More Stupid Shit


Please, dear Jeebus, let it all be over soon.

So, while I was drinking coffee this morning, I turned on the CBS morning show to see what they’d have to say about Sweet SweetBarack’s prime-time address last night. Before they got to that topic, however, they were talking about polls. Harry Smith, Julie Chen, and the collection of other empty suits mentioned that Senator Obama is “ahead in most polls.” Then they cut to a segment in which the reporter uttered the same phrase.

Excuse me? Ahead in most polls?

Obama is ahead ineverysinglefuckingnationalpoll, and has been for a month and a half. Saying that he leads in “most polls” is like saying an undefeated team has won most of its games. Is this some of that bullshit “objectivity” that the major news organizations like to claim they exhibit? It’s not bias to say the following: Shit looks bad for McCain. Real bad. In fact, he hasn’t even gotten to 50% in any of the national polls (with the exception of one USA Today/Gallup pollwhich was almost certainly an outlier).

That ain’t bias. That’s a fact. 

But the dumbassery didn’t stop there. Oh, no.

These halfwits went on to talk about how, in some state polls, John McCain is within the margin of error! It’s true! So, and this was their example, even though Obama is up seven points in Ohio, due to the four-point margin of error, it could be a tie! Really! Trust us!

Come the fuck on. If you’re up by seven points in a poll of 600 people (the size of most state polls), it’s almost impossible for that to be a tie. Kevin Drum addressed all of this in 2004, and he did it pretty well. So I think I’ll let him handle it again.Take it away, Kevin:

TheGlobe and Mail reported this [49-47 Kerry-Bush poll] as a “statistical tie”
because Kerry’s 2% lead is within the poll’s margin of error (MOE) of
3%. This in turn is based on the theory that (a) statistical results
are credible only if they are at least 95% certain to be accurate, and
(b) any lead less than the MOE is less than 95% certain.

There are two problems with this: first, 95% is not some kind of
magic cutoff point, and second, the idea that the MOE represents 95%
certainty is wrong anyway. A poll’s MOEdoes represent a 95% confidence interval for each individual’s percentage, but itdoesn’t represent a 95% confidence for the difference between the two, and that’s what we’re really interested in.

In fact, what we’rereally interested in is the probability
that the difference is greater than zero — in other words, that one
candidate is genuinely ahead of the other. But this probability isn’t a
cutoff, it’s a continuum: the bigger the lead, the more likely that
someone is ahead and that the result isn’t just a polling fluke. So
instead of lazily reporting any result within the MOE as a “tie,” which
is statistically wrong anyway, it would be more informative to just go
ahead and tell us how probable it is that a candidate is really ahead.
As a service to humanity, here’s a table that tells you:

So in the poll quoted above, how probable is it that Kerry is really
ahead? The MOE of the poll is 3%, so go to the top row. Kerry’s lead is
2%, which means there’s a 75% probability that he’s genuinely ahead of
Bush (i.e., that his lead in the poll isn’t just due to sampling error).

–snip–

Now, there are plenty of reasons other than sampling error to take
polls with a grain of salt: they’re just snapshots in time, the results
are often sensitive to question wording or question ordering, it’s
increasingly hard to get representative samples these days, etc. etc.
But from a pure statistical standpoint, a lead is a lead and it’s
always better to be ahead than behind.

So: how about if the media gets itself out of the mythical
“statistical tie” business and just reports the actual probabilities
instead? The table above does all the heavy lifting, and all it takes
is a5-line Excel spreadsheet if you want more precision. Simple.

See? It’s not that hard.

I know the news people have a “horse race” narrative that they love to push, and conventional wisdom is that blowouts aren’t fun to watch (and, as we all know, fewer eyeballs on screens means lower ad revenue). But shit. Call ’em like you see ’em.

I hope that in January, after Mount Rushmore has been re-carved with the faces of Malcolm X, Muhammad Ali, Jeremiah Wright, and Aretha Franklin; after “Fuck tha Police” becomes the new national anthem; after all cigarettes are outlawed except for Kools and Newports; after we’ve all been forced to become Commie Muslim atheists; after President Obama hands the nuclear launch codes to al-Qaeda; after abortions are not only fully funded but mandatory; after Rastus Odinga Odinga becomes Secretary of State; and after we’ve all been interned in Learn How To Hate Whitey camps–after all of that, I hope that Caliph Obama Marx X institutes some serious statisticalre- education programs, so we won’t ever have to deal with this kind of stupid again.

