April 25th 2013: BC projections by the numbers

April 25th 2013: BC projections by the numbers
Once in a while, I'll switch from my usually text heavy posts to straight up, pure numbers. This section is therefore called (unoriginally) By the Numbers.


Outcome
Probability
NDP victory
100%
NDP majority
100%
NDP with 70 seats or more
6.4%
NDP with 50 seats or less
6%
Lib with 10 seats or less
1.3%
Lib with 20 seats or less
48%
Cons with at least 1 seat
44%
Cons with 5 seats or more
1.4%
Green with at least 1 seat
1.2%



Seats
Min Liberals
7
Max Liberals
40
Max Conservative
8
Max green
1



Other
Chances of Christy Clark being elected

51%
   
# ridings where all 4 parties can win

1 (West Vancouver- Sea to sky)
# riding where one party is projected to win 100% of the time
35 (32 NDP, 3 Lib)


Also, here are the latest projections, using the poll from Angus-Reid released today (April 24th). Riding-by-riding projections are here. The 3 points picked-up by the Liberals are really helping. Indeed, with these numbers, there is one scenario (out of 1000) where the BC Liberals would get 40 seats while the BC NDP would get 43. So the race is slightly closer now. If the trend goes on next week, we could actually have some suspense.

25 avril 2013: Le potentiel de la CAQ et de QS

25 avril 2013: Le potentiel de la CAQ et de QS
Léger a publié un nouveau sondage (je cherche le lien, vous pouvez trouver les chiffres sur twitter) montrant une course bien plus serrée que dans le dernier sondage Crop. En utilisant les chiffres du Léger,  le modèle prédit une courte victoire PLQ avec 57 sièges, devant le PQ avec 56. La CAQ serait toujours troisième avec 8. Quant à QS, ce parti décrocherait un 3e siège (dans Sainte-Marie-Saint-Jacques). Comme d'habitude, vous pouvez voir ces chiffres et les projections détaillées en utilisant le simulateur. En termes de probabilités, le PLQ aurait 60% de chances de gagner, contre 40% au Québec.

Au lieu de parler de ce sondage en détails, je voudrais parler du potentiel pour la CAQ et QS. Ces deux plus petits partis se trouvent dans des situations très différentes. Pour la CAQ, être 3e à 20% avec un vote plutôt inefficace (i.e: distribué partout) signifie un taux de conversion entre % et sièges très faible. Cependant, 20% est proche de la fameuse "zone payante". Ainsi, quand le modèle fait ses simulations, il doit bien y avoir des scénarios où la CAQ se retrouve supérieure (et le PLQ/PQ inférieurs) au sondage.

Le meilleur scénario a justement la CAQ à 26.4%. Donc largement supérieur au 20% du sondage et dans les faits, en-dehors des marges d'erreurs. Mais c'est normal, le modèle va un peu au-delà des marges d'erreurs pour tenir compte du fait que les sondages ont torts parfois (après tout, le PLQ lors de la dernière élection a récolté 31% des votes, ce qui était hors des marges d'erreur de la plupart, si non tous, des sondages). Bien sûr, ce "meilleur scénario" est possible mais peu probable. Et pour être juste, le pire scénario voit la CAQ récolter seulement 14% des votes. Donc le modèle n'est pas biaisé en faveur ou contre un parti.

Dans le meilleur scénario en termes de sièges, la CAQ aurait 24 députés. Dans le pire des cas, seulement 5. Ainsi la formation de François Legault a pas mal de variations en termes de sièges possibles. Mais même dans le meilleur des cas, ce parti ne pourrait rêver de remporter l'élection. Pas en étant sondé aussi loin derrière les deux autres partis.

