With all the pollsters in, we can finally run our final election day mega-simulation – and boy is it a close one! Not only does this simulation use our usual quasi-dependency framework (where we don’t treat seats as independent events), but we’ve also anchored seats together within each state on the basis of capital city seats being linked and non-capital city seats being linked, as well as Western Sydney seats being linked. In the simulation, seat groups effectively “move together” as we see in real life, as well as accounting for the “Western Sydney” issue that the polling heavily suggests is happening.
The pollsters used are Newspoll, Nielsen and Morgan phone – giving us a pooled sample of 6419 – where we use their aggregated state breakdowns to derive state based swings as the key mechanism to calculate total seats (with the fancy shmancy quasi-dependency framework buolt into the swings)
The monte carlo simulation stabilised at around 130,000 iterations, with the ALP seat results coming in like this (click to expand):
The most likely result is the ALP winning 74 seats, the Coalition winning 72 seats, the Independents getting 3 and the Greens winning 1 (where I substituted betting market data for the seat of Melbourne in the surprising absence of any seat polling).
However, switching to the more useful cumulative probability view of the results, we get (click to expand):
Labor is coming in with a 50.2% probability of winning at least 75 seats. That jumps out to 59.6% for winning at least 74 seats and to 68.3% for winning at least 73 seats (which is the close to guaranteed ALP minority government result).
However, there is only a 24% implied probability of the Coalition winning at least 75 seats , jumping up to 32% for them winning at least 74 seats – where 74 Coalition seats would be nearly guaranteed to give the Coalition minority government.
If we run two simulations under two seperate assumptions – 1.where the Greens win Melbourne and there are 3 independents and 2. where the ALP wins Melbourne and there are 3 independents, the implied probability of a hung parliament is 34% with a Melbourne Green and 20% with only 3 members on the cross-benches.
The combined phone polls show it to be a close one, slightly favouring the ALP.
The big issue in the simulation was actually the Newspoll result for Qld. If the actual Qld result comes it at around 45% for the ALP rather than the 42% that Newspoll estimated it as (pulling down the Qld estimates in the simulation), those simulated implied probabilities start shifting to Labor pretty quickly because of the spread of the margins in Qld and the number of seats involved. The 45% TPP level for the ALP is a bit of a threshold in Qld (assuming the rest of the polling is approximately correct). If they get above it – it increases the likelihood of an ALP win substantially, below it and it increases the likelihood of an ALP loss just as quickly.
There’s a similar key threshold point for the ALP in NSW – sitting about the 51% mark. Above that, the chances of an ALP win start increasing dramatically, below that they start declining dramatically.
The final polling has it tight – very tight. With the relatively high undecideds some were pollsters were picking up on top – there’ll be a lot of nervous folks around today 
———————
And don’t forget (disgraceful self promotion) – Possum needs a job!
24 Comments
Thanks for that Poss. Is good to have those critical numbers from QLD (45%) and NSW (51%).
Cant help but think that last Newspoll was a bit out there for the QLD vote.
Ah well, the big one today, all questions answered.
Good luck to all.
Who wants to bet the Coalition will claim a ‘mandate’ if there’s some surprises and they just sneak over the line?
Shannessy’s (Newspoll head) revelation that Labor had picked up 1.6% on the final night on primaries
So, how much of a damping effect did that Newspoll 42% Qld 2PP have on the overall probabilities? Would it contribute to a quarter of the sample?
If the Qld 2PP comes in at 45%, how much does that lift the probability of reaching a minimum of 74 seats?
I guess that’s what we call “The Narrowing” huh? It couldn’t get any narrower.
Great work Poss, and good luck with the job hunt.
Hi Poss, You want a job, but would you move to Sydney? Cheers, Tomasso (email me for a chat).
Why are we having this election?
Will do Tomasso!
Pasok, about 7% in the middle of the distribution – it’s very sensitive around the 45% mark for Qld (which it sits on at the moment because of Newspoll). If Newspoll came in at 45 rather than than 42, the mean swing figure would be 46 and bit, pushing up Labors probabilities significantly.
Just wondering if the late trend to the Libs will continue into the last day (probably) and if it will increase, also a chance since the cause of the trend seems to be closeness to voting day.
Just a quick Count of the centrebet markets
W.A.
