Legal Beagle by Graeme Edgeler

Read Post

Legal Beagle: Voting in an STV election

115 Responses

First ←Older Page 1 2 3 4 5 Newer→ Last

  • Sacha, in reply to Steve Todd,

    tempted to stop after 7

    Ak • Since May 2008 • 19745 posts Report

  • izogi, in reply to Steve Todd,

    The writer warned voters not to rank-order too many candidates, because “If you choose to number your preferences then your one vote can be split, supporting all of your numbered preferences depending on how the vote counting proceeds, including those that you don’t want.” (He said this had happened in Kapiti Coast – 2007?)

    As agents for informing the public I find it disconcerting enough that major media outlets frequently don't bother to fact check stuff presented as if it's objective fact, and which should be easily determined as right or wrong, before it's published in online comment threads.

    I'm not sure if I should feel any better to be reminded that it doesn't always even happen in the more controlled printed letters to the editor, let alone in an age when newspapers probably had staff who really should have been able to understand how a vote count actually works.

    Wellington • Since Jan 2007 • 1142 posts Report

  • Steve Todd, in reply to izogi,

    The sad fact of the matter is, izogi, “media” workers have only ever had a very basic understanding of how STV works. That is very clear from the hopelessly incomplete and inaccurate descriptions of STV we see in our local papers, particularly around local election time.

    I’m sure that newspaper editors, in this democracy of ours, adhere to the principle of ‘free speech’, which (simplistically), I take to mean we are free to communicate with each other, even when what we espouse is actually quite wrong. Follow-up letters from readers (often unpublished – I have personal experience of this) will give (hopefully) correct information.

    However, I want to take the opportunity given by your response, to actually show readers exactly how later preferences can never harm earlier preferences, using the 2007 Kapiti Coast District (at-large) election, that I referred to upthread.

    This was an election to fill five seats. For the purposes of this explanation, the description begins at iteration 14 – Anne Molineux is already elected.

    As you read through it, keep in mind that, at the conclusion of each iteration, the current keep values of the elected candidates are re-calculated, downwards, to take account of the increasing number of votes that have dropped out of the election; and that the votes remaining in the election are recounted, using their new (lower) keep values.

    Iteration 14 – Quota 2832.64

    Total surplus is 279.30

    David Scott is elected with 2892.45 votes (surplus 59.81). Norm Pashby has 1650.48 votes and is now excluded (1650.48 plus 279.30 = 1929.78, which is less than the next lowest candidate, Hilary Wooding, on 2058.21).

    Mansell 2201.31
    Wooding 2058.21

    The gap between Barry Mansell and Wooding is 143.10 votes. Pashby's 1650 votes and the total surplus of 279.30 votes are now redistributed.

    Iteration 15 – Quota 2761.23

    Total surplus is 1048.76

    Peter Ellis is elected with 3091.05 votes (surplus 329.81)

    Mansell 2371.47
    Wooding 2273.72

    Following the distribution of the total surplus of 1048.76 votes, the gap between Mansell and Wooding is now 97.75 votes. This indicates that Pashby's supporters tended to favour Wooding over Mansell.

    Iteration 16 – Quota 2709.49

    Total surplus is 475.25 votes

    Tony Jack is elected with 2757.43 votes (surplus 47.93 votes)

    Mansell 2487.54
    Wooding 2456.18

    Following the distribution of the total surplus of 475.25 votes, the gap between Mansell and Wooding is 31.36 votes. Jack's surplus, plus the surplus votes of the other three elected candidates, are now redistributed.

    Iteration 17 – Quota 2685.58

    Total surplus is 287.43

    Mansell 2544.51
    Wooding 2539.22

    Following the distribution of the total surplus of 287.43 votes, the gap between Mansell and Wooding is now only 5.29 votes. It is now clear that the supporters of the four elected candidates are tending towards Wooding, rather than Mansell.

    Given that both candidates are still about 140 votes short of the quota, and that there are no more candidates to be excluded from the count (adding new votes to the mix), it can now be said that Mansell is doomed.

    Iteration 18 – Quota 2671.27

    Total surplus is 170.40

    Mansell 2587.49
    Wooding 2584.64 (gap 2.85)

    Iteration 19 – Quota 2662.58

    Total surplus is now down to 100.66

    Mansell 2612.06
    Wooding 2612.43

    Wooding has now overtaken Mansell. The remaining iterations are performed in order to redistribute the ever-decreasing total surplus, and to put Wooding up over the final quota.

    Iteration 20 – Quota 2657.41

    Total surplus is 59.23

    Mansell 2626.77
    Wooding 2628.82 (gap has widened from 0.37 votes to 2.05 votes)

    Iteration 21 – Quota 2654.36

    Total surplus is 34.78

    Mansell 2635.42
    Wooding 2638.50 (gap 3.08)

    Iteration 22 – Quota 2652.55

    Total surplus is 20.40

    Mansell 2640.51
    Wooding 2644.19 (gap 3.68)

    Iteration 23 – Quota 2651.50

    Total surplus is 11.95

    Mansell 2643.50
    Wooding 2647.53 (gap 4.03)

    Iteration 24 – Quota 2650.88

    Total surplus is 7.00

    Mansell 2645.25
    Wooding 2649.49 (gap 4.24)

    Wooding has now almost attained the quota, falling 1.39 votes short at this iteration.