QS est dans une situation différente car son vote est plus concentré est donc plus efficace. En étant sondé à 8%, le modèle prédit 3 sièges. Parmi les 1000 simulations, QS aurait un meilleur scénario à 12.6%. Remarquez bien que l'intervalle possible pour QS est plus petit que pour la CAQ. C'est normal, les marges d'erreurs sont plus grandes pour la CAQ à 20% que pour QS à 8%. Je le répète souvent, mais les marges d'erreurs dépendent du niveau de support et celles rapportées dans les médias correspondent au maximum, lorsqu'un parti serait à 50%. En termes de sièges, QS pourrait récolter 6 sièges (Gouin, Mercier, Hochelaga, SMSJ, Laurier-Dorion et Rosemont). Bien sûr, souvenez-vous qu'il s'agît là d'un scénario peu probable. Dans les faits, à part dans Gouin, Mercier et SMSJ, les chances de victoires sont inférieures à 10%. Prenez ces 6 comtés comme les 6 comtés dans lesquels QS pourrait être dans la course. Mais les remporter tous serait une grosse surprise et un peu chanceux. Néanmoins, en se basant sur ce sondage et en tenant compte de l'incertitude due aux sondages et au système électoral, on ne peut pas complètement exclure ce scénario.

Cela veut-il dire que techniquement, en se basant sur ce sondage, on ne pourrait exclure que QS obtienne davantage de sièges que la CAQ? Après tout, le minimun pour la Coalition est inférieur au max pour QS. La réponse est non. Sur les 1000 simulations, il n'y a aucun scénario où le nombre de sièges pour QS est supérieur au total de la CAQ. Dans le pire des cas pour la CAQ (5 députés), QS ne dépasse jamais les 4 députés. Cela s'explique par plusieurs raisons. Tout d'abord, je ne fais "que" 1000 simulations. Ainsi, le scénario (CAQ pire /QS meilleur) ne se produit peut-être pas. Par exemple, quand la CAQ ne récolterait que 14% du vote, QS ne serait pas à son maximum. Si je faisais 10,000 simulations, cela pourrait survenir possiblement. D'autre part, si la CAQ connait son pire scénario, cela veut probablement dire que le PQ n'est pas au minimum. Et le PQ est l'adversaire principal de QS.

Pour conclure, voici quelques statistiques tirées de ces simulations:

Probabilité que la CAQ obtienne moins de 10 sièges: 53%!
Probabilité que la CAQ obtienne 20 sièges ou plus: 1.4%
Probabilité que la CAQ n'obtienne que 5 sièges: 6%

Probabilité que QS obtienne plus que 2 sièges: 51%.
Probabilité que QS obtienne 4 sièges ou plus: 14%.
Probabilité que QS obtienne 5 sièges ou plus: 3%

Ainsi, il est presque autant probable que QS obtienne 5 sièges ou plus ou que la CAQ ne gagne que 5 comtés. Les deux scénarios restent cependant improbables (en particulier simultanément) mais cela illustre relativement bien l'efficacité du vote QS (ou l'inefficacité du vote CAQ).

24 Avril 2013: Philippe Couillard donne des ailes aux PLQ

Note to English readers looking for the BC projections: just scroll down this post.


Un premier (du moins il me semble) sondage depuis l'élection de Philippe Couillard à la tête du PLQ est disponible dans La Presse. Comme il s'agît d'un Crop, nous avons malheureusement que la moitié des résultats et très peu de détails. C'est ridicule et unique à Crop, mais enfin.

Les résultats sont extrêmement favorables au PLQ. En effet, ce parti est largement en tête des intentions de votes avec 38% des voix, devant le PQ qui chute à 25% et la CAQ à 22%. Québec Solidaire récolterait 11% des votes, ce qui est énorme. Pas d'info sur ON et les Verts, j'ai donc dû deviner pour les projections. Au final et de toutes manières, cela ne change pas grand chose dans le cas présent.

