It's not that I'm offended by any criticism of Democrats, but I know that Biden is smart, he has experience, and he knows what he's talking about. To me, his mistakes about Roosevelt appearing on television are just minor mistakes. He wasn't trying to show off knowledge he doesn't have (like Palin). He just made some silly mistakes.

It felt like Stewart was really trying to grab at anything he could to put Biden in the spotlight, and it just didn't work.

I can't think of any other reason why he would put this woman so close to becoming the next President.

those no-so-rare cases of people reading books while driving. Granted, it's low-tech, but you'd be surprised how often people do it.

Dear Lord, Ms. Countess has obviously never been in a relationship with an Asian woman. I don't know where that stereotype came from but Wow, Asian women are not submissive.

Granted you need an internet connection and the ability to burn DVDs (which everyone has), but you just download the cracked game, burn it to disc, and play it on your PS or Xbox. So there a few extra steps. Big deal.

There have been a couple times when Palin almost started chittering as if a big spring were going to pop out of her head like a broken cartoon clock. You can tell she is concentrating on an almost superhuman level and she's barely getting by.

When you start believing your own propaganda, you're screwed. You can't just watch the cheerleaders -- you have to watch the game.

Ninety-four feels wrong. Most viewers are going to feel it's an exaggeration, even if it were true. McCain should've just said "Obama voted for raising taxes a hundred bazillion times".

Counting down to election day, Sarah Palin gives us a little gift every day...

Hi. Statistician here. There's really nothing wrong with using an 80% confidence interval. You aren't required to use 95% or greater for a confidence interval. Keep in mind that the only reason alpha levels of 0.1, 0.05, and 0.01 (giving CI's of 90%, 95%, and 99%) became the "standard" is because for decades one had to refer to tables in textbooks to compute these things, and the authors didn't have the space to include tables for each and every percentage value. So they chose the most intuitive to include in their books. It can be argued that if they had the computing power a century ago that we have now, we would be doing confidence intervals a lot differently today.

There are lots of different kinds of analysis where not only is 80% confidence accepted, but it is necessary to use a value that low. It all comes down to the acceptable Type I error, or how frequently you will conclude that something interesting is going on when it isn't. If it's okay to be wrong 20% of the time, then an 80% CI is perfectly fine.

Frankly there's no problem in using a 70% CI, 50% CI (I've seen 'em), or a 63.286529% confidence interval. The vitally important thing is that you choose it BEFORE YOU RUN THE STATS. Actually you should choose it before you start collecting data, and in most cases you go with the standard for your academic subject. So here's the real criticism of this study: they should have used the polling standard of 95%. I haven't read the actual study, but they should have phrased their conclusion, "Although the result are no significant at the 95% level, it is significant at the 80% level." If they only reported the 80% CI, then they are weaseling things a bit by implicitly stating that 80% is good enough.

But does an 80% confidence interval give us good information? Damn right it does!! Anyone automatically dismissing these results because it isn't at 95% doesn't know what they're talking about. An 80% CI says it's more likely than not (or roughly a 4 in 5 chance) that there's something really happening here. There is important imformation here.

Another point: What's much more important than confidence level and even the size of the sample is the quality of the sample. The confidence level and sample size are really easy for the layman to latch on to because they are always reported (or should be), and the sampling method details are not. But if it's a nonrepresentative sample, you could poll a million people and use 99.9999% confidence and it's still bullshit. The conclusions are worthless, and in comparison a small sample with 80% confidence is infinitely better.

Quick description of data mining: If you lay on your back and stare at the clouds long enough, you'll see a cloud that looks like an elephant. That doesn't mean you're looking at a real goddam elephant.

I did some computations a few years back regarding the CAPPS II thing which I believe was rejected eventually. Using conservative estimates (conservative in a scientific sense, not politically) and Bayes theorem, I computed that using such a system, the probability that a person identified as a terrorist ACTUALLY IS a terrorist is about 1 in 50,000. Imagine being a poor airport security officer, knowing that each time a red flag comes up there is practically no chance that the suspected flyer is a terrorist. Utterly demoralizing, and it would completely defeat the intentions of the system.

It's really weird that it takes the concentrated effort of a team of experts to convince the government of something which is just common sense to the average person.

But somebody that smart should be able to find a good paying job somewhere.