SURVEY METHODS
THE CAMPAIGN THAT WASN'T: TRACKING PUBLIC OPINION OVER THE 44TH PARLIAMENT AND THE 2016 ELECTION CAMPAIGN
April, 2018
This book chapter in Double Disillusion: The 2016 Australian Federal Election (Edited by Anika Gauja, Peter Chen, Jennifer Curtin and Juliet Pietsch published with ANU Press) I co-authored with Professor Simon Jackman. This chapter assesses the health of political polling in Australia during the period of 2013-2016 and identifies major movements in voting intentions in this period. It finds that most national polls for two-party preferred voting intentions are reliable however there are systematic underestimations of Labor primary voting intentions and overestimations of Greens voting intentions. Seat-specific polling is comparatively lower quality in contrast to national polling. Most movements in voting intentions in the period studied occurred long before the election campaign exposing the popular media narratives of a "Mediscare" and "Greenslide" as unsubstantiated on the available evidence.
NATIONAL POLLING AND OTHER DISASTERS
2 July 2020
Professor Simon Jackman and I co-authored Chapter 7 in Morrison's Miracle: The 2019 Australian Federal Election (Edited by Anika Gauja, Marian Sawer and Marion Simms with ANU Press) that examines the failure of the national polls conducted before the election to anticipate the result. The national polls—which had been reasonably accurate predictors of election outcomes in recent years—powerfully shaped expectations among the public, journalists and politicians themselves that Labor would win the election. Mansillo and Jackman fit a ‘state-space model’ to the public opinion polls fielded between the 2016 and 2019 federal elections, identifying the estimated trajectory of voting intentions between the two elections, house effects (biases specific to each polling organisation) and the discontinuity in public opinion associated with the transition from Malcolm Turnbull to Morrison as prime minister in August 2018. Polling error in 2019 was largely associated with underestimating Coalition support, while overestimating support for minor parties, especially on the part of YouGov Australia. Some of this polling error could have been anticipated given the observed biases in polls fielded before the 2016 federal election (Jackman and Mansillo 2018), but most of the 2016–19 error was new. What was especially striking about the polling errors in 2019 was that: a) errors in estimates of first preferences did not ‘wash out’ when converted to two-party-preferred estimates, such that b) the resulting errors in the two-party-preferred estimates were large by historical standards, and c) they led to an incorrect prediction as to which party would form the government, at which point larger-than-typical ‘poll error’ became a fully-fledged crisis of confidence in polls and the polling industry. The chapter identifies pollster malpractice through ‘herding’; published polls during the campaign period were far too close, suggesting adjustment of weighting procedures to match estimates from rival polling organisations.
SMALL AREA ESTIMATES OF PUBLIC OPINION: MODEL-ASSISTED POST-STRATIFICATION OF DATA FROM VOTER ADVICE APPLICATIONS
4 January 2019, Conference paper with Simon Jackman & Shaun Ratcliff
Small-area estimates of public opinion are vital for studies of representation but are constrained by the costs of collecting sufficiently large surveys. We use model-assisted post-stratification procedures to repurpose data from a voter advice application (VAA) fielded during the 2016 Australian Federal election campaign. VAAs are typically run with media partners and provide massive samples relative to commercial and academic surveys (in this case, nearly 800,000 respondents). However, considerable bias is generated from self-selection. Our procedure uses Bayesian classification trees to form predictive models of survey responses, which we project onto post-stratification frames for each of Australia’s 150 House of Representatives electoral divisions. We demonstrate the utility of these data and our methodology for district-level estimates using a unique opportunity, a 2017 plebiscite on same-sex marriage, calculating small-area estimates that would have been prohibitively expensive to obtain with conventional surveys.