as sense of shame would be required. And even if Strategic Vision let Silver sit in on their phone banks, he’s so deeply invested in calling them a fraud that he wouldn’t change his story.

Without reading the whole article above, and jumping right to the link, I saw the graphs uncoached. And then it hit me, and I came the same conclusion that Neil did above.

Neil is right. Silver starts by removing data from his data set without any justification, the cardinal sin of statisticians everywhere (and broken more often than the sixth Commandment). By neglecting the roughly 5% of people that typically aren’t sure, don’t understand, or choose a third alternative, Silver generates a bias in numbers that actually isn’t there.

Examples:

48 kept, 50 kept , 2 dropped
48 kept, 47 kept , 5 dropped
46 kept, 49 kept , 3 dropped
48 kept, 46 kept , 6 dropped

Look familiar? Biased much? Maybe in the eye of Nate.

Baseball statistics aren’t opinion-based, so there is a reasonable expectation of uniform end-digit incidence. Opinion polls are, by their very nature incomplete, and have some small amount of unknowns. Silver’s baseball methodology simply doesn’t apply.

Now I must call into question Mr. Silver’s ability to properly process baseball data correctly. I’m curious if there is any way to demand that Major League Baseball go over his work with a nit comb. After all, a potential hall-of-famer could be wrongly excluded from his rightful place. All because of bad math.

Shoulda kept it to yourself until you had an explanation besides shouting fraud, dude.

As a lifelong baseball fan, one of the reasons I refused to delve into SABRmetrics is because its devotees are often insufferable jerks who pass judgment on professional ballplayers, coaches and managers despite the probability that none of them could hit a batting practice fastball.

Such is the tool who gave us the anti-Morgan site you linked. Joe’s crime is to be a heretic in the church of “Moneyball,” Michael Lewis’ runaway bestseller about the ballyhooed strategies of Oakland Athletics GM Billy Beane. FireJoeMorgan.com’s pro-Moneyball / anti-Joe psychosis led its founder and fans (and a SFWeekly writer) to the conclusion that Morgan’s ESPN partner Jon Miller hates Joe as much as they do, and do they ever.

Thankfully, FireJoeMorgan.com failed in its mission. It’s dead, and Joe’s still rockin’ it on Sunday night.

Joe Morgan was the gold standard for second basemen when I first took interest in the game, and was a key cog in the legendary Big Red Machine featuring Pete Rose, Johnny Bench, Tony Perez, and Dave Concepcion. He’s been a great player, he’s played with great players, he’s been coached and managed by great managers, he’s got World Championship rings. OTOH, Billy Beane, the hero of Moneyball, has got … hmmm, lemme double che–NOTHING. In fact, Oakland’s devotion to Beane’s half-baked methods has brought it back to the pack (if by “the pack” you mean “the bottom”) and hemorraging cash and fans.

Never mind Beane’s blunder in signing Rockies star hitter Matt Holliday and dealing him away halfway into the season — his biggest display of empty-headstrongedness was at the end of the 2006 season. Given the opportunity to promote Ken Macha’s highly-regarded 3rd base coach Ron Washington to manager, Beane instead chose his personal pal Bob Geren, who buys into letting Mr. Roboto guide on-the-field decisions and (unlike Macha and his predecessor Art Howe) presumably doesn’t bristle under Beane’s Jerry Jones-like tentacles reaching into the dugout. Washington instead took over the thankless task of rebuilding the hapless Texas Rangers, which nearly resulted this year in the fifth playoff appearance in the team’s 37-year history and the first since 1999. Meanwhile, Geren guided the A’s into the toilet earlier this season than he did last, so the only excitement about the A’s was whether or not they could find a way to move out of the McAfee Mausoleum — oops, I mean Coliseum, a once-nice baseball field that is now a butt-ugly football venue with basepaths.

It’s hilarious to me that there is serious talk of making “Moneyball” into a movie — Brad Pitt as Beane? Gimme a fraking breek! The first plan for a cinematic version reportedly fell through; I presume the reason is that most movies like to have a HAPPY ending, not one where the best-laid plans turn to (ahem) spit.

The good news for SABRmet-heads is that the movie might get made after all, and that a screenplay is being prepared by Aaron Sorkin (“A Few Good Men,” “The West Wing,” etc.) .

Such a shame. I thought he had kicked drugs.

It seems clear to me that Nate Silver has been
taking lessons from James Hansen over at NASA.

If the data fails to give the desired results CHANGE THE DATA.

PC is Thought Control
LEE

On the first sets of numbers (comparing the last digit distributions):

You’ve conveniently dropped the fact that he’s comparing two sources of polling data and noting the differences, not simply comparing one data source against an assumed baseline. The methodology used to actually choose the numbers to compare is insignificant as long as two conditions hold:

1) The two data sets are of the same nature
2) The same methodology is used on both

In particular, note the comparison with Quinnipiac, which he chose because of the highly similar nature of the data being compared (and he explains his methodology here). There is no question that the two data sources are of a very different nature, despite the fact that they’re measuring the same thing, so visibly so that the need for a statistical test like chi^2 is unnecessary (it would merely confirm the obvious, although for reference chi^2 for these two gives confidence <0.0001 that they’re the same). Crying foul play because the obvious isn’t beaten like a dead horse seems like something of a stretch on your part.

On Benford’s law:

It’s well established that Benford’s law can be extended to later digits (http://en.wikipedia.org/wiki/Benford’s_law#Generalization_to_digits_beyond_the_first). The application to polling data may be a stretch, but note how he uses it: “This would be consistent with a distribution that at least partially observes Benford’s Law, in which smaller digits are more likely to occur.” He does not state that it *does* observe Benson’s law, only that if it did these results are consistent.

On the Oklahoma student poll:

I appreciate that this received only a one line comment, in a seemingly obvious attempt to gloss over the fact a full fledged argument would hold no water. Comparing to artificially simulated data is a completely valid thing to do when you’re attempting to demonstrate that the data you’re analyzing appears to have been artificially generated. Noting that the maximum difference between an artificially generated CDF and the actual CDF is only ~0.025 and then considering the incredibly simple model being compared against has to at least raise some questions (FYI, with my sample size of 1000 artificial students this gave a confidence of 93.5%. that the two distributions are the same, using the Kolmogorov-Smirnov test). As a final sniff test, and answer this honestly (if only to yourself), do you really, truly believe that of 1000 high school students, none could get more than 8 correct? Take the quiz yourself and see how you do and think about whether that is even remotely plausible.

And I’ve also noticed that you’ve still not responded to any of my points. I can probably even guess why:

1) It doesn’t matter what I say here, because it’s your blog and most readers will side with you regardless of what happens.
2) You don’t think it’s worth the effort, since I’ll probably still disagree with you.
3) It’s more fun to taunt dissenters than to address them.

It’s too bad there isn’t more of a commitment to open discussion and respect for those who disagree with you.

Now that Strategic Vision has stopped polling, and their survey of Oklahoma students can now be regarded as a complete fake, are you still interested in defending them?

Cheers.