Simpson's paradox

Courtesy AustinContrarian  Mon, 03/09/2009 - 6:54pm

Counterintuitive fact o' the day (and one I'm a little embarrassed I just learned).

Let's say you run an experiment on a sample population.

 You do this by dividing the population into two subgroups and running the experiment on each separately.  The experiment succeeds for each subgroup.

If the experiment succeeded for each sub-sample, then it necessarily succeeded for the combined sample, right?

Nope.  Sometimes an experiment's apparent success on two samples disappears  when the samples are...



 

More related items

SXSW Film Preview: Beauty Is Embarrassing
Beauty Is Embarrassing, appearing in the SXSW 2012 Documentary Spotlight category, follows the trajectory of cartoon artist Wayne White, one of the creators of the Pee Wee's Playhouse...

APD Wants More Electronic Eyes On Criminals
Police are hoping to launch a new program to catch criminals, but they need help from local Austin businesses.The Austin Police Department is looking for businesses to give them access to...

Will The Wet Winter Weather Continue through Spring?
We’re currently under the influence of a La Nina Weather pattern, which 75 percent of the time means warmer than normal temperatures and drier than normal precipitation. However, this...

New Release Alert: The Daily Brothers - The Dream Is Dead
Who: Austin’s own version of the Kinks, right down to the familial connections. The Daily Brothers feature bros Chris and Jeff, who write, record, and produce their own music from the...

President Obama Sends FY2013 Budget Proposals To Congress
President Barack Obama unveiled a $3.8 trillion spending plan on Monday for 2013 that seeks to achieve $4 trillion in deficit reduction over the next decade but does little to restrain growth...


 

Post new comment

The content of this field is kept private and will not be shown publicly.