Feeds:
Posts
Comments

Archive for the ‘Electorate Races’ Category

[Update: Election results available on the Electoral Commission website.]

The 2011 Te Tai Tokerau by-election will be held today. This is the fourth by-election to be held since the 2008 general election, which, whilst not a record, is certainly the most during the last ten terms of parliament.

To date I am aware of only one poll in the electorate, which was the Native Affairs-Baseline poll which had Hone Harawira (Mana Party) on 41%, Kelvin Davis (Labour Party) on 40% and Solomon Tipene (Maori Party) on 15%.

As with the previous 2009 Mount Albert by-election, 2010 Mana by-election and 2011 Botany by-election I have attempted to predict the outcome of the election and the share of the votes won by each of the major or minor NZ political party’s candidates using a Monte Carlo simulation of 50,000 NZ general elections based on recent political polling results. The results for the Te Tai Tokerau by-election are determined using the Uniform National Swing model of electorates. The results of the simulation are shown in the table below, and the results of the 2008 General Election for the Te Tai Tokerau electorate are included for reference.

Simulated results of 2011 Te Tai Tokerau by-election

Table showing simulated results of 2011 Te Tai Tokerau by-election, as calculated on 25 June 2011.

So that is a guaranteed win for Solomon Tipene and the Maori Party!

It goes without saying that the whole prediction is an excercise in futility given that the recently-formed Mana Party didn’t exist at the previous election, and so we don’t have any baseline off which to predict their performance. In fact the discrepancies with the one opinion poll quoted above are so great that, unlike the recent Mana and Botany by-elections, the simulation has practically no predictive power whatsoever. It isn’t even obvious what would count as a “good” result for each of the candidates (although winning the by-election should probably be considered a “good” result). I guess this post therefore serves as another warning against taking the results of Uniform National Swing predictions too seriously.

The only other quantitative predictions for the Te Tai Tokerau by-election that I’m aware of are from New Zealand futures market iPredict, who as of 17:50 (see screen captures below) are giving the Mana Party a 78.0% chance of winning, the Labour Party an 18.7% chance of winning, and any other candidate a 2.0% chance of winning (probabilities do not necessarily have to add to 100% due to the bid/ask spread). iPredict also predict that the Mana Party candidate will win 43% of the vote, the Labour Party candidate will win 41% of the vote, the Maori Party candidate will win 17% of the vote.

I’m not aware of anybody else making quantitative prediction on the results, but if you know of anybody, or if you would just like to take a punt, then feel free to leave a comment below.

iPredict's Te Tai Tokerau by-election winner predictions

Screen capture of iPredict's Te Tai Tokerau by-election winner predictions, as of 17:50 on 25 June 2011.

iPredict's Te Tai Tokerau by-election vote share predictions

Screen capture of iPredict's Te Tai Tokerau by-election vote share predictions, as of 17:50 on 25 June 2011.

Advertisements

Read Full Post »

The 2011 Botany by-election will be held today.

As with the 2010 Mana by-election I have attempted to predict the outcome of the election and the share of the votes won by each of the major or minor NZ political party’s candidates using a Monte Carlo simulation of 50,000 NZ general elections held today based on recent political polling results. The results for the Botany electorate are determined using the Uniform National Swing model of electorates. The results of the simulation are shown in the table below, and the results of the 2008 General Election for the Botany electorate are included for reference.

Table showing simulated results of 2011 Botany by-election

Table showing simulated results of 2011 Botany by-election, as calculated on 5 March, 2011.

As long as the Uniform National Swing assumption is correct there is realistically no way that the National candidate can get anything less than 50% of the vote. It is worth mentioning that the model used for the simulation does not know that there is no candidate standing from the Green, Maori, United Future, New Zealand First or Progressive parties, which is why the vote estimates for those parties are non-zero

The usual caveats mentioned in the previous Preditions post for the 2010 Mana By-election still apply, so as always, I’m not going to take responsibility for them if they are significantly out, and conversely I will not be taking any credit if they prove accurate.

As for today’s Botany by-election, the only other predictions of the result of the election that I am aware of are from New Zealand futures market iPredict, who as of 18:30 are giving the National candidate a 100.0% chance of winning and the Labour candidate a 1.0% chance of winning (probabilities do not necessarily have to add to 100% due to the bid/ask spread.) I’m not aware of anybody else making quantitative prediction on the results, but if you know of anybody, or if you would just like to take a punt, then feel free to leave a comment below.

