Wednesday, May 28, 2014

2014 Ontario election projection - Week 4



There are now just 15 days remaining in the Ontario provincial election campaign, and with the list of candidates confirmed last week, it's time for another seat projection. Since my projection last week, polls have shown the Liberals inching further and further away from the Tories, but are still in minority territory according to this week's projection.

EKOS and Forum Research continue to show the Liberals with a healthy lead, with EKOS's poll released on Friday showing the Liberals ahead 36-30 (down from 37-30 a week before), and Forum Research's most recent poll showing the Liberals ahead 41-34 (up from 38-35 the previous week). Ipsos, which uses an online panel (as opposed to IVR, which is used by EKOS and Forum) on the other hand continues to show the Tories ahead (35-31), but by a lesser margin than the previous week (39-30). Abacus has released two polls since my last projection, with their most recent poll (released Monday), showing the Liberals ahead 34-32. All of the pollsters show the NDP in third place, with both EKOS and Forum showing the party at 20%, while Abacus and Forum have the NDP and 25% and 28% respectively. Averaged out, the Liberals have a narrow 3-point lead, which is very similar to the 2.2% popular vote margin they led by in the last election. 



For this projection, I made two major tweaks to my model in an effort to correct for some strange results that it had been showing. This change however has created for some new strange results, which I will discuss later. The biggest tweak I made was accounting for incumbents who lost in the last election. Until now, my projection was mostly using the results from the 2011 election to project the results of this election. This is for the most part still true, but I needed to “tweak” the real results in a few of the ridings to reflect the fact that the incumbents in the 2011 election will not be on the 2014 ballot. In previous elections in Ontario, we have seen on countless occasions that there are huge swings when previous incumbents are no longer running. Take Chatham-Kent-Essex for example. In 2007, Liberal incumbent Pat Hoy easily won the seat with 52% of the vote, with the PC candidate winning just 29%. However, he did not run again in 2011, and in an open race, the Tories won the seat 42%-32%. This was a huge swing - one that many projectors (myself excluded) - did not predict correctly. Had Hoy been defeated by the conservatives in 2007, it stands to reason that the Tories, buoyed by incumbency, would have won the riding by an even larger margin in 2011. This effect is what I have tried to account for in this week's projection. To do this, I created estimates based on recent federal election results, to try and predict what the result of the 2011 election would have been with the candidates of 2014 in ridings where the 2011 incumbent lost (and will not be running in this election). These ridings are Prince Edward-Hastings, Perth-Wellington, London-Fanshawe, Lambton-Kent-Middlesex, Kitchener-Conestoga, Huron-Bruce, Algoma-Manitoulin and Hamilton Mountain.

The second major tweak to my model was in ridings that had by-elections since the last general election where the incumbent party was re-elected. In these ridings I replaced an estimated result that I had come up with (based on province-wide polling at the time of the by-elections) with the actual results of the 2011 elections. I did not change my estimates in ridings that did change hands in by-elections since 2011. This tweak in my model affected Vaughan, Ottawa South, Scarborough-Guildwood and Thornhill. I made this change because in these ridings, using the 2011 results in my model are likely to produce a more accurate projection of the election than using an estimate based on the by-election results. This is because possible by-election-specific factors could skew my model, for example in Scarborough-Guildwood, which had a higher than normal NDP vote in their by-election last Summer.  In ridings that did change parties in by-elections, the by-election results are more useful to use in my model, because they have a different incumbent party than in the previous election, meaning comparing the results to an estimate based on subsequent by-elections are more likely to produce an accurate projection.

Finally, I have also taken int account three riding specific polls released this morning byForum Research. These polls were conducted in the three Northwestern ridings of Kenora-Rainy River, Thunder Bay-Atikokan and Thunder Bay-Superior North. My projection model was very close to the poll numbers in Kenora-Rainy River, but overestimated the NDP (and underestimated the Liberal numbers) in the two Thunder Bay ridings. One thing the polls confirm is that Thunder Bay-Atikokan may no longer be considered a target for the NDP, even though they came very close to winning it in 2007.