I would have said that we’d have Huey Newton, Nat Turner, and Stokely Carmichael on our money, but of course we won’t need any money in our coming Worker’s Paradise, now will we, Comrade?

4 thoughts on “More Stupid Shit

  1. Hell Kat says:

    I hope that in January, after Mount Rushmore has been re-carved with the faces of Malcolm X, Muhammad Ali, Jeremiah Wright, and Aretha Franklin; after “Fuck tha Police” becomes the new national anthem; after all cigarettes are outlawed except for Kools and Newports; after we’ve all been forced to become Commie Muslim atheists; after President Obama hands the nuclear launch codes to al-Qaeda; after abortions are not only fully funded but mandatory; after Rastus Odinga Odinga becomes Secretary of State; and after we’ve all been interned in Learn How To Hate Whitey camps–after all of that, I hope that Caliph Obama Marx X institutes some serious statistical re- education programs, so we won’t ever have to deal with this kind of stupid again.
    I think this is my favorite run-on rant ever.

    Like

  2. Doc says:

    Jude, you know exactly why the media keeps doing the “ahead in most polls” thing.
    1) You never want to appear like you understand math. Just like it’s OK to stereotype yourself as a bad driver or having a poor sense of direction, journalists became journalists because they suck at math.
    2) You don’t want to have to be in the “Tom Brokaw Shit Eating Chair” and have to be the guy who goes on TV and says “Florida is for GORE!” and then have to say later “Sorry, we made a mistake.” TV journalism means never having to say your sorry. To keep that idea alive, we couch our bets a bit.
    3) Ad money. If the polls can be viewed as “Hey, you might have an outside chance here…” more folks will continue to dump money to the campaigns and more campaign folks will freak out and dump that money into “Obama has been known to chew on pencils. We can’t have THAT kind of LEADER” ads in every C-break of every show I’m watching.
    4) Human nature. We like to win, but blow outs are boring. The only time I watched or listened to a blow out from start to finish was when my beloved Tribe beat the Yankees 22-0. I think I had it on internet radio and it was pure joy listening to Tom Hamilton bask in this thorough ass-whipping. Other than that, if my team’s up by 20 points and there’s 3 minutes left, I’m looking for Friends reruns.
    To that last point, as much as you hate the bad math, I’d think you’d be happier that folks are still doing the “wait, this thing’s not over” thing. It’ll hopefully keep people engaged enough to remember that an intention to vote doesn’t count as a vote until they trek their ass down to the polling place and punch the little card (or tap the screen or whatever). If too many people are going to do the “Obama’s won, I was going to vote but I’d rather watch this high colonic info-mercial” we might have President McCain.
    Just a thought. And a scary one at that.
    Doc

    Like

  3. Robert Earle says:

    If you’re really interested in polls and poll analysis, and you are NOT currently reading fivethirtyeight.com (particularly, the nightly “Today’s Polls” posts), start now.
    http://www.fivethirtyeight.com/
    Nate Silver is a well-known baseball stats guy who this election has decided to put his statistics knowledge to use by tracking the polls and the election.
    Whenever some TV talking head starts getting me worried about how “things are getting tighter”, etc., I go read Nate’s posts, to see what is really happening. From last night:
    “What we can say, when we put all this information together, is that there are two things that John McCain is NOT doing.
    “Number one, John McCain is NOT closing Obama’s margin as quickly as he needs to (if indeed he is closing it at all).”

    “Number two, John McCain is NOT gaining ground in the states that matter the most. The top tier of states in this election are Virginia, Colorado and Pennsylvania.”

    Like

  4. Melissa says:

    The penultimate paragraph of this post (how’s that for alliteration?) might be the best thing I’ve read all year. And, for extra points, it made me chortle aloud and briefly choke on my coffee.

    Like

Leave a Reply to Melissa Cancel reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: