Science, Statistics, Politics, Current Events, Photos and Life.

Wednesday, May 21, 2008

Helping Retire Clinton Campaign Debt

The Clinton campaign is now $20 million in debt according to the LA Times.
There has been continued speculation in the news about how Obama might help her retire her campaign debt. Obama could donate the maximum $2300 to her campaign.

Then release the information as a whisper campaign.

Might help to bring her supporters over to his campaign as well.

Saturday, May 17, 2008

Obama's wealth rises rapidly

LA Times has a story today on Obama's wealth rising rapidly.
Barack Obama's wealth has more than doubled during his presidential campaign -- and has shot up tenfold since he entered the U.S. Senate three years ago, his financial disclosure filed Friday shows.
The easiest way for your wealth to shoot up tenfold or to double in a year, is to start with next to nothing. If you have a dollar today, and next year you have a hundred, your wealth just shot up 100 fold. But don't go congratulating yourself yet.

Addendum May 18, 2008:

The correct statistical interpretation of the quote data unquote presented in this article is that Obama was far and away the poorest of the 3 (and then there were 2) presidential candidates 3 years ago, and 1 year ago. The implications of the article are that he is on the fastest upward track, hence he is the elitist with the most-est...

Tuesday, May 13, 2008

Insurance pricing and genetic information

Kevin Drum has a comment on insurance companies not allowed to use genetic information in setting their pricing. He doesn't understand why it shouldn't be allowed.

In setting prices, a company isn't required to use all available information in setting the price. Reasons can be many, from it being too hard, to making the product difficult to understand for consumers, to being bad customer relations.

Airlines have tried for years to segment their market and charge different individuals different amounts for the same exact flight. And where has that gotten them? Airlines rank up there with used car salespeople, spammers, music companies and telemarketers for popularity. Airlines that charge closer to a single price are much more popular, consider SouthWest, although even they have multiple price levels for the same plane.

If we disallow insurance companies from charging more for people with genetic errors, then insurance companies will find themselves in the situation they find themselves in right now, where virtually no one has genetic information. Thus, it isn't that strange that we might require them to stay with current pricing schemes.

Suppose that insurance companies knew exactly how much each individual in the world will cost in terms of health care, over their lifetime. Essentially, if companies charge more to more costly people, and less to cheaper/healthier individuals, then insurance is no longer an insurance product. Everyone pays their own exact cost(s), properly amortized over the years. Insurance becomes a charge-added (as opposed to value-added) product. The insurance companies take some money for their own trouble, and charge you what you should pay anyway. No value to you, except for the amortization service.

By requiring insurance be the same price to all people, the insurance company must charge the average person the average cost + fees for the insurance service. Everyone pays the same amount. Those who are healthier subsidize those who are less healthier, true. But everyone can potentially get insurance, as long as some one picks up the cost.

Wednesday, May 7, 2008

I Got That Wrong

Indiana barely goes for Clinton.

North Carolina is a strong result for Obama.

I didn't predict that very well at all. Zogby actually did quite well with their late polling estimates.

Why? My guess: the biggest issue on the table, gas tax holiday pushed late deciders to Obama.

In contrast, at the last few primary rounds, the big issue on the table, Rev Wright, bittergate, pushed late deciders to Clinton.

Monday, May 5, 2008

Indiana Primary

Maybe Obama will do better than my prediction? From, the last 6 polls are, through yesterday:
Polling organization, dates, sample size and LV=likely voters, Clinton%, Obama% and the undecided%.

InsiderAdvantage 5/4/08 502 LV 48 44 8
Zogby 5/3-4/08 636 LV 42 44 8
Suffolk 5/3-4/08 600 LV 49 43 6
PPP (D) 5/3-4/08 851 LV 51 46 3
ARG 5/2-4/08 600 LV 53 45 2
SurveyUSA 5/2-4/08 675 LV 54 42 1

The average of these gives a 5.5% difference, with 4.7% undecided. Allocating those as if they will split like everyone else gives 5.8%. If they all go for Clinton, then we get to a 10% difference.

One of several interesting things about this is that while the standard deviation of the Obama percentages is 1.4, the standard deviation of the Clinton percentages is 4.3. The standard deviation of the undecided percentages is 3.1. Basically, all those undecideds go over to Clinton or not, depending on specific details of the question phrasing, and how the organization balances their sample to the statewide demographics.

I'll drop my prediction from Clinton by 14% in the previous post to Clinton by 10%. Same standard deviation as before, 4%.

The Day Before the Polls Close: Indiana and North Carolina

Zogby has run a poll that says that Obama is ahead in Indiana. No other polling organization sees that however, so I'm inclined to disbelieve it. Further, polling is hinting that late deciders are going for Clinton, which I find believable. When you're not sure, the devil you know is the one you tend to go with. Clinton has been around for a long time, Obama is the fresh face on the block.

I'm guessing double digit win in Indiana for Clinton, maybe 14 points.

North Carolina is a tougher call. A virtual tie wouldn't surprise me. I'll bet on Obama by 3 percent.

Errors: If I'm wrong in Indiana, give it a standard deviation of prediction of 4 on the prediction. If I'm wrong in North Carolina, also a standard deviation of prediction of 4.