Projected seat changes (since last week)

Since my last projection, the Liberals have gone down a net two seats, the Tories are down a net three seats, and the NDP is up five. Polls have shown the NDP recovering in Toronto, which has put Davenport, Parkdale—High Park and Trinity—Spadina back in the NDP column, all at the expense of the Liberals. My projection also shows the NDP ahead in Oshawa and Niagara Falls, both at the expence of the Tories which I had ahead last week. Two seats have flipped from the Liberals to the Tories (Perth—Wellington and Haliburton—Kawartha Lakes—Brock) while three have gone in the opposite direction (Cambridge, Scarborough—Guildwood and Northumberland—Quinte West).


Strange results

My projection tweaking really had the affect of pushing Liberal numbers down in ridings where they no longer had the power of incumbency. This resulted in Liberal numbers being re-distributed to other ridings, creating a new slew of surprise results. Perhaps the biggest surprise was in Cambridge, a riding that the Liberals have never won since it was created in 1975. The 2011 election saw a close race in Cambridge, because it was an open seat following the resignation of Tory Gerry Martiniuk. Recent polls have shown the Liberals actually doing better in Southwestern Ontario than in the last election, so this has also helped push Cambridge into the Liberal column. However, I personally feel this is an unlikely projection. In my opinion, the Tories now have the power of incumbency and riding history, and are therefore likely to hold on to the seat.

My tweaks in the 905 region, coupled with the Liberals and NDP polling better there than in the 2011 election has resulted in a couple of surprises as well. One such surprise is in Oshawa where my model now shows the NDP ahead. The NDP has a long history in Oshawa, but have not won the seat since 1990. Since then, the riding has slowly been trending more and more away from the NDP (in general) as the riding has become less blue-collar with more typical suburbanites moving in. Another surprise in the 905 (well, on the edge of the 905) is in Northumberland—Quinte West where my model shows a narrow Liberal lead. Personally, I think that this riding is one that is trending conservative in general (at least based on federal results), which is why I think the Tories will probably win it. However, the Liberals are running Lou Rinaldi again, who was the MPP for the riding from 2003 until 2011, when he lost in a close race to Tory Rob Milligan.

Finally my model continues to show the Liberals in the lead in Barrie. I'm still not convinced this will happen. I think for my next projection, I will come up with new estimated vote totals in ridings that were open seats in 2011 to try and come up with more accurate numbers in my model for those seats. This will at least correct for the odd projections in Barrie and Cambridge. 

Here are my projected numbers for each seat. Ridings are coloured by how they voted in 2011:



Methodology

The basis of my model extrapolates the results of the 2011 election using regional polling averages from recent polls. If a party is polling at double the level they won in 2011, then that party would see its support double in each riding in the region my model. I have also taken into account recent by-elections, but projecting the results of the by-elections backward to the last election based on poll numbers from around the time of each by-election. That is, if a party did 5 points better than polls indicated they would've won in a by-election, then I have made their 2011 result 5 points more than they actually received in 2011. 

I have also made further tweaks to my model based on a number of factors, such as candidate strengths. Please see above for more information about what tweaks I have made. 


Tuesday, May 20, 2014

2014 Ontario election projection - Week 3


Add caption
We are now into week 3 of the Ontario provincial election campaign, and it's now time for my second projection. Since my last projection two weeks ago, we have seen only a little movement in the polls, as voters are still waiting to make up their minds as to who to vote for on June 12. Two weeks ago, polls were split as to whether the Liberals or the Tories were leading in the polls, and that has not changed. In the last week, both EKOS and Forum Research have shown the Liberals ahead (37-30 and 38-35 respectively), while Ipsos shows the Tories with the lead (39-30). All three pollsters have the NDP in the low 20s. Averaged out, we get a small Liberal lead, with numbers that are very similar to the 2011 election. It is therefore no surprise that my projection shows a Liberal minority (or technically a “plurality”), just like in the last election:



For this projection, I factored in polling data from all three of the aforementioned polls: EKOS (released May 16), Ipsos (released May 14) and Forum Research (released May 13).