En termes de sièges, cela donnerait les résultats affichés. Un gouvernement Libéral et majoritaire. En termes de probabilités, le PLQ aurait 99.6% de chances de remporter l'élection, contre seulement 0.4% au PQ (dans les faits, c'est déjà assez fou de penser que le PQ pourrait gagner même en étant sondé 13-points derrière). À remarquer que QS récolterait pas moins de 5 sièges! Dans les faits, le meilleur scénario voit la formation de gauche remporter 9 sièges!

Les projections détaillées sont disponibles ici.

Bien sûr, il faut prendre ces résultats avec précautions. Un parti bénéficie en général d'une effet "lune-de-miel" après l'élection d'un nouveau chef. Il faudra voir si cet effet perdure. En particulier, et comme je l,ai déjà mentionné plusieurs fois, si ces résultats tiennent, cela voudra dire que Couillard réussit à prendre des votes directement au PQ, un phénomène plutôt rare au cours des dernières années.

April 24th 2013: What would it take for a Green candidate to be elected?

April 24th 2013: What would it take for a Green candidate to be elected?
If my model is relatively kind on the Conservatives (especially when compared to other models), it can seem incredibly hard on the Green party. Indeed, with the latest numbers, I don't project a single Green MLA and even the best case scenario would only see one Green candidate win his/her riding. That seems low since this party is polled around 10-12%.

People seem to think that one Green candidate has some real chances: Andrew Weaver in Oak-Bay-Grodon-Head. He's a well known candidate and definitely qualifies as a "star candidate". These candidates can perform significantly above expectations, or above what a "normal" candidate would. The best (and potentially more relevant) example is Elizabeth May. No matter where she ran (Ontario, NS or BC), she got a share of the vote much greater than the candidate before. During the last federal election, I spent a lot of time trying to estimate a "May effect" based on her past results. I found out that it could be as high as 20-25 points. However, during the actual eleciton in 2011, she seemed to have done even better. She indeed won the riding by increasing the share of votes for the green party from 10.45% in 2008 to 46.33% in 2011. All that while the Green party actually decreased by almost 2 points provincially! This is a typical examples of the effect of a star-candidate. However, and having done that for multiple elections, I can tell you that such a big effect is rare. Elizabeth May wasn't a typical star-candidate. She was a popular leader, known across the country. She even participated to the debate in 2008. She also seemed to have taken full advantage of the collapse of the Liberal party in BC.

So let's look at the results in Oak-Bay-Gordon-Head in 2009:

BC NDP: 44.3%
BC Liberals: 46.5%
Green: 9.1%

The current projections, without any bonus/boost/star-candidate effect are:

BC NDP: 47.1%
BC Liberals: 33.2%
Green: 22.6%

As you can see, the model already acknowledge that Victoria (and Vancouver Island in general) is a good region for the Green party. Indeed, it transposes a provincial swing of around 5-points (according to recent polls) into a riding-level swing of almost 13-points. So don't think that the model is biased against the Green or doesn't account for some regional effects. The problem however is the fact that the NDP isn't going down, not provincially at least. Therefore the model will predict a stable NDP in this riding as well.

But what if we account for the increased potential of Andrew Weaver? As opposed to May though, we don't have past data to estimate the magnitude of this effect. So we'll have to guess (until we get a riding-level poll for instance). Let's be generous and assume that the average effect is 15-points, taken mostly and evenly from the NDP and the Liberals. I say in average cause over the 1000 simulations that I run, this effect will sometimes be as low as 0 and sometimes be as high as 30-points. Again, we need to add some uncertainty here, especially due to the lack of previous data.

So with this bonus, out of 1000 simulations, the Green party is now projected to win this riding about 40% of the time, with the NDP winning the remaining 60%. Quite a difference!

So how should you interpret these numbers? Well, what they mean is that without a strong candidate-effect, the Green party won't win a riding, not at the current level this party is in the polls. In the mentioned riding, the effect has to be around 15-points for Andrew Weaver to have a real chance. And this effect better comes at the expense of the BC NDP, at least partially. So if you believe that Andrew Weacer can indeed pull that off, then there is a race in this riding. But I can guarantee you that getting a boost of 15-points is very hard and very rare. Usually, only the leader of a party could achieve that. So while I would love to see more parties elected at the legislative assembly, I have to remain skeptical of the chances of the Green party in BC.

