Statistics experts reject global cooling claims

[mugacoffee]

http://customwire.ap.org/dynamic/fronts/HOME?SITE=VANOV&SECTION=HOME

WASHINGTON (AP) -- An analysis of global temperatures by independent statisticians shows the Earth is still warming and not cooling as some global warming skeptics are claiming.

The analysis was conducted at the request of The Associated Press. Talk of a cooling trend has been spreading on the Internet, fueled by some news reports, a new book, and temperatures that have been cooler in a few recent years.

The statisticians, reviewing two sets of temperature data, found no trend of falling temperatures over time.

U.S. government data show that the decade that ends in December will be the warmest in 130 years of record-keeping and 2005 was the hottest year recorded.

© 2009 The Associated Press. All rights reserved. This material may not be published, broadcast, rewritten or redistributed. Learn more about our Privacy Policy.

PS is it ok for me to paste that text here? Hope its ok. Sorry if not

 

[RyanX]

The analysis was conducted at the request of The Associated Press. Talk of a cooling trend has been spreading on the Internet, fueled by some news reports, a new book, and temperatures that have been cooler in a few recent years.

... falling surface sea temperatures, falling air temp readings, fewer sunspots, the list goes on...

The statisticians, reviewing two sets of temperature data, found no trend of falling temperatures over time.

U.S. government data show that the decade that ends in December will be the warmest in 130 years of record-keeping and 2005 was the hottest year recorded.

Obviously, one should turn to a statistician when in need of some weather or climate prediction.

Let's not forget ice cores go back many thousands of years showing wide swings of warming and cooling on the planet. This is just another cycle.

 

[Third_Density_Resident]

Obviously, one should turn to a statistician when in need of some weather or climate prediction.

With all due respect, it is absolutely vital to have a thorough understanding of statistics in order to understand climate and climate science. In many ways, climate science and statistics go hand-in-hand. I've studied both of these disciplines and can tell you this from experience. Many times a climate scientist won't have the expertise necessary to analyse data, so they use a statistician to do it instead.

Of course none of what I have said above has any bearing whatsoever on the conclusion that was reported by the Associated Press. I would be very interested to see the actual data that was used, and how it was analysed. I seriously question the outcome of the analysis.

 

[Laura]

Of course none of what I have said above has any bearing whatsoever on the conclusion that was reported by the Associated Press. I would be very interested to see the actual data that was used, and how it was analysed. I seriously question the outcome of the analysis.

Me too. Obviously, these guys are never let out of their laboratory or they would see/feel the evidence outside...

 

[ark]

From Joe Best, "Damned Lies and Statistics":

"This is a book about bad statistics, where they come from, and why they won't go away. Some statistics are born bad—they aren't much good from the start, because they are based on noth­ing more than guesses or dubious data. Other statistics mutate; they become bad after being mangled (as in the case of the Author's creative rewording). Either way, bad statistics are poten­tially important: they can be used to stir up public outrage or fear; they can distort our understanding of our world; and they can lead us to make poor policy choices.
The notion that we need to watch out for bad statistics isn't new. We've all heard people say, "You can prove anything with statistics."~ My title, Damned Lies and Statistics, comes from a famous aphorism (usually attributed to Mark Twain or BenjaminDisraeli): "There are lies, damned lies, and statistics." ~ There is even a useful little book, still in print after more than forty years, called "How to Lie with Statistics."'

In other words: with statistics one can prove almost anything - just select your data and make some assumptions about them. Data, the raw data, are more important than statistics. Because someone may be able to see in these data patterns that the statistician may not be prepared or willing to see.

 

[RyanX]

With all due respect, it is absolutely vital to have a thorough understanding of statistics in order to understand climate and climate science. In many ways, climate science and statistics go hand-in-hand. I've studied both of these disciplines and can tell you this from experience. Many times a climate scientist won't have the expertise necessary to analyse data, so they use a statistician to do it instead.

Of course none of what I have said above has any bearing whatsoever on the conclusion that was reported by the Associated Press. I would be very interested to see the actual data that was used, and how it was analysed. I seriously question the outcome of the analysis.

I agree that statistics plays a role in climate science and other sciences, no doubt about that. I shouldn't have been so sarcastic in my post, I apologize. I have nothing against the use of statistics in science. However, I believe it takes more than just statistics to understand the limitations of the data set and to interpret the statistical model too. We don't see the data sets in this instance, but my guess is that they would be limited and selective.

Like you said, the outcome of this analysis is questionable. I agree with that wholeheartedly!