[UPDATE] Results are now available at the Elections NZ website.

Read Full Post »

The 2010 Mana by-election will be held today. Unfortunately, we haven’t seen any polling in the electorate, and national-level polling over the past few weeks has been sparse, so it’s not very obvious what to expect.

In spite of the problems mentioned above, I have attempted to predict the outcome of the election and the share of the votes won by each of the major or minor NZ political party’s candidates using a Monte Carlo simulation of 50,000 NZ general elections held today based on recent political polling results. The results for the Mana electorate are determined using the Uniform National Swing model of electorates. The results of the simulation are shown in the table below, and the results of the 2008 General Election for the Mana electorate are included for reference.

Table showing simulated results of 2010 Mana by-election.

Table showing simulated results of 2010 Mana by-election, as calculated on 20 November, 2010.

For reference, similar predictions and results for the 2009 Mt Albert by-election are shown in the table below. The results of the 2009 by-election are of course already known, so you’ll just have to take my word for it that they were not used to cheat by including them as inputs in the simulation.

Table showing simulated results of 2009 Mt Albert by-election.

Table showing simulated results of 2009 Mt Albert by-election, as calculated on 13 June, 2009.

As you can see, the predictions aren’t particularly brilliant. The simulation significantly underestimated the results for the Green Party, and overestimated the results for National. The results for Labour aren’t significantly out, but given that the flow of support was most probably National to Labour and Labour to the Greens, rather than National to the Greens directly, then this was probably just a lucky coincidence.

There are several likely possible causes for discrepancy:

  1. The UNS model for the electorate results is not reasonable.  Empirically, the model has performed well in median seats, but is not very realistic when used in party strongholds such as Mt Albert and Mana, which have historically been safe Labour seats.
  2. There is usually a swing against the government in by-elections relative to that which would be expected from national-level polling, something which the simulation doesn’t take into account.
  3. By-elections tend to attract a different selection of candidates than a general election typically would.
  4. By-elections tend to attract a different selection of voters than a general election typically would, with voter turnout affecting the result in unpredictable ways.

Given the above caveats, the predictions for Mana should be interpreted loosely.  I’m not going to take responsibility for them if they are significantly out, and conversely I will not be taking any credit if they prove accurate.

As for today’s Mana by-election, the only other predictions of the result of the election that I am aware of are from New Zealand futures market iPredict, who as of 15:40 (see screen captures below) are giving the Labour candidate a 96.99% chance of winning and the National a 2.36% chance of winning. iPredict also predict that the Labour candidate will win 46.67% of the vote, the National candidate will win 36.97% of the vote, and all others combined will win 16.80% of the vote. I’m not aware of anybody else making quantitative prediction on the results, but if you know of anybody, or if you would just like to take a punt, then feel free to leave a comment below.

iPredict Mana by-election winner predictions

Screen capture of iPredict's Mana by-election winner predictions, as of 15:40 on 20 November, 2010.

Screen capture of iPredict's Mana by-election vote share predictions, as of 15:40 on 20 November, 2010.

Screen capture of iPredict's Mana by-election vote share predictions, as of 15:40 on 20 November, 2010.

Read Full Post »

The latest NZ political poll was released by Roy Morgan Research on Wednesday, March 10. The poll does not show any significant changes for any of the major or minor NZ political parties relative to either the previous Roy Morgan poll or the most recent Kiwi Poll Guy polling averages.

As usual, the two graphs below summarise the polling averages for the party vote after the new poll. The horizontal axes represent the date, starting 60 days before the 2005 NZ General Election, and finishing 60 days from the present. The solid lines with grey error bands show the moving averages of the party vote for each party, and circles show individual polls with the vertical lines representing the total errors.

Party vote support for the eight major and minor NZ political parties

Party vote support for the eight major and minor NZ political parties as determined by moving averages of political polls. Colours correspond to National (blue), Labour (red), Green Party (green), New Zealand First (black), Maori Party (pink), ACT (yellow), United Future (purple), and Progressive (light blue) respectively.

Party vote support for the six minor NZ political parties

Party vote support for the six minor NZ political parties as determined by moving averages of political polls. Colours correspond to Green Party (green), New Zealand First (black), Maori Party (pink), ACT (yellow), United Future (purple), and Progressive (light blue) respectively.