    Iteration 25 – Quota 2650.51

    Total surplus is 4.23

    Mansell 2646.28
    Wooding 2650.64 (gap 4.36)

    Wooding has now attained the quota and is elected. Mansell is excluded.

    From the above, it can be seen that the later preferences of the voters who supported the already-elected candidates, at each iteration, favoured Wooding over Mansell, and that, therefore, the voters, collectively, preferred Wooding to Mansell, although it was a remarkably close-run thing.

    Therefore, it is clear that Mansell was ranked lower than Wooding (or not ranked at all) on the relevant voting documents that played a part in deciding which candidate would fill the fifth and final seat.

    Wellington • Since Jul 2013 • 125 posts Report

  • Paul Campbell,

    The bulk of redistributed votes come from those left over each time a candidate reaches the threshold and has votes left over (those votes ‘left over’ are not votes of individual people, they are fractions of votes equally shared between everyone who elected the candidate which are distributed to each voter’s next preference).

    However there are also other fractional votes that come into play during counting from the other already elected candidates as the voting threshold reduces.

    And the threshold reduces as votes (or redistributed fractions of votes) reach the end of their voter’s list and have no where to go – for example the Dunedin election this year started with a threshold of 2595 and ended with one of 2403, that mean that at least 2200 people (11 candidates times a 200 vote spread) voted for few enough candidates that some portion of their vote was left on the floor …. some of those are people who only voted for candidates who were excluded and their vore rested with no one .. others left their votes with 2 or 3 other candidates but still had a small fraction of their vote in play at the end …. my guess is that 0.1 of my vote was left unassigned at the very end. It was probably far far more people than 2200 who had a fraction of their vote not counted because sorting 43 names is not easy

    Dunedin • Since Nov 2006 • 2623 posts Report

  • Rich of Observationz,

    “media” workers have only ever had a very basic understanding of how STV works

    And as this thread demonstrates, people who understand STV haven't cracked being able to explain it to anyone who isn't a voting system geek.

    Back in Wellington • Since Nov 2006 • 5550 posts Report

  • Steve Todd, in reply to Paul Campbell,

    I agree with your summation, Paul, but I can't help reiterating that it was not necessary for people to rank-order all 43 candidates in order to have an effective say in the outcome. Associate-Professor Janine Hayward recommeded people just rank-order the candidates they want to see elected. I go a bit further and say people should rank-order only those candidates they are able to. If your vote runs out and there are still three or four seats (out of 14) to be filled, what does it matter? You've affected the outcome in the way you wanted; others can determine who fills the last vacancies. Everyone happy.

    Wellington • Since Jul 2013 • 125 posts Report

  • Steve Todd, in reply to Rich of Observationz,

    Rich, if you were to read the papers I linked to (at the dunedinstadium website) near the top of page 2 of this thread, particularly the first four, I doubt you would come back and say you still don't know how STV works.

    For those who don't want to know (or who don't particularly care about) the workings of STV, all they have to do is what I said to Paul a few minutes ago, just rank-order those candidates they are able to – job done.

    Wellington • Since Jul 2013 • 125 posts Report

  • Paul Campbell, in reply to Steve Todd,

    unless of course all the people you choose are eliminated, then all of your vote is still in play and is thrown away ..... as I mentioned it's stupidly difficult to rank so many different people ...

    However once you reach the "people I don't know enough about to vote for, plus people I don't want to vote for" one thing you can do is separate out from that list who you rate as "people I actively despise" and start numbering them backwards from the last number (43 in Dunedin's case) starting with the person you despise the most, this can actually be a quite satisfying process .... then take the remaining "people I don't know enough about to vote for" list and number them arbitrarily between the two groups.

    The goal here is to make sure that your vote, or whatever is left over, lodges with someone not in your "actively despise" list - the alternate to not doing this is that you effectively contribute your still active vote to decreasing the quota/threshold ... which means you are effectively spliting your vote between ALL the candidates, including the ones you despise (and including ones already elected who you may not like, freeing up their voters STV votes)

    Dunedin • Since Nov 2006 • 2623 posts Report

  • Steve Todd,

    Again, agreed. This is what Andrew Geddes suggested people might want to do, but I've heard that he actually confused people. Also, he talked about making sure you don't help the ones (plural) you don't like, whereas the "numbering all candidates" ploy only ensures you don't help elect your bottom-ranked canidate.

    For example, if a voter's 42nd preference (out of 43) is activated, that means the previous 41 candidates are either elected or excluded, and preferences 42 and 43 are vying for the last vacancy. In that case, preference 42 is the last candidate to be elected, or the runner-up, and preference 43 is the runner-up candidate, or the last to be elected.

