May 1st 2013: New model and simulator

I just uploaded the latest version of the simulator. Changes take care of the various ridings where the Green or the Conservatives don't have candidates, as well as 1-2 more independents candidates. I also slighlty changed the regional coefficients for the BC Conservatives as to reflect the fact that their support seems more uniform across the province than expected (by only looking at the 2009 results).

Whenever there is no Green candidate, the model assumes that the BC NDP will get 50% of the votes the Green candidate would have got, while the remaining 50% is simply lost. It's a complete assumption but one that makes sense, at least to me. Indeed, the Green Party voters have a lot in common with the NDP, but not 100% so that some voters will simply not cast a ballot because of the lack of a Green candidate. The same logic applies whenever the BC Conservatives aren't running a candidate, except that the votes then transfer to the BC Liberals (well, 50% of them). Polls generally show that the increased support for the Green comes from the NDP while the swing for the Conservatives is done at the expense of the Liberals. 

Most of the time, these changes don't matter, but you have the usual exception. For instance, the lack of a Conservative candidate in Boundary-Similkameen greatly benefits the Liberals. This riding was indeed one of the few the Conservatives could have won (given their current level of support and the 2009 results). So the controversy of last week which led to the withdrawal of the Conservatives candidate is a huge blow to this party.

Finally, I added the bonus to Green candidate Andrew Weaver. The bonus is 15-points and is taken evenly from the NDP and Liberals. I talked about this in previous posts. It's reasonable to assume that this candidate will get some kind of bonus/boost given his notoriety, but it's really difficult to estimate the magnitude of this boost. For now, I'm being generous and giving 15-points, but I reserve the right to change that.

You can try the new simulator here.

I'll incorporte these changes into the simulations model and publish new projections soon.