As always, please check the Graphs page for further simulation results.

Seeing as it’s been over a month since I updated the election probabilities for individual candidates I have included the updated list below. Please see the original post on candidate election probabilities for a rough outline of the methodology. The table contains one new column with respect to the previous version: Elect. 08, which will show either “Electorate” if the candidate was elected to the 49th Parliament as an electorate MP, or “List” if the candidate was elected as a list candidate. David Shearer is listed with the tag “Electorate”, as he is an electorate MP for Mount Albert in the 49th Parliament, even though he was elected to Parliament in the 2009 Mount Albert by-election and not the 2008 General Election. Similarly Gareth Hughes, David Clendon, Cam Calder and Damien O’Conner are tagged as “List.”

Probabilities for each candidate to be elected to Parliament

Probabilities for each candidate to be elected to Parliament through their electorate, through the party list, and the overall combined probability.

There haven’t been too many big changes since the last update.

Additionally, after the last Candidate Election Probability post David Farrar at Kiwiblog did a post on the electorate results for each of the current electorate MP’s. For ease of viewing, here is the above table showing only the candidates that served as electorate MP’s in the 49th Parliament (ordered by their respective electorate’s Electorate Code.)

Probabilities for reigning electorate candidates to be elected to Parliament

Probabilities for reigning electorate candidates to be elected to Parliament through their electorate, through the party list, and both.

Read Full Post »

One of the major goals of this site is to try and predict election results based on recent relevant political polling. This is intended to include not just the total number of seats won by each party, but also viable coalition possibilities and electorate level results.

Today I present the simulation results at the candidate level, including probabilities for each major or minor party candidate to be elected to parliament by either winning an electorate or being selected off their party list. First though, in the interests of disclosure, I thought I should release the data I’m using for the party lists. The 2008 Party Lists are available in MS Excel (.xlsx) format [82kB].

The simulation requires the party lists to be input in the form of a list linking each candidate to the electorate they stood for (or else indicating they were a list only candidate.) The list is based largely on the information on the Party lists for the 2008 General Election page on the Elections New Zealand website, and the electorate information from the Candidates by electorate page from Wikipedia, and is amended at discretion.

The data format is as follows:

  1. Party Code : A unique code for each political party.  Parties are numbered 0~7, and ordered firstly by the number of seats won in the 2008 NZ General Election, and secondly by the number of party votes received.
  2. Party
  3. List Ranking
  4. Name : The name of the candidate as given on the Elections New Zealand website.
  5. Electorate : The electorate the candidate stood in. For list-only candidates this will read “list only.”
  6. Electorate Code : A unique code for the electorate.  Electorates are numbered in alphabetical order, with general electorates (#0 ~ #62) preceding Maori electorates (#63 ~ #69). If the candidate is a list-only candidate candidate this code will take the value -1.

For computational reasons each major or minor party candidate standing in an electorate must have a list ranking. In order to avoid having this requirement affect the results the lists are simply extended to 100 candidates for each party, with electorate-only candidates placed in the lowest ranked positions such that they will never be elected to a list seat. The intermediate positions are then filled with dummy candidates: for example, the candidate “NAT-74-list only” refers to the 74th ranked candidate on the National Party list, with the “list only” suffix indicating that they are a list-only candidate. Please feel free to use or amend the file at will. Corrections gratefully accepted.

The current simulation, however, does not use the 2008 Party Lists. Instead it references an alternative list that has been amended to take into consideration changes during the current term of Parliament. This current list used for the simulation is also available in MS Excel (.xlsx) format [82kB]. A summary of changes is as follows:

  1. Labour : The list reflects the retirements of Helen Clark and Michael Cullen during the term of Parliament. Candidates ranked #3 (Phil Goff) onwards are moved up two list places each. Current Parliamentary members are moved up in the list ahead of unsuccessful candidates (ahead of list candidate #42 Judith Tizard). A new candidate replacing Helen Clark (David Shearer, Mount Albert) is included, ranked #41 and inserted into the list ahead of Judith Tizard. A new dummy list candidate (“LAB-77-list only”) is inserted in position #77 in place of Michael Cullen.
  2. National : Richard Worth (unsuccessful candidate for Epsom, list rank #23) is removed, and subsequent candidates are moved up one rank. A new dummy candidate for Epsom (“NAT-67-Epsom”) is inserted in position #67 in his place.
  3. Green : Jeanette Fitzsimons (list-only candidate, list rank #1) and Sue Bradford (candidate for East Coast Bays, list rank #3) are removed, and subsequent candidates moved up. A new dummy candidate for East Coast Bays (“GRE-66-East Coast Bays”) is inserted in position #66 replacing Sue Bradford. A new dummy list candidate (“GRE-67-list only”) is inserted in position #67 in place of Jeanette Fitzsimons.