21 April 2013: the BC Conservatives and the impact of various projection methods

21 April 2013: the BC Conservatives and the impact of various projection methods
The BC Conservatives got 2.1% of the vote in 2009. However, they achieved this by running only 24 candidates. So make no mistake, these 24 candidates got in average way more than only 2.1% (in fact they got 7.4%, with one candidate getting as much as 20%). This time around, they are currently polled around 10-12%. Quite a a big increase. But the good news is attenuated by the fact that less than a year ago, this party had a real shot at passing the BC Liberals in the polls where it was standing above the 20% mark.

I don't want to cover or try to explain why the BC Coservatives have dropped so much in the last 10 months. What I want to do is look at the number of seats this party could potentially win. By doing so, I'll compare my projections to other methods.

With the current voting intentions, the BC Conservatives are projected to win 2 seats (Kelowna-Lake-Country and Kelowna-Mission) by small margins. In the best case scenario, the party of John Cummins would get 9 MLAs. If you look at the most recent projections (just click on the picture in the right column), you see that the CP is actually in play in 11 ridings (i.e: where its probability of winning is >0%). But except in the above mentioned ridings in Kelowna, the odds of winning are very low. Still, 9 MLAs would be quite an achievement for this party and would constitute a surprise few saw coming. Of course, the best case scenario mentioned here is possible but unlikely.

How can my model project so many Conservative wins while, at the same time, projecting no more than 1-2 victories for the Green party? The answer is simple: vote concentration (note: I'll talk about the Green very soon, doN,t worry Green fans). With our electoral system, a small party is better concentrated. A big party is better widespread. The model uses past election results to estimate regional coefficients. In the case of the Conservatives, the task wasn't easy since they only ran 24 candidates in 2009 and even less in 2005. Nevertheless, looking at the (few) data, it was clear this party was more succesful in some regions of the province, mostly the interior. I worked hard and came up with some regional coefficients reflecting this fact. For instance, it is assumed that when the Conservatives takes 1% from the Liberals province-wide (as seen in the polls), they will actually take 1.6% in the Okanogan but only 0.3% in Vancouver.

The other piece of the puzzle here is to acknowledge the source of the Conservative growth: The BC Liberals. Just look at the most recent polls by Angus-Reid and you'll see that while only 5% of people who voted NDP in 2009 would currently cast a ballot for the new right wing party, this number is as high as 14% among Liberals. Actually, Christy Clark is losing almost as many votes to the Conservatives as to the NDP! The model takes this fact into account. It assumes that the Conservatives' share of votes is taken proportionally more from the Liberals.

So when the Conservatives are increasing from 2.1% to 12%, this swing is assumed to be more concentrated in the interior than in Vancouver for instance. It is also assumed to come at the expense of the Liberals. So ridings where the Liberals got a lot of votes in 2009 are better for the Conservatives. The "pool" of potential voters is bigger. This is why the model currently projects wins in the two Kelowna ridings, even though the best score in 2009 for the CP was in BoundarySimilkameen. The difference? In the latter, the Liberals only got around 35% of the votes, while they got above 50% in the former.

These are assumptions of course, but they are based on past regional trends. Still, let's compare our projections to other models and methods. Specifically let's compare for the Conservatives (comparing the general outcome is pretty useless as everybody will agree that the BC NDP would win if the election was held today).

Method 1: redistribution matrix from prof. Werner Antweiler (UBC-Saunder School of Business).

