Yeah. And Napoleon's Invasion Of Russia Was Really A Success Too.

Let us re-visit a topic I brought up back in January of this year. You may remember that I took the company Risk Management Solutions to task:

Insurance companies are now using the threat of global warming to rip its customers off. Evidently a group called Risk Management Solutions (RMS) supplies the models insurance companies use to get an idea of what their risks and liabilities are in hurricane prone areas. Well, last spring threw out its old models based upon 100 years worth of empirical evidence in favor of a guess; a guess real life hurricane experts call "actually unscientific."

I then looked at the data and found:

The claim that "significantly higher hurricane activity that has persisted in 9 out of the last 12 years" is simply false. Since hurricanes can only hit in full integers (i.e. one at a time), it is dishonest to claim a year that has 2 hurricanes is an example of "higher activity" when the average is around 1.75. It would be much more honest to claim it is an example of bouncing around the mean.

I then worked on a more statistically sophisticated post (as sophisticated as I can get anyway) where I concluded:

According to my work the claim that the last 12 years of hurricane activity is significantly different from what came before is false. In fact I found that the activity fell within a standard deviation from the mean. I also ran the numbers using as a baseline the data from 1946-1993 and comparing the 1994-2005 years to that (i.e. a log10 mean of 0.9625, with a standard deviation of 0.1326 for the 1946-1993 data, vs. a log10 mean of 1.1354 for the 1994-2005 period.), and found the 12 year period was still only barely one standard deviation away from the older numbers.

It seems clear to me that the claims of the folks at RMS (" "Increases in hurricane frequency should be expected along the entire U.S. coast, but will be highest in the Gulf, Florida, and the Southeast, while lower in the Mid-Atlantic and the Northeast.") is in no way borne out by the data.

So, we now are two years into the "predictions" offered by RMS. Who is doing a better job, RMS or The Iconic Midwest? Thanks to Roger Pielke over at Prometheus you can be the judge:

In the spring of 2006, a company called Risk Management Solutions (RMS) issued a five year forecast of hurricane activity (for 2006-2010) predicting U.S. insured losses to be 40% higher than average. RMS is an important company because their loss models are used by insurance companies to set rates charged to homeowners, by reinsurance companies to set rates they charge to insurers, by ratings agencies for evaluating risks, and others.

We are now two years into the RMS forecast period and can thus say something preliminary about their forecast based on actual hurricane damage from 2006 and 2007, which was minimal. In short, the forecast doesn't look too good. For 2006 and 2007, the following figure shows average annual insured historical losses (for 2005 and earlier) in blue (based on Pielke et al. 2008, adjusted up by 4% from 2006 to 2007 to account for changing exposure), the RMS prediction of 40% more losses above the average in pink, and the actual losses in red.

So the RMS forecast has been spectacularly wrong to this point. They predicted close to $15 Billion in storm damages for 2006-7 and we have had under $1 billion. The historical average would predict $11 billion for the same time period, so yes we have been lucky during the last two years. But what seems more likely, that we are in a totally different situation where we can expect Katrina like events every few years, OR that we are bouncing around the historical mean for these events?

Well, if you are RMS you don't even admit your models have failed to this point.

From Prometheus:

So what has RMS done is the face of evidence that its first 5-year forecast was not so accurate? Well, they have declared success and issued another 5-year forecast of 40% higher losses for the period 2008-2012.

Risk Management Solutions (RMS) has confirmed its modeled hurricane activity rates for 2008 to 2012 following an elicitation with a group of the world's leading hurricane researchers. . . . The current activity rates lead to estimates of average annual insured losses that will be 40% higher than those predicted by the long-term mean of hurricane activity for the Gulf Coast, Florida, and the Southeast, and 25-30% higher for the Mid-Atlantic and Northeast coastal regions.

In gambling terms, RMS has effectively doubled down. Adding 40% increases to the remaining three years in their original 2006-2010 forecast means we will have to average $17.5 Billion in storm losses during the next three years.

Not only is RMS doubling down, they are doing so on the basis of cards showing a King and a Six against a house showing an Ace.

Good luck with that.

ADDED:

I'll point out RMS' strange way of attempting to "confirm" their models. They look not at what actually has happened during the period they were supposedly predicting, but instead talk "with a group of the world's leading hurricane researchers." Huh, and here I was thinking they should use empirical observations instead.

This new science amazes me....explain again how sheep's bladders can be used to prevent earthquakes.