Skip to main content

This diary is an analysis of the model I developed to predict the seat-by-seat outcome of the Australian federal election held in September.

Unfortunately late polling released the morning of the election was somewhat worse for Labor than the consensus prior to that. My last full update used only the data available the day before the election. I mentioned in a last minute update that the model's final prediction was 91 seats to the Coalition and 56 to Labor but wasn't able to provide final seat by seat predictions due to time constraints (I work at Australian elections and the election day polling was released literally minutes before I was legally obliged to abjure posting on the internet). So this analysis post refers to the model's final prediction rather than my final posted prediction.

In reality the Coalition has won 90 seats and Labor won 55. However the Coalition also lost Indi to a conservative local independent and Fairfax to the conservative eccentric billionaire Clive Palmer (of Titanic II and world's-largest-dinosaur-park fame) so as far is the model is concerned the Coalition won 92 seats (the model can only actually predict if a seat will be won by the left or the right sides of politics). Therefore the model was, overall, off by only a single seat with Labor losing one more seat to the right then was predicted.

However the model purported to be able to predict the results and final two-party preferred percentages in each individual seat rather than merely an overall seat prediction. Therefore here are tables detailing the predicted Coalition winning percentage in each seat, the actual Coalition vote, and the model's predicted Coalition vote.  

You might notice that eleven seats are missing from the tables. These seats had a "non-classic" two party preferred vote so Labor/Greens or Liberal/National or Coalition/Right-wing minor party were the top two vote-getters. Therefore I don't know the actual left-right two-party preferred breakdown it these seats, yet.

Labor had a tough time in New South Wales and lost eight seats including three of the four tossups and one lean Labor seat. Labor did manage to hold onto Greenway easily even though the model didn't care much for their chances. This one was down to local factors, the Liberal candidate was incredibly terrible. It was embarrassing for them.  
Labor lost three seats in Victoria (including La Trobe against the prediction of the model) and had a very narrow escape in McEwen, which the model had rated as safe. Adam Bandt held Melbourne very easily for the Greens, in the end, to widespread surprise. The unpopular fire-breathing Liberal incumbent in Indi was edged out by a local independent in a display of the merits of preferential voting.
The media was talking about a wipeout for Labor in Queensland but the model always maintained they'd lose no more than one or two seats. In the end they lost two. Clive Palmer won in Fairfax and Bob Katter clung on in a shockingly close race in his personal fiefdom of Kennedy.
Not much happened in WA with no seats changing hands. The model did very badly in the Coalition seat of Canning with by far it's worst miss of the election (9.5 point miss, no other non NT misses by over 6).
Labor lost Hindmarsh but held the rest contrary to media speculation. It was the only seat the model believed to be in major danger.
Things did not go well for with Labor or the model here. I blame poor polling data. Garbage In Garbage Out. I mentioned frequently my lack of faith in polling for the territories (mostly because there basically is none) and doubt over the model's prediction there.

Labor had some bad luck in Tasmania. They won a majority of the two-party preferred vote but hold just one seat.

Overall the model was pretty accurate. Every seat ranked at least "likely" to be won by either party was (except Lingiari in the Northern Territory but I said not to trust that one) even though only 18 of 150 seats were regarded as a "lean" or "tossup". 30% of all seats were predicted within 1 percent of the actual result and a further 32% were within 2 percent (16% 2-3 percent miss, 14% 3-4 percent miss, 6.5% 4-6 percent miss, only Canning and Lingiari outside that).

Over the next six months or so I'll update the model for the next election cycle. There are data availability problems at present due to the probable fresh election for the Western Australian Senate.

Originally posted to Alizarin Indigo on Tue Nov 12, 2013 at 02:48 AM PST.

Also republished by Community Spotlight.

Your Email has been sent.
You must add at least one tag to this diary before publishing it.

Add keywords that describe this diary. Separate multiple keywords with commas.
Tagging tips - Search For Tags - Browse For Tags


More Tagging tips:

A tag is a way to search for this diary. If someone is searching for "Barack Obama," is this a diary they'd be trying to find?

Use a person's full name, without any title. Senator Obama may become President Obama, and Michelle Obama might run for office.

If your diary covers an election or elected official, use election tags, which are generally the state abbreviation followed by the office. CA-01 is the first district House seat. CA-Sen covers both senate races. NY-GOV covers the New York governor's race.

Tags do not compound: that is, "education reform" is a completely different tag from "education". A tag like "reform" alone is probably not meaningful.

Consider if one or more of these tags fits your diary: Civil Rights, Community, Congress, Culture, Economy, Education, Elections, Energy, Environment, Health Care, International, Labor, Law, Media, Meta, National Security, Science, Transportation, or White House. If your diary is specific to a state, consider adding the state (California, Texas, etc). Keep in mind, though, that there are many wonderful and important diaries that don't fit in any of these tags. Don't worry if yours doesn't.

You can add a private note to this diary when hotlisting it:
Are you sure you want to remove this diary from your hotlist?
Are you sure you want to remove your recommendation? You can only recommend a diary once, so you will not be able to re-recommend it afterwards.
Rescue this diary, and add a note:
Are you sure you want to remove this diary from Rescue?
Choose where to republish this diary. The diary will be added to the queue for that group. Publish it from the queue to make it appear.

