Straw Man

Internet Electoral Data Demigod Patrick Ruffini has just posted his 2008 GOP straw poll. He provides lots of interesting ways to break down the poll data (by state, region, even by referring blog!) that make data nuts like me want to hug him and squeeze him and call him George. Go vote, and then take a look at the overwhelming popularity of one “fantasy” candidate.

About these ads

16 thoughts on “Straw Man

  1. Internet “polls” don’t even live up to the minimal usefullness of actual polls. I can understand participating in it as a lark but hopefully you aren’t really bothering to analyze data that is so hopelessly compromised.

  2. An Internet poll is only different from a traditional party straw poll in being much larger and more geographically dispersed. Traditional straw polls have exactly the same selection bias characteristics as this one does.

    Before you can say whether a poll is “useful” you have to know what its ostensible use is. If its purpose is to divine a sensus fidelum of candidate preference among a set of people normally thought of as “the party base” or “highly motivated voters” you could do a lot, lot worse than an Internet straw poll. In fact, a standard stratified random phone poll would be much inferior.

  3. Uh no Kathy there’s a huge difference between a straw poll and an internet poll: in an internet poll a person or even a device can vote repeatedly skewing the results in any direction and in manner that cannot be reasonably determined by looking at the data. A straw poll on the other hand is adminstered by people in a manner so as to make cheating on it at least much harder.

    “If its purpose is to divine a sensus fidelum of candidate preference among a set of people normally thought of as “the party base” or “highly motivated voters” you could do a lot, lot worse than an Internet straw poll. In fact, a standard stratified random phone poll would be much inferior.”

    I really really hope you are kidding here, because otherwise you need to go back and study statistics again. The mathematical anaylsis of statistical data only works when you can control the sample set so as to eliminate events like multiple voting. Without that basic control (which no internet poll has) it is meaningless data.

  4. Kathy is right. Ruffini is a party operative in touch with people who are very active in the party. By taking a straw poll, he can find out who the most energized party activists support. Now, will that give you the eventual nominee? Not necessarily. It might give you the next Howard Dean.

    I voted. Sam Brownback for round one. Condi Rice as the fantasy candidate.

  5. “Kathy is right.”

    Uh no she’s not, not even remotely. In addition to the issue of multiple voting you run into an inherent selection error becausew of course only those with internet access can use internet polls. You run into a further selection error in that the user has to come to the poll rather than vice versa so you are selecting for people in a given internet geography. These are both big issues for any system that wants to pretend to have statistical veracity.

    Do I need to go on or have you gotten the point?

  6. Tlaloc, there is no point in blathering about parametric statistics when the purpose of the poll is not to produce parametric estimates. Ruffini runs his polls for the purpose of finding out what Internet-aware party activists and highly motivated and interested conservative bloggers and blogreaders are thinking. You’re still stuck in Gallupland, assuming that all polls are designed to estimate total population fractions from a stratified random sample. This poll gets the sample it wants by using the very characteristics you claim make it invalid.

    Multiple votes might be a problem, but its my sense that most people do not overvote. Ruffini does track votes by referring site, so would be aware of a coordinated pollbomb effort.

  7. Like I said if you want to do it as a lark to determine something trivial and un-quantifiable (the political vision of the internet users of one site) then have a ball. My objection was to your apparent regard for this data as actually meaningful of anything substantial.

    As long as you know it’s exactly as accurate as a magic eight ball then by all means enjoy.

  8. I think Kathy’s kind of right on this one. The selection bias, in this case, is really what Ruffini is going for: it’s how he gets his convenience sample. So, in terms of selection, there’s no problem for him there. He doesn’t want random people’s votes, he wants an idea of what a GOP primary might look like if it was held today.

  9. Just admit it, T, you just want to disagree with anything stated in a post on this forum at any time. Kathy and I have both had graduate stat. methods courses, so we’re well aware of all the stuff you are complaining about. Ruffini’s poll is clearly going to yield better info than a magic eight ball, but not as good as a gallup poll. Get over yourself.