Changes

My last projection two weeks ago, showed the Tories with a narrow lead, with a plurality of the seats in the 107 Ontario legislature. This week's projection flips that result, now showing the Liberals on top with a plurality. This has come due to a shift in the polls across the province, except in the usually swing-heavy 905 region, which has remained stagnant. In Eastern Ontario, there has been a shift from the Tories to the Liberals, which has been enough to shift Ottawa—Orleans, Ottawa South, Ottawa West—Nepean and Glengarry—Prescott—Russell back into the Liberal column in my projection model. Polls have also seen a shift from the Tories to the Liberals in Southwestern Ontario, putting Brant, Kitchener Centre and Perth—Wellington into the Liberal column. In Central Ontario, the Liberals are polling much stronger than expected, and my projection now shows Haliburton—Kawartha Lakes—Brock in the Liberal column as well. In Toronto, polls are showing a shift from the NDP to the Liberals, giving Davenport and Parkdale—High Park to the Grits in my model. However, in Northern Ontario my projection now shows the NDP back on top in Kenora—Rainy River (which was PC in my last projection) and also in Sudbury (from the Liberals), taking into account aconstituency-level poll conducted there by OraclePoll. To sum, the Liberals have gained a net of 9 seats in the last 2 weeks, the Tories have lost 9 seats while the NDP has had a net of no change.

In addition to factoring in the Subdury riding poll, I have also factored in two other riding polls done by OraclePoll: one done in Sault Ste. Marie (done in conjunction with the Sudbury one) and one done in Don ValleyWest, the riding of Premier Kathleen Wynne.



Odd projection results

Once again, I have yet to take into account local candidacy strengths in my projection, which has resulted in some more bizarre riding projections in my model. I do plan on factoring in a candidacy strength factor into my next projection following this coming Thursday, which marks the final day for candidacy declarations.

With the Liberals polling stronger than usual in the 705 area code, my projection still shows the Grits on top in Barrie as well as in Haliburton—Kawartha Lakes—Brock. The latter is usually a safe Tory seat, but the race was closer than usual in 2011, with the Liberals having an incumbency advantage. This was because they had won the seat in a by-election in 2009 caused by then-PC leader John Tory wishing to enter the legislature after failing to win a seat in the Assembly in the 2007 election. Voters in the usually safe conservative seat said “no” to Tory, and elected Liberal Rick Johnson instead. Johnson is actually running again, but my instinct suggests his support from 2011 is likely to have waned. Meanwhile, in Barrie- the riding is a bit of a Tory-leaning bellwether, so it may not be that inconceivable at this point that the Liberals would have a narrow lead. However, it still seems hard to believe.

Recent polls have shown a resurgence for the Liberals in Southwestern Ontario, which has led my projection to show the Liberals ahead in Perth—Wellington. Until 2011, the riding had been held by Liberal John Wilkinson, who had enough personal popularity to win the seat in 2003 to 2007 despite the riding being your typical rural conservative seat. However his popularity wasn't enough to keep the seat in 2011, when Tory Randy Pettapiece won the seat by just 210 votes. Without Wilkinson on the ballot this year, the Liberals are unlikely to win the seat back.

In Toronto, the populist campaign that the NDP has been running has alienated some progressive voters in the city, resulting in a decline for the NDP in regional polls in the city. This has resulted in my projection showing the Liberals now ahead in Parkdale—High Park and Davenport, as well as Trinity—Spadina, which I think is a more likely result than the other two. Parkdale—High Park is a bit of surprise, as I think its MPP, Cheri DiNovo is quite popular. Davenport is less of a surprise, but I still think the NDP will keep it, as the riding seems to be trending to the party. Another surprise in Toronto continues to be Scarborough—Guildwood. With Tory polling numbers higher than usual in the 416, Scarborough—Guildwood- which saw a close-ish by-election last summer- continues to be in the PC column in my projection. However, I think with the NDP's by-election candidate city councillor Adam Giambrone off the ballot, much of his support will go to the Liberals, giving them this seat.