This method (and simulator) relies on the principle that voters don't vote for the same party every election. And if one party is experiencing a positive swing, it must come from one or more other parties. While the principle is sound, the application is more tricky as it requires you to either guess the matrix or rely on data not easily available. Indeed, polls usually don't provide us with this information. We simply see thet net, aggregate effects. For instance, we see that the BC NDP is increasing, so are the Green and the Conservatives. But we don't see the exact transfers of votes between these parties and the Liberals for instance. The latest poll from Angus-Reid does provide us with some partial information regarding this (page 6). Using these numbers and playing/guessing the other numbers in order to match the province-wide percentages of the polls, we would find that the Conservatives aren't projected to win any seats. In Kelowna, they would fall short by about 10-points in my scenario, it really depends on your matrix.

Why the differences? Well, as opposed to my model, this matrix doesn't have regional reffects. If you input in the matrix that 14% of the Liberals are now voting Conservatives, it'll use this ratio in every riding. While my model would transpose this 14% differently depending on whether the riding is in downtown Vancouver or in Kelowna.

Method 2: prediction market.

This method doesn't use polls, at least not directly or explicitly. It is based on trading with real money. Just click on the link and read the details. The seat projections are similar to mine except that the Conservatives would get slightly more seats (5) than in my most likely scenario. But given that I have other scenarios where this party would get as many as 9 seats, it seems 5 is a good middle ground.

Why the differences? Well, in this case, the predictions are a lot less different than using method 1. It seems the traders are aware of the concentration of the vote of the Conservatives. Looking at the predicted shares of vote, it seems that traders also believe that the BC Conservatives are underestimated in the polls. Ultimately though, it's hard to directly compare and explain discrepancies as the two methods are widely different. Since historically predictions based on trading have performed relatively well, I see that as an encouraging sign that I'm not completely loss with my current projections for the Conservatives.

Method 3: other projection websites.

I'm not the only one blogging about this. Hey, some even do that for a living despite using very simplistic models. As opposed to my model, the difference is that the other models usually don't include regional effects and simply apply an uniform or proportional swing (read the FAQ for more details). Or if they do include regional effects, it's entirely based on the current polls and not the past election. In theory, you could use the regional breakdowns of the polls. In practice, the sample sizes by region is so small that you are at the mercy of very imprecise estimates. Right now, the polls don't show any concentration of the vote for the Conservatives. Indeed, the AR poll actually has the Conservatives at the same level in the lower mainland and in the interior! To me, this can't possibly be right. But models who use these numbers directly will obviously assume a very uniform swing across the province for the party of John Cummins. This leads to a lot less wins than my model or method 2.

Who is right? Well honestly we won't know until election night. However, in the past, uniform or proportional swing models have performed poorly for small parties. If the Conservatives really has a vote distributed almost evenly everywhere, then this party will likely not win a single seat. However, given the past election results and the ideology of the party, it isn't unreasonable to imagine some sort of concentration of the vote in a couple of key regions. My model probably overestimates this concentration while method 1 and 3 probably underestimate it.

At the end, I'd say that it's safe to assume that the Conservatives will be in play in about 5-10 ridings and could win some of them. Luck, turnout and vote concentration will play key roles in determining whether this party actually gets MLAs or not, despite experience the highest positive swing of all parties in the province.

April 20th 2013: How high can the NDP go?

April 20th 2013: How high can the NDP go?
If my first campaign post was about the chances of a BC Liberals victory on May 14th (spoiler: right now, the odds are very close, if not exactly, zero), my second is about how manys seats the BC NDP can expect or hope for.

Looking at the most recent polls (from Ekos, Angus-Reid or Ipsos), the NDP is clearly ahead in term of voting intentions. If the election was held today, the only possible outcome would be a BC NDP government. However, would it necessarily be a majority one? Could the NDP sweep the province the same way the Liberals did in 2001? The short answers are, respectively, yes and yes.