    Wellington • Since Jul 2013 • 125 posts Report

  • Paul Campbell, in reply to Steve Todd,

    right but the difference is that if you had otherwise just voted for 9 your vote goes to the 10th, not the 42nd .... but, if candidates 10-41 drop out during the counting and your vote does end up residing with #42 then, well that's why you listed them in reverse order, yes your vote ends up with someone you don't much like, but it goes to elect that person over someone you dislike even more.

    Wile that's a rather negative sort of result it's still a great use of your result and ends up with a council without that person you despise the most.

    Having said that - I only voted for 9 people, 3 of whom were elected so most of my vote went to good use, some small portion was left live, why didn't I vote for all 43? in the end it was way too much of a pain, it should be a lot easier

    Dunedin • Since Nov 2006 • 2623 posts Report

  • Steve Todd, in reply to Paul Campbell,

    Once again, I'm not arguing with you, Paul. In my humble, you're spot on.

    "[...] why didn't I vote for all 43?" (Strictly speaking, why didn't I rank-order all 43?)

    It's pretty clear to me, you didn't rank-order all 43 because you knew, deep down within, that your rankings beyond 9 would have merely been arbitrary. Yes, indeed, it would have been a pain, and for what? Answer: certainly no additional satisfaction in a job well done.

    "[...] it should be a lot easier." And it was! You made sure of that, by rank-ordering only 9 candidates. (Just quietly, between you and me, I say, "Well done.") Imagine if this election had been by multiple-FPP, citywide? You would still have agonised over whether or not to give a tick to one, two, ..., 10, or 14 candidates. And, you would still have had to sort them out, in your own order of preference (more or less), even though you would not have been voting that way.

    I'm going to let you into a little secret. As you probably know, I rank-ordered 13 out of the 20 Capital and Coast DHB candidates (see upthread). All seven elected candidates - six women and one man - were included in my 13. But, my first preference was for that great lady, (incumbent member) Helene Ritchie, who finished up as the runner-up! As you know, that means my vote stayed solely with her right through the entire count. To me, that's a bummer, but, as you can imagine, I'm still pretty happy. So, too, should you be (in my view).

    Wellington • Since Jul 2013 • 125 posts Report

  • izogi, in reply to Paul Campbell,

    unless of course all the people you choose are eliminated, then all of your vote is still in play and is thrown away ..... as I mentioned it's stupidly difficult to rank so many different people ...

    Given most people out there seem to compare this with FPP, claiming that FPP is more simple (and therefore better), I think it needs to be pointed out that FPP also results in votes being thrown away, except that it happens immediately for everyone whose first choice doesn't get elected. STV also doesn't require anyone to rank more than their first choice, so you can quite easily make your vote about as meaningful as any FPP vote ever was. I guess the main difference in that respect is that under STV, everyone else might not be voting so simplistically.

    Wellington • Since Jan 2007 • 1142 posts Report

  • Paul Campbell, in reply to izogi,

    Given most people out there seem to compare this with FPP, claiming that FPP is more simple (and therefore better), I think it needs to be pointed out that FPP also results in votes being thrown away, except that it happens immediately for everyone whose first choice doesn’t get elected.

    yes exactly

    Dunedin • Since Nov 2006 • 2623 posts Report

  • Paul Campbell, in reply to Steve Todd,

    I’m going to let you into a little secret. As you probably know, I rank-ordered 13 out of the 20 Capital and Coast DHB candidates

    lucky you, the Nats took away my right to elect my local DHB this year

    Dunedin • Since Nov 2006 • 2623 posts Report

  • izogi, in reply to Steve Todd,

    The sad fact of the matter is, izogi, “media” workers have only ever had a very basic understanding of how STV works. That is very clear from the hopelessly incomplete and inaccurate descriptions of STV we see in our local papers, particularly around local election time.

    Also, assuming it's true, this is really depressing.


    On the surface politics often seems to be the last major topical area which local media spends any resources on. Maybe that's just because it's cheap to pay for never-ending opinion and sniggering as if the whole thing's just an entertaining tactical game. I suppose understanding the actual rules requires more investment than just making stuff up.

    I’m sure that newspaper editors, in this democracy of ours, adhere to the principle of ‘free speech’, which (simplistically), I take to mean we are free to communicate with each other, even when what we espouse is actually quite wrong. Follow-up letters from readers (often unpublished – I have personal experience of this) will give (hopefully) correct information.

    I haven't interacted with letters to the editor for ages, but I had cautiously positive experiences when I did (back in Evening Post days). Editors would often add a note to correct obviously wrong things that were published from people, if necessary, and I routinely found that if I actually followed the stated rules (length limits, etc), a letter I wrote would normally be published. By comparison, comment threads from the same newspapers are rubbish. They're controlled by anonymous moderators who seem to let random, frequently personally abusive and incorrect, comments through on a whim... and block others for no obvious reason. A couple of times now I've avoided interacting with journalists because I don't want to be subjected to the utter crap in comment and facebook threads that'll most likely flow underneath any article that's published.

    Wellington • Since Jan 2007 • 1142 posts Report

First ←Older Page 1 2 3 4 5 Newer→ Last

Post your response…

This topic is closed.