May 16th 2013: What if I had used only the best poll?

Among all the pollsters for the last BC election, Forum did clearly better than anyone else. Pollsters seem to go for the "late swing" excuse again, yet the best polling firm conducted its poll... one week from the election! Forum wasn't spot on, but they were close enough that a late swing could indeed explain the discrepancies. Kudos to this firm as they were already the only one to catch the much closer race in Alberta (while still being off though) and the only one to have the Liberals much higher than anybody else in Quebec. So while not perfect, it seems that Forum polls are at least within the margins of error (or very close).

So what would the projections have looked like had I used only Forum's numbers?
Well, the model and simulations would still have predicted a BCNDP victory, but the actual outcome would have been much more likely to happen. When I used an average of all recent polls, I had the BC Liberals with around 13-14% of winning. But even in the scenarios where Christy Clark was winning, 50 seats was really at the extreme of the intervals (and outside of the 95% confidence intervals).

But when using Forum's numbers only, here are the seat ranges (at 95% confidence) for each party:

BC Liberals: 30-52
BC NDP: 33-54
BC Green: 0-1
BC Conservatives: 0

As you can see, the actual outcome was indeed in the 95% confidence intervals. Remember, when we do our simulations, we account for the uncertainty due to polls as well as the electoral system. Statistically speaking, it'd have been acceptable.

Moreover, the probability of winning would have been 43% for the BC Liberals and 57% for the BC NDP. So again, while not spot on, it'd have been much closer to reality.

I think that from now on, I'll publish final projections based on Forum only, just as additional information. Although, I might just have jinxed the good streak for this firm!

Share this

Related Posts

Previous
Next Post »