2 loses (Swan, Hasluck)
S.A.
No gains
N.T
No loses***
Vic
2 gains McEwen (certain), Latrobe
1 loss Melbourne (green)
NSW
6 losses (Bennelong,Lindsay,Macquarie,Robertson,Gilmore(certain), Macathur(certain)
QLD
5 losses (Dawson,Dickson,Flynn,Herbet,Leichhardt)
Tas
No losses
NSW and QLD have no real chance of any gains to lab (LNP <=$1.50, LAB $2+).
Boothby has Lib at $1.48.
Ok that takes it to lab @ 76 seats; but
***Solomon is too close to call – $1.83 vs $1.88
Also Bonner, Forde are too close to call as labor holds (1.70, 1.72 vs 2.03,2.00)
HUNG PARLIAMENT – NO 1.45
HUNG PARLIAMENT – YES 2.55
Solomon was on a small margin and only then thanks to the appeal of Rudd. Rudd is gone, I think people will revert to their normal pattern, that means the seat should go to the CLP.
After four hours of handing out HTV cards this morning in Sturt, it really did feel like 50/50 to me. One abusive comment all day from a Liberal voter, most people very polite, one Liberal voter said he couldn’t bring himself to vote for Abbott, but two said they were Labor voters but voted Liberal because of the way Rudd was knifed. I think now tonight will be an anti-climax. If it is this close, postals and EVs in critical seats will be needed to determine final numbes. and if the overall numbers are this close, we won’t know for sure who will be PM till Thursday.
My prediction two weeks ago was Labor 76 seats, but my prediction tonight is deadlock.
I think its critical for labor that it does not lose solomon – if its does, its out of office.
As far as swings go in NSW and QLD, i think the following has / is happening.
1. labor stuffed up and fixed problem by replacing rudd.
2. liberals haven’t promised anything big.
1 & 2 cancel out in the mind of the undeciders.
3. state labor governments
I think the labor brand in NSW and QLD are stuffed – i saw one article that labor may only win 8 seats in the next state gov in nsw. The voters are anrgy and this will leak through and most of the undecided voters will go through to T. Abbott. I think this is why Newspoll shows a big swing in QLD esp.
If voters are so angry with (state) labor as newspoll suggest, up to moreton could be lost.
IMO, lab supporters shouldnt be blaming the MSM, but their state govs in QLD and NSW. The libs haven’t done anything and prob. don’t deserve to win (except they appear to be more united).
My Key Seats for lab
1. Solomon
2. Brisbane
3. Latrobe
4. Corangamite
Any of these are lost / not won – its goodnight.
wal kolla
You may be right but we might still win Boothby and Sturt here in SA, so lets wait and see.
“Pollsters Roy Morgan are conducting an SMS exit poll that predicts a hung parliament the most likely outcome.” from the ABC news
Boothby and Sturt…. i think Boothby is a chance, I don’t give Sturt a chance though – nor does the markets, i can’t bet on it. (Im using centrebet as a guide)
Ive been constantly told that sturt achieved its “high-water mark” last election.
BTW im not associated with any party, but im a geomatics research student…. so numbers, MAUP etc interest me…
wal koala
I know that is the view about Sturt, but the boundaries have shifted quite a bit since last time. It is a new ballgame.
Poss
Can I ask you please what is a tracking poll?
Betfair market has been very interesting – http://au.site.sports.betfair.com/betting/LoadRunnerInfoAction.do?marketId=100012927&selectionId=2049781&timeZone=Australia/Sydney&locale=en®ion=AUS_NZL&brand=betfair¤cy=AUD
election eve: Labour approx. 1.40
election morning: Labour touching as high as 1.6
election afternoon: Labour dropping as low as 1.2
early election count: Labour rising to 1.8
Labour currently: 1.33
somebody knows!
Looks like my thoughts about Solomon came to pass.
Brisbane looks like going to the LNP.
Thats basically cost them a maj-gov.
I predicted 73 seats to LAB… so i was almost right…
I didn’t see denison coming, but everything else was statistically elementary.
Poss,
I note this story about 5% informals being recorded yesterday – an unusally high figure.
http://www.abc.net.au/news/stories/2010/08/22/2989878.htm
Do you have any records on how this ranks historicaly? Has it ever been exceeded?
I think it’s the highest in 25 odd years