Here are my projected numbers for each seat. Ridings are coloured by how they voted in 2011:




Methodology

The basis of my model extrapolates the results of the 2011 election using regional polling averages from recent polls. If a party is polling at double the level they won in 2011, then that party would see its support double in each riding in the region my model. I have also taken into account recent by-elections, but projecting the results of the by-elections backward to the last election based on poll numbers from around the time of each by-election. That is, if a party did 5 points better than polls indicated they would've won in a by-election, then I have made their 2011 result 5 points more than they actually received in 2011. (I've only done this for the NDP, the PCs and the Liberals, except for Thornhill where I only did it for the PCs and Liberals).

In the coming weeks, I will be doing further tweaks to my model based on a number of factors, such as candidate strengths. However, candidates are still being nominated, so they have been ignored for the time being. You can say that this model reflects polling data as if all candidates were the same as in 2011 (or recent by-elections).

Tuesday, May 6, 2014

2014 Ontario election projection - Week 1

Week 1 projection map
Last Friday, Ontario NDP leader Andrea Horwath announced that she would no longer be supporting the governing Ontario Liberal Party's budget. This triggered Premier Kathleen Wynne to call an election for the province which will be held on June 13. Officially, the writs will drop on Wednesday, and the campaign will officially begin.

The Liberals have governed the province since 2003, and have been led by Premier Wynne since February 2013 when provincial Liberals elected her leader, replacing the previous leader Premier Dalton McGuinty, who had resigned. Since the last election held in 2011, the Liberals have faced many scandals, such as the “gas plant scandal”. The scandals, as well as a number of corruption controversies threaten their 11-year reign. In the last election held, voters returned a Liberal minority government, with the Liberals winning just one seat shy of a majority. However, subsequent by-election losses have eaten into this minority. Since 2011, the Liberals have counted on the support of the left wing NDP to help keep the government going. On Friday though, the NDP had enough of the scandals and alleged corruption and withdrew their support. The opposition Tories, led by Tim Hudak, have not supported the Liberals since the election. In recent polls, the Progressive Conservatives have traded with the Liberals for the lead among Ontario voters. Up to about a year ago, they consistently led in the polls. Since the last election, the NDP have also polled quite well, compared to their historic third place showings. They even led in one poll conducted in January 2013. Just in the last two weeks however, the NDP have fallen back to their 2011 election numbers in the low 20s.

The beginning of a provincial election campaign means that once again I will attempt to do weekly projections of what the polls are showing, and then map the results to predict what might happen on election day. For my first projection, I will be using two recent polls conducted by EKOS and Forum Research. The EKOS poll released on May 2, showed the Liberals in the lead with 34.7%, the Tories in second at 31.6%, the NDP at 22.2% and 9.4% for the Greens. Forum Research released a poll the next day showing very different numbers. They have the Tories at 38%, the Liberals at 33%, the NDP at 22% and the Greens at 6%. What this means is that the Liberals and Tories are in a statistical tie at the moment, and the parties are close to where they were at in the last election.

Pumping the regional numbers from both polls into my new Ontario election model, I get a very narrow PC lead, with the Tories at 46 seats, the Liberals at 43 and the NDP at 18. This would result in a minority Progressive Conservative government in the 107 seat legislature.



Methodology

The basis of my model extrapolates the results of the 2011 election using regional polling averages from recent polls. If a party is polling at double the level they won in 2011, then that party would see its support double in each riding in the region my model. I have also taken into account recent by-elections, but projecting the results of the by-elections backward to the last election based on poll numbers from around the time of each by-election. That is, if a party did 5 points better than polls indicated they would've won in a by-election, then I have made their 2011 result 5 points more than they actually received in 2011. (I've only done this for the NDP, the PCs and the Liberals, except for Thornhill where I only did it for the PCs and Liberals).

