Polling post mortem
Polling became a big issue for media in the recent Ontario campaign thanks to a highly critical letter sent out by Ipsos Reid executives in mid-September, which called other pollsters "hucksters selling methodological snake oil", adding journalists were "no mere dupes in this process." So, now that the results are in, how did pollsters do at predicting the outcome?
Polling became a big issue for media in the recent Ontario campaign thanks to a highly critical letter sent out by Ipsos Reid executives in mid-September, which called other pollsters "hucksters selling methodological snake oil", adding journalists were "no mere dupes in this process."
So, now that the results are in, how did pollsters do at predicting the outcome?
Well, interestingly, Ipsos was one of the worst. It placed in the bottom three with 10.2 points total error.
As Eric Grenier writes in today's Globe and Mail:
Ironically, in light of the controversy stirred up in the opening days of the campaign, the two most accurate polls came from the newest firms: Forum Research, with a total error of only 1.6 points and using the IVR method, and Abacus Data, with a total error of 4.4 points using an online panel.
He adds:
[node:ad]Generally speaking, the polls performed well Thursday night. They accurately estimated Liberal support and those reporting on the very last days of the campaign indicated that the Tories were closing the gap in the final hours.
Grenier also said that no one pollster's methods stood out. A couple used the traditional phone method, a couple used interactive voice response method, and two used online panels.
Some of the pollsters — Ekos, Angus Reid, and Abacus — weighed in with their own wrap-ups. Nothing yet from Ipsos.