You must be a member of a group to use this feature.

Add a quick update to your diary without changing the diary itself:
Are you sure you want to remove this diary?
(The diary will be removed from the site and returned to your drafts for further editing.)
(The diary will be removed.)
Are you sure you want to save these changes to the published diary?

Comment Preferences

  •  Well (2+ / 0-)
    Recommended by:
    Sky Net, naka

    at least your model was way more accurate than all of the seat level polling that was published during the election! But seriously good job on the model, your predictions basically lined up where they were fell.

    The Republican party is now an extreme right-wing party that is owned by their billionaire campaign contributors. - Bernie Sanders

    by ehstronghold on Tue Nov 12, 2013 at 09:24:46 AM PST

  •  Shocker of an election (0+ / 0-)

    Nobody even knows what the new governments policies will be, we just know that they're going to hurt.

    Man I wish there was something like Daily Kos in Australia. I guess there would have to be a pretty big Greens v Labor pie fight to even attempt starting something like it.

    •  Daily Kos Australia (3+ / 0-)
      Recommended by:
      naka, ehstronghold, myrmecia gulosa

      You know I think that would be interesting. The Labor/Green split amongst progressive votes is statistically real but there isn't a huge amount of venom there between actual voters. I guess the internet is a different place though!

      •  Might not be a problem (1+ / 0-)
        Recommended by:
        myrmecia gulosa

        I suppose in the US there isn't much room in terms of voting for a third party, but with the Aus electoral system - Greens, Labor and others could potentially work side by side.

        If I had the writing ability, credibility and political knowledge I'd start one myself. Thanks to places like this I probably know more about US politics than the local stuff, heh.

    •  Well, we do know one thing... (1+ / 0-)
      Recommended by:
      Nobody even knows what the new governments policies will be, we just know that they're going to hurt.
      We do know they'll be reversing the trend away from painful austerity for austerity's sake. You know, the one that kept Australia from being bent over and fucked to the same extent that the rest of us have been. So there's that at least.

      After all, seems quite unfair that the rest of the world is destroying itself without Australia jumping on board the express elevator to hell too, right?

      •  Yes, that much is clear (0+ / 0-)

        But there isn't a lot of detail on how exactly that will occur (well, there's some - such as planned infrastructure that they announced would be canceled, and a few other things...)

        If the economy has to crash, I suppose it is better that it happens during Abbott's watch. Too bad they never ran an Abbott/Costello ticket, at least that would have been good for laughs.

  •  I can answer what happened in Canning; (1+ / 0-)
    Recommended by:
    Alizarin Indigo

    In 2010, Labor ran a fantastic candidate in Alannah McTiernan, who produced the only pro-ALP swing in Western Australia and cut heavily into Don Randall's 59.8% TPP in 2007.

    2013, Labor ran McTiernan in Perth instead, and Canning snapped back to its old voting habits. It's the best damn argument I've ever seen for "candidates matter!".

    "Violence never requires translation, but it often causes deafness." - Bareesh the Hutt.

    by Australian2 on Wed Nov 13, 2013 at 01:12:48 AM PST

    •  Canning (1+ / 0-)
      Recommended by:

      That is a really good answer and if you had asked me the day before the election which non territorial electorate I was least confident in I'd have said Canning for that exact reason. But it isn't enough to explain a 9.5 percent miss. McTiernan isn't that strong. I'll look into it more when the rest of the election data is available, assuming it ever is given the probable WA senate rerun.

      A lesson I've learned with the Model is that candidates usually don't matter all that much, in Australia. Only truly exceptional candidates (or particularly terrible ones) can really have much of an impact. That said they do matter on the margins and recruitment does matter.

      •  Not really. (0+ / 0-)

        I'm going to give you some numbers - they are the ALP TPP in Canning:

        2004: 40.5%
        2007: 44.4% (+3.7%, ALP gain Aus-wide +5.4%, ALP gain in WA +2.0%)
        2010: 47.8% (+3.4%, ALP gain Aus-wide -2.6%, ALP gain in WA - 2.8%)
        2013: 38.2% (-9.6%, ALP gain Aus-wide -3.6%, ALP gain in WA -1.2%).

        Basically, the fact that McTiernan was such a stellar candidate meant that Canning swum against the tide in 2010, only for the 2013 candidate to be high and dry. On the numbers alone, McTiernan's candidacy was worth 6.2% - the amount that Canning went against the WA numbers by. Add the 1.2% that all of WA swung against Labor this time, and you're looking at 5/6 of the missing 9% swing right there.

        "Violence never requires translation, but it often causes deafness." - Bareesh the Hutt.

        by Australian2 on Wed Nov 13, 2013 at 08:32:27 AM PST

        [ Parent ]

        •  On those numbers (0+ / 0-)

          McTiernan is worth 6.2% but the Model considers her worth 3-4 points in Canning in 2010 (for complicated reasons), which isn't to say that it is right but given that it's also what  she was worth in Perth in 2013 I'm not inclined to assume it's wrong.

          It's possible she was an even better candidate in 2010 compared with 2013, or is particularly strong in Canning, or is a particularly good match-up with Don Randall. I suspect there was just some natural noise in Canning in 2010 that coincided with a particularly strong challenge.  

Subscribe or Donate to support Daily Kos.

Click here for the mobile view of the site