For the majority, I'm using the numbers from Angus-Reid (Ekos is a little bit old and Ipsos doesn't provide enough details to the public. In any case, all three recent polls agree. On top of that, remember that the 1000 simulations take care of the uncertainty regarding polls. In other words, if the NDP is at 45%, there will be scenarios with the party is as low as 38% or as high as 52% in my model). So, using these numbers, the lowest possible number of seats for Adrian Dix's party is currently 47. Remember (or discover if you're new to this site), it means that even in the worst case scenario where the NDP would perform significantly lower than what the polls predict (and thus the Liberals or another party would perform much better than expected) AND be inefficient in the repartition of its votes, this party could not get less than 47 seats. This is good enough for a (small) majority. So, as of right now, not only is the BC NDP sure to win, this party is even sure to get a majority! In case you're curious, the best result for the Liberals would be 35 seats. For the Green and the Conservatives, 1 and 9 respectively.

Then we have the second question: what if the NDP actually performs even better than what the polls predict? After all, there is no reason (a priori) to believe that the polls could be biased or skewed in one direction only. Could the BC NDP sweep the province? BC isn't foreign to this situation. In 2001 the Liberals won 77 of the (then) 79 seats of the legislative assembly. They achieved this by getting "only" 57.6% of the vote. The electoral system and some bad luck (or inefficiency) for the NDP did the rest. So, could we see a complete reversal of the 2001 outcome?

Actually, it does seem to be possible. First of all, it would require an important underestimation of the popular vote share of the NDP. In my 1000 simulations, the NDP best case is to get 53% of the vote. This is going even beyond the normal margins of error (but not completely impossible, especially if the latest Ipsos poll was actually right). In terms of seats, the highest number Adrian Dix could get is 80! 80 out of 85 is pretty similar to 77 out of 79.

Please notice the implications of these numbers. As of right now, based on the polls and the past elections results, the BC NDP is more likely to win 80 seats than to lose the election! This is a pretty comfy situation Adrian Dix is in right now! In term of suspense, this is definitely not the best election.

My next article will look at the impact the Conservatives could have. In particular, how high can they get and who do they hurt.

April 17th 2013: The BC election begins. Can the Liberals even win?

The BC election has officially started yesterday. One long month of (most likely dirty) campaign leading to May 14th. As this election begins, polls and analysts would agree on one thing: the BC NDP is the big favorite to win it. Actually, one could wonder if it's even possible for the BC Liberals to win. This is the object of this post.

First, let's look at the situation assuming that the polls aren't completely wrong.

A lot of things can happen between now and the election (after all, there is this thing called a campaign), but as of right now, the odds aren’t good for the BC Liberals. Most recent polls have all shown a lead for the BC NDP around 15-20 points. The gap between the main two parties was closing in fast for a couple of months but this trend has clearly stopped recently. In term of seats, this is what the projections would look like by using the most recent polls (released yesterday) by Angus-Reid.

BC Liberals: 14 seats
BC NDP: 67.
Green: 0.
BC Conservatives: 2
Ind.: 2

The detailed projections (in pdf format) can be found here. You can also find the probability of winning for each riding). If you need the details of how I do that, just read the FAQ. As usual, if you want to make your own projections, use the simulator.

Let’s look at the probability of winning the election. People are relatively familiar with margins of error while looking at polls. However, not everybody really knows how much uncertainty can come from these polls and what it can means in terms of electoral outcomes. On top of that, our electoral system is such that knowing the percentages isn’t enough in order to predict who will win. Therefore, there is actually quite a lot of uncertainty when predicting elections.

The model tries to capture and measure the two main sources of uncertainty: the polls and the electoral system. The first one comes from the margins of errors. When a party is polled at 35%, this party could actually be at 32% or at 38% (or even further away, since margins of error apply 95% of the time). Additionally, our electoral system is such that the same province-wide percentages can lead to very different numbers of seats. So there is this additional uncertainty at the riding-level. Our model takes the polls and runs 1000 simulations, accounting for both sources of uncertainty. It can transpose province-wide percentages into riding-level ones using coefficients estimated from past elections results.