The above modifications are only intended to capture the spirit of changes since the beginning of the term of parliament and are of course subject to change when the parties release their official party lists closer to the date of the 2011 General Election. If anybody has any serious objections – or is just curious how things would work out with different party lists – and is willing to provide an updated list in the same format then I would be happy to rerun any simulations.

The candidate level results of the most recent simulation (January 22nd, after the release of the latest Roy Morgan Research poll) are shown in the table below (please click for an enlarged view.)

Probabilities for each candidate to be elected to Parliament

The table gives the probabilities for each candidate to be elected to Parliament by winning an electorate, by being elected from their party list, and an overall probability for either method combined. The “Rank” column gives the respective candidate’s relative likelihood of being elected, and is ordered firstly by probability to be elected, and then by party code and list ranking where there is a tie. Probabilities are rounded to the nearest percent.

The first 89 ranked candidates are guaranteed to be elected, and will of course win 89 seats between them. Candidates ranked 90 through to 114 are considered highly likely to be elected, and each have individual probabilities in the 90% to 100% range. These 25 candidates are expected to win a further 24.6 seats between them, for a cumulative total of 113.6 seats in Parliament. After this we get to the marginal list and electorate candidates: those ranked 115 through to 135 have probabilities in the 10% to 90% range. These 21 candidates are expected to win a further 9.4 seats between them, for a cumulative total of 123.0 seats in Parliament. Next we have 14 more canadidates ranked 136 through to 149 who are considered highly unlikely to be elected to Parliament, with probabilities of less than 10% each. These 14 candidates are expected to win only 0.2 seats between them, bringing the cumulative total to 123.2 seats – an expected overhang of 3.2 seats. Finally, candidates ranked 150 through 800 (many not shown in the table for ease of viewing) have no chance of being elected to Parliament based on current polling data.

I realise that the above calculations may seem little more than trivia at the moment given that we are so far out from the next election, and that the finalised party lists and electorate candidates will not be known for a long time. However, the main motivation for doing this simulation is a hope that people will be able to see which individual list candidate their party vote is likely to be counted for. Closer to the 2011 General Election I will begin publishing “effective party lists” on a regular basis. These effective lists will show only those candidates on the cusp of winning a list seat for each party, and will hopefully give NZ voters a better idea of where their vote is going, and a more meaningful alternative to a quick glance at the top of the lists for each party which some seem to use now when deciding how to cast their votes.

Read Full Post »

A few days ago Jeanette Fitzsimons announced her retirement from Parliament, effective February 11th 2009. Ms Fitzsimons will be replaced by Gareth Hughes, who was ranked #11 on the Green Party List for the 2008 NZ General Election.

The implications of this move for the other major and minor NZ political parties are potentially far greater than many would suspect of a simple swapping of list members, something that has already happened three times in the last year alone (Labour list MP Michael Cullen, National list MP Richard Worth, and Green list MP Sue Bradford have all resigned in the last 10 months.) The reason for this is that the new Green MP Gareth Hughes stood for the Ohariu seat in the 2008 General Election, where he had the effect of splitting the vote and allowing United Future MP Peter Dunne’s party in to Parliament through the MMP electorate waiver (Mr. Dunne did not bring any list MP’s with him, however.) Assuming Gareth Hughes contests Ohariu again in a 2011 General Election he will be campaigning as an MP, not as an outsider, which should change the dynamics of the race. BKD has a multi-part series (prologue, part 1, part 2, part 3, part 4, part 5) looking at how this affects the race in Ohariu.

