« Tech Tech Symposium on Criminal Law & the First Amendment | Main | Google Takes One on the Chin »

Thursday, March 24, 2011

Type I and Type II errors

Inspired a few years ago from a piece I read of Christine Hurt's, I began using the Type I and Type II error jargon a lot, not only in my writing on punitive damages or punishment theory generally, but also in my teaching, particularly in the realm of criminal procedure rules related to adjudication (the bail to jail class). Since the last time I could be even plausibly described as competent with numbers and stats was about 11th grade, I was not surprised that many of my students and some colleagues exhibited some trouble keeping track which error was which. So, I'm grateful to Michael Heise, who pointed out this recent blog post from Ethan Fosse with mnemonics for keeping Type I errors differentiated from Type II errors:

first, a Type I error can be viewed as a "false alarm" while a Type II error as a "missed detection"; second, note that the phrase "false alarm" has fewer letters than "missed detection," and analogously the numeral 1 (for Type I error) is smaller than 2 (for Type I error)

 

 

Posted by Administrators on March 24, 2011 at 02:08 PM in Blogging | Permalink

TrackBack

TrackBack URL for this entry:
https://www.typepad.com/services/trackback/6a00d8341c6a7953ef014e86f0945c970d

Listed below are links to weblogs that reference Type I and Type II errors:

Comments

Not sure about Scott's mnemonic: "false positives" sometimes refer to something "good" and sometimes to something "bad