?. Quite the hobby.

But wait, there’s more…

There are a lot more goodies on Peter Ellis’s blog, both with and without Stan.

A plea

I’d like to make a plea for a Stan version of the Bradley-Terry model (the statistical basis of the Elo rating system) for predicting Australian Football League matches. It’s an exercise somewhere in the regression sections of Gelman et al.’s Bayesian Data Analysis to formulate the model (including how to extend to ties). I have a half-baked Bradley-Terry case study I’ve been meaning to finish, but would be even happier to get an outside contribution! I’d be happy to share what I have so far.

[edit: fixed spelling of “Elo”]


  1. Adam says:

    On Bradley-Terry models in Stan, have you seen this?

  2. Andrew says:


    Elo, not ELO. Or, better still, Glicko.

    Also this: Adiabatic as I wanna be: Or, how is a chess rating like classical economics?

    I can’t believe that post is 3 years old. I feel like I wrote it just the other day.

    • My bad—I somehow forgot it was named after its creator. Elo’s just Bradley-Terry with online updates and an eccentric scale.

      Thanks for the reminder about that post—Andrew and I discussed the interpretation of the Elo procedure in the comments. The Elo procedure involves an online update that’s kind of like what the engineers call a filter, but more forgetful in that the gradient update only considers one piece of data at a time and doesn’t lower step size a la Robbins-Monro to guarantee asymptotic consistency. Hence it doesn’t asymptotically approach the complete data batch posterior. Glickman’s alternative that Andrew was blogging about is to create a proper time series. Much more compute intensive, but it gives you a lot more control.

  3. Dzhaughn says:

    End antipodalizationism! We should support repodalifying minoritized hemispheric communities.

  4. Joshua Pritikin says:

    I’ve got a basic Bradley-Terry model plus multivariate covariance and factor models. It should be up on CRAN in a few days,

Leave a Reply