Sunday, August 30, 2009

When Are We Ever Gonna Have To Use This?

I'll be listening to this soon:

Oxford mathematician Peter Donnelly reveals the common mistakes humans make in interpreting statistics -- and the devastating impact these errors can have on the outcome of criminal trials.


I'm still considering a master's degree in stats.

4 comments:

rightwingprof said...

Good video. I'm having my students watch it.

gbradley said...

I had a professors whose favorite Cliche was:
"There are Lies, Big Lies, and Statistics."

neko said...

Here's one major mistake some people made when interpreting statistics: winning 52% of the country is not a landslide!! ^_^

Steve USMA '85 said...

I had a stats professor at UofMD who was regularly called on to be an expert witness. She would tell us of some of the things 'experts' would try to pull. Her best story was that of the opposing expert who got on the stand and unequivocally stated that the odds that a certain thing happening was 50% and that it was statistically significant. Essentially he said the jury should hang the guy because of a 50% likelihood.

While she almost couldn't stop laughing at the idiocy of that, when it was her time in the stand, she realized that the jury bought it. It took her and the defense lawyer a long time and step-by-step explanations to get the jury to realize that a 50% chance basically meant totally random. Flip of the coin.