  10. “Just admit it, T, you just want to disagree with anything stated in a post on this forum at any time.”

    No just the stuff that’s wrong. I’m funny like that. I provided ample evidence to support my contentions in this case so your claim I am disagreeing just for disagreements sake doesn’t wash.

    “Kathy and I have both had graduate stat. methods courses, so we’re well aware of all the stuff you are complaining about.”

    So then you accept that my position is correct. Why then do you accuse me of disagreeing for disagreements sake?

    “Ruffini’s poll is clearly going to yield better info than a magic eight ball, but not as good as a gallup poll.”

    I disagree, you have absolutely no way to verify that any of the data comes from mopre than 1 person. And you can’t even verify that that person is a republican. Obviously the result is precisely as meaningful as a magic eight ball.

  11. To give you a couple quick examples of agreement between me and the clubbers I’ve said I find PC abhorrent, I see no issues (so far at least) with Judge Robert’s nomination, and I like many of the same movies as you do, Hunter.

    I do think you are completely backwards on a great many issues but you clearly think the same of me. Isn’t discourse fun? However when you accuse me of playing devil’s advocate on an issue that you then admit I was right on all along I have to wonder if you aren’t getting a bit defensive.

  12. I didn’t admit you were right all along. Your position was always “no value.” Our position was always “some value.”

  13. And my position is more extreme than Hunter’s: Ruffini’s poll does not just have “some value”; in this case, given the target population, the timing, and the subject, it has more value than a traditional Gallup-style poll. It is more than three years until the next presidential election and about 2.5 until the first primaries. There is zero value in polling average Americans about their presidental candidate choices right now. They are not engaged, and fewer than one in 20 could even minimally identify all the names on Ruffini’s poll. The preferences that are important right now are the preferences of the people who are going to put effort and money into propelling candidates into the primary cycle. The same people that Ruffini attracts.

  14. That’s a good point. Plus, I haven’t seen any drives to pack the Ruffini ballot box. Nor has any one else I know. I think people are honoring the straw poll.

  15. “I didn’t admit you were right all along. Your position was always “no value.” Our position was always “some value.””

    You said “Kathy and I have both had graduate stat. methods courses, so we’re well aware of all the stuff you are complaining about.” Do you often take classes to learn things of no value and then go ont to boast about how you learned these things of no value and thus don’t have to be reminded of them?

    “That’s a good point. Plus, I haven’t seen any drives to pack the Ruffini ballot box. Nor has any one else I know. I think people are honoring the straw poll.”

    Which means what? You don’t have to have a drive when you can write a simple script that would vote every 15 seconds from a rotating IP address. Admit it- you have absolutely no wayto know that any of the votes except the ones you make personally come from anyone at all.

  16. “And my position is more extreme than Hunter’s: Ruffini’s poll does not just have “some value”; in this case, given the target population, the timing, and the subject, it has more value than a traditional Gallup-style poll.”

    SO much for Hunter’s claim you’ve taken stats courses. The poll isn’t targetted because there is absolutely no restriction on who votes. To prove it to you I’ll go vote in it. Am I a registered republican? Nope and yet here I am casting a vote about their primary.
    I voted for Giuliani and Fred Thompson and said I was from Montana. None of which is accurate or true. I could easily set up a script to vote for the same people or to rotate votes through a small selection and have it vote 15,000 times today alone. It’s not hard to do. And you’ll never know if someone has.

    Now are you still going to bluff that this poll has meaning beyond that of an astrology chart?

    “There is zero value in polling average Americans about their presidental candidate choices right now. They are not engaged, and fewer than one in 20 could even minimally identify all the names on Ruffini’s poll.”

    Your point is? Just because you want to say a Gallup poll won’t give you the insight you want doesn’t mean the huge gaping flaws in internet polling go away suddenly.

Comments are closed.