In the coming weeks, I will be doing further tweaks to my model based on a number of factors, such as candidate strengths. However, candidates are still being nominated, so they have been ignored for the time being. You can say that this model reflects polling data as if all candidates were the same as in 2011 (or recent by-elections).


Odd results

I should also mention some strange results in my model that I hope will be corrected before my final projection on election day. Ontario, being my hope province, is the province that I know the most about in terms of its political geography. I like to think that I have a good knowledge of how ridings will vote, even without a model helping me. In 2011, without the aid of a true mathematical model, I correctly predicted the winner of 92% of the ridings. (threehundredeight.com which did use a mathematical model only correctly projected 85% of the ridings). This knowledge will allow me to identify any flaws in my model so that I can come up with “tweaks” to correct them. In this first map, the three strangest results in my opinion are:

* Barrie. My model has the Liberals ahead here thanks to the EKOS poll showing the Liberals ahead in the 705 area code. However, I think the Tories will easily win the seat. The seat is currently held by the Tories, and in the 2011 federal election, the Liberals won just 16% of the vote. In the last election, the race was close, so any strength the Liberals have in the 705 is going to give Barrie to the Liberals in my model. The Liberals haven't nominated a candidate yet, so they don't seem to be prepared to win this one.

* Scarborough—Guildwood. My model has the Tories ahead, thanks to a close by-election result from last August. However, I believe the Liberals will win it. The candidates for both the PCs and the Liberals will be the same as in the by-election, but the wild card is the NDP. In the by-election, the NDP ran city councillor Adam Giambrone who was popular enough to eat into Liberal support in the riding. The NDP have yet to nominate a candidate, and are unlikely to nominate anyone of Giambrone's strength, so Liberal support is likely to go back up to normal levels. This riding has a Liberal history, and is one of the few ridings the federal Liberals were able to win in the 2011 election. I don't see the Tories winning any seats that their federal counterparts didn't win in the last federal election.

* Kenora-Rainy River. Small sample sizes in the 807 area code from the EKOS poll, and strong Tory strength in Forum Research's “Northern Ontario” region (which likely takes in all of the 705 area code which includes large swaths of Tory friendly Central Ontario) are to blame here. Currently, my model shows the PCs ahead in this riding, but its history clearly indicates the riding will likely be won by the NDP. When the NDP won the riding in 2011, it came as somewhat of a surprise to me, as I predicted the Tories would win. After all, the riding overlaps with the federal riding of Kenora which the NDP have failed to take back from the Conservatives in recent elections. However, the NDP ran a strong candidate in Sarah Campbell, who had worked for the riding's previous MPP, former Ontario NDP leader Howard Hampton. Hampton had represented the area since 1987. I suppose the Tories could win it, but it will be a bit of a long shot.


Gains and losses

Compared to the 2011 election, my model shows the Tories picking up 11 seats: Etobicoke-Lakeshore, Scarborough-Guildwood, York Centre, Brant, Kitchener Centre, Glengarry-Prescott-Russell, Ottawa-Orleans, Ottawa South, Ottawa West-Nepean and Niagara Falls (from the Liberals) and Kenora-Rainy River (from the NDP). It has the Liberals picking up two seats: Trinity-Spadina (from the NDP) and Barrie (from the Tories), and it has the NDP picking up three seats: Kitchener-Waterloo (from the Tories) and London West and Windsor-Tecumseh (from the Liberals). The Tories would have a net gain of nine seats, the NDP would have a net gain of one seat while the Liberals would have a net loss of 10 seats. Some of these changes aren't really gains or losses due to recent by-elections (like in Etobicoke-Lakeshore, Kitchener-Waterloo, Windsor-Tecumseh and London West, while in Niagara Falls, the Tory gain is actually from the NDP who won the riding in a recent by-election)

As always, I will be taking in suggestions from readers about ways I can improve my model. So please share with me your opinions. I will also be monitoring electionprediction.org to see what submitters to that site think about how each riding will go.

Here are my projected numbers for each seat. Ridings are coloured by how they voted in 2011.