Science Magazine officially retracts study on gay equality canvassing

Science Magazine has officially retracted a study that argued a single conversation could change a person’s opinion on a divisive issues, namely gay marriage.

The December 2014 study showed that people who opposed same-sex marriage were more likely to switch their opinion if they had a 20-minute chat with a gay canvasser versus a straight one.

This American Life, BuzzFeed News and The Washington Post were among a plethora of news outlets that covered the original report.

Last week, scientists raised several questions over statistical irregularities in the report. As described by Virginia Hughes of BuzzFeed:

“The problems came to light after three other researchers tried, and failed, to replicate the study. David Broockman, of Stanford, Joshua Kalla, of the University of California, Berkeley, and Peter Aronow of Yale found eight statistical irregularities in the data set. No one of these would by itself be proof of wrongdoing, they wrote, but all of them collectively suggest that “the data were not collected as described.”

This team initially presented their findings to the study’s senior author, political scientist Donald Green of Columbia University, who subsequently confronted his co-author: UCLA graduate student Michael LaCour. Green said that LaCour confessed to falsifying the data, and the Columbia professor requested that Science Magazine pull the article.

LaCour had performed the majority of the field work on the report, ostensibly collecting thousands of surveys from canvassers in Southern California and raising funds from the Williams Institute, the Ford Foundation, and the Evelyn and Walter Haas Jr. Fund. Along with citing the report’s statistical dilemmas, Science Magazine’s retraction confirmed early suggestions that LaCour falsified his sponsorships as well.

Retraction Watch was the first group to report on the study’s irregularities. Details of how they discovered the scoop are available here.