The graph below represents the probability of winning the election (defined as having won the most seats) for the BC NDP, as a function of the party’s lead in the polls. As you can see, as soon as the BC NDP is polled 10-points above the BC Liberals, it’s pretty much game over.


Remember, what it means is that when polled 10-points ahead of the Liberals, the BC NDP is projected to win the most ridings in all 1000 simulations, if the election was held today. Even in the case where the NDP would perform significantly lower than the polls (and the Liberals significantly better), even in the case where the NDP would be “unlucky” in the sense that its vote would be inefficient in getting seats, so even in this worst case scenario, Adrian Dix would still get the most MLAs.

Remember as well, these 1000 scenarios account for the natural statistical variation of polls. Actually, it goes beyond the normal margins of error. Specifically, with the vote intentions given above, there is one scenario where the NDP would be as low as 40%. In another one, the Liberals could get as much as 32.6% of the vote, almost 5-points above the poll. Add to this the uncertainty of the riding level (the second sampling if you prefer), and you realize that the model does account for a lot of uncertainty.

With that said, we are still assuming that the informaiton from the polls isn't completely invalid. In other words: we are assuming that what happened in Alberta will not happen here. Let me remind you of how wrong the polls were. One just needs to look at this picture (from wikipedia) to realize how bad the pollsters did.


I don't want to go over the reasons of this failure. Some pollsters even don't seem to acknowledge the mistake and are saying that people really changed their minds in the last minute. I mean really? around 25% of people switch during the last night? lol This is ridiculous. Sure the last minute poll by Forum did better, but I'm not sure this is really an achievement. It could well be luck. The last minute poll in Quebec by Forum was quite off.

Looking at this graph, the average for the Wildrose alliance was around 40% (let's be hard on this party and accounts for the slight decreasing trend) and 35% for the Conservatives. So at best, we are talking of an underestimation of 9-points for the PC and an overestimation of 5 for the Wildrose. This is beyond what my simulations could predict. I'd need to assume an incredibly large sample size to even have some scenarios as crazy as this one.

So the short answer is no, my model doesn't account for that much uncertainty. And quite honestly, I'm not sure it should. What happened in Alberta was a unique failure, something we haven't really seen before or since. Polls are less accurate now than before (for various reasons), but they are still reliable in average. So, during this campaign, I'll sometimes run a scenario where an Alberta-like failure would occur. If you really think polls are wrong, you can always use the simulator.

So, is the election already over? No, of course not. But as long as the polls will show the NDP with such a big lead, there won't be much suspense regarding the outcome of the election. The silver lining for Christy Clark and the BC Liberals is that the current electoral system seems to favor them. Indeed, look at the first graph. The NDP needs a 3-points lead to have more than 50% chances to win. In other words, the Liberals don't need to pass the NDP in the polls, they just need to get closer to have a chance.

Throughout this campaign, I'll also try to keep you entertain and look at various things. For instance, can the Green win a seat? Can the Conservatives win seats as well? How much damage can they do to the Liberals? etc etc.

April 15th 2013: The Trudeau effect?

April 15th 2013: The Trudeau effect?
The Liberals have a new leader, one that got elected even more easily than expected. Justin Trudeau is currently seen as the savior of the LPC and many hope he will bring this party back to power.Looking at his leadership run and the recent polls, Liberals might indeed be right to have high hopes for the next election. The object of this post is to look at the potential "Trudeau effect" and try to quantify it.