Firstly, before starting with any analysis, I thought I should mention the latest election simulation results from Ohariu: based on the latest polling averages the United Future candidate (presumably current MP Peter Dunne) is expected to win 73.2% of the time, the National Party candidate (presumably current list MP Katrina Shanks) is expected to win 26.7% of the time, and the Labour Party candidate (presumably current list MP Charles Chauvel) is expected to win 0.1% of the time. I wouldn’t put too much faith in these numbers though, as they are computed partially by comparing the current polling averages to the results of the 2005 and 2008 NZ General Elections, and as National as polling considerably higher than they were then the model is behaving a bit pathologically. Additionally, the model does not take the merits of individual candidates into account, instead calculating probabilities for “generic” candidates from each party, and so doesn’t take into account any changes in the dynamics that will occur due to Mr. Hughes’ presence in Parliament.

Rather than focusing on trying to calculate the probabilities for each of the above candidates, I would instead like to investigate the results of an election under two simple scenarios; firstly with Peter Dunne winning Ohariu, and secondly with him losing. The implications of the first scenario are calculated using a MC Simulation of 50,000 NZ Elections with Dunne winning Ohariu. The resulting distributions of seats for National and Labour are shown below.

Histogram showing the total number of seats National are expected to win in parliament under Scenario #1

Histogram showing the total number of seats National are expected to win in parliament under Scenario #1, with Peter Dunne winning the Ohariu electorate. National are expected to win 66.5 +- 1.8 (RMS) seats.

Histogram showing the total number of seats Labour are expected to win in parliament under Scenario #1

Histogram showing the total number of seats Labour are expected to win in parliament under Scenario #1, with Peter Dunne winning the Ohariu electorate. Labour are expected to win 38.6 +- 1.6 (RMS) seats.

Under this scenario, National are expected to pick up a total of 66.5 +- 1.8 seats in Parliament, and Labour a total of 38.6 +- 1.6 seats.

The implications of the second scenario are calculated analogously using a MC Simulation of 50,000 NZ Elections with Peter Dunne not winning Ohariu. The resulting distributions of seats for National and Labour are again shown below.

Histogram showing the total number of seats National are expected to win in parliament under Scenario #2

Histogram showing the total number of seats National are expected to win in parliament under Scenario #2, with Peter Dunne not winning the Ohariu electorate. National are expected to win 66.8 +- 1.8 (RMS) seats.

istogram showing the total number of seats Labour are expected to win in parliament under Scenario #2

Histogram showing the total number of seats Labour are expected to win in parliament under Scenario #2, with Peter Dunne not winning the Ohariu electorate. Labour are expected to win 38.8 +- 1.6 (RMS) seats.

At a casual glance, it may not be easy to see the difference between these two graphs and the ones shown earlier. However, under this scenario, National are expected to pick up a total of 66.8 +- 1.8 seats and Labour a total of 38.8 +- 1.6 seats. The slightly counter-intuitive result of the study is that if Peter Dunne loses the Ohariu seat both National and Labour are individually expected to be slightly better off, and this result holds regardless of which party’s candidate picks up Ohariu in the event that Mr. Dunne loses. The reason for this outcome is that if Peter Dunne loses Ohariu, his party does not achieve the electorate waiver, and as they are also unlikely to acheive the 5% party vote threshold they end up with no seats in Parliament. This effectively creates an extra list seat for National and Labour to fight over. The probability of it falling to one party or the other (or to a minor party) is roughly proportional to their respective party vote totals. The actual results are shown in the table below to two decimal places:

Comparison of total number of seats won in Parliament by each party for two different scenarios

Comparison of total number of seats won in Parliament by each party for two different scenarios; Peter Dunne wins Ohariu, and Peter Dunne loses Ohariu. The right-most column shows the expected difference for each party between the two scenarios.

This raises an interesting problem with regards to election strategy in the Ohariu electorate. If United Future were equally capable of going into coalition with either a Labour-led or National-led coalition, then Labour would be slightly better of if Peter Dunne won the seat, and National slightly worse off. However, as Peter Dunne has made clear, United Future would not be interested in going into coalition with Labour, and so therefore the opposite applies. Labour’s counter-intuitive goal for the Ohariu electorate in the 2011 NZ General Election is not to win, but rather to make sure that the United Future candidate (or ACT or Maori Party candidates, if applicable) do not win. To do otherwise, and vigorously contest the electorate and risk splitting the vote three or more ways, as they did in the 2008 General Election, would be a massive tactical and strategic blunder, and would indicate a poor understanding of the MMP electoral system. Of course, the above conclusion is of limited importance if the the Labour Party are unable to close the 22% point polling gap between themselves and National, but could be crucial in determining the results of a closer election.

Read Full Post »