1. Justin Trudeau's performance in his own riding.

Before looing at the potentiel for the party, let's look at his results in his riding of Papineau. He ran there in 2008 after Pierre Pettigrew lost to the Bloc in what was one of the great victories for the Bloc in the 2006 election (taking a riding on the Island of Montreal is never easy). He successfully reconquered this seat for the Liberals and kept it in 2012 despite the rise of the NDP. The original win in 2008 wasn't easy and if you look at the numbers, Trudeau increase the Liberal share of votes by 2-3 percentage points, the same average as for the LPC in the province in general (people are quick to forget tht Dion actually managed to increase the support for the Liberals in Quebec). I understand the Bloc probably ran a tough campaign then (hey, they really wanted to keep this riding and they really, and I mean really wanted to prevent the son of the former PM Pierre-Elliot Trudeauto win). Thinsg are better for Justin Trudeau in 2011 where he seemed to have got a boost or bonus. Indeed, he managed to keep his seat by losing only about 3-points, way less than the average for the Liberals. It could be beause of an incumbency effect, but data shows it was more of a specific effect. Advanced econometrics methods show the same thing: no effect in 2008 (when the Liberals got some votes from the Conservatives, province-wide), but a large (between 3-4 points) and significant effect in 2011 when the Liberals lost votes to the NDP.

What can we learn from this? Mostly that Trudeau can  be especially good at fighting a rising NDP. While most of the island (and the province) was turning orange, Justin managed to fight the orange wave quite well

2. The recent polls.

All along the Liberal leadership campaign, we've got polls. Some were even as specific as to ask the vote intentions twice: with and without Trudeau as the leader of the Liberals. I won't try to list all the polls of the last 6 months, but we can look at these two: Legermarketing (March 30th) and Leger (December 8th 2012, so at the beginning of the race). For the former, let's ignore the ridiculous numbers (both with and without Trudeau) of the Atlantic. If we look at Quebec and Ontario, we see that Trudeau as leader would greatly benefit the Liberals. In Quebec, we're talking of a net gain of 4-points, at the expense mostly of the Bloc. Right there, if you follow politics, that shoud be a red herring. To me, it doesn't make any sense that Justin Trudeau would manage to convince Bloc supporters to switch to the Liberals. Especially when the Bloc is already quite low and therefore, the Bloc voters are more likely the "die hard" ones. In Ontario, the LPC would gain around 10-points, mostly from the NDP. In the latter poll (the one from late 2012), we see a boost for the Liberals, taken from the NDP. That makes sense. In Ontario, similar boost, taken equally from the CPC and NDP.

What I'm trying to show here is that the "Trudeau effect" isn't that obvious in the polls and hasn't been very consistent, at least not in terms of which party would lose votes. Generally however, it seems, the NDP would be more affected by a Trudeau-led Liberal party. Angus-Reid polls show the same: NPD down, CPC barelly affected.

Other polls have been released and the Liberals have been quite volatile. They could be very high in most Forum polls, but very low and a distant third in most polls from Angus-Reid. In both cases, Trudeau as leader would help. The volatility is definitely too important and reminds us to be use caution while looking at polls, especially outside of an election period.

What is also weird is that people were clearly expecting Trudeau to win this race, from months. So over the months, polls shouldn't show such a big Trudeau effect since people should be factoring the fact that Justin Trudeau would be the leader, no matter if the question asked for it specifically. In uebec, because people were pretty sure (and rightfully so) that Phillipe Couillard would win the Liberal leadershop (provincially), we didn't see any real boost for this party after the leadership. Which makes sense. No such consisteny at the federal level.

At the end, even if we do observe such a boost (and we most likely will in the next couple of polls, we always do when there is a new leader), it'll likely be at the expense of the NDP. While it's great for the Liberals to climb back, that leaves Harper and the Conservatives ahead. It's almost like LPC and NDP will simply split the vote differently among them. The effect could be particularly visible in Quebec where some scenarios actualy allow the Bloc to become the first party (in term of seats) again, simply because Liberals and Neo-Democrats are splitting the same vote. Both Trudeau and Mulcair have said no to any deal or coalition. We'll see in 2015 if they were right.

The real key battle will obviously be (as usual) Ontario and it'll be interested to see if Trudeau can really get some of the Conservatives vote back. First in the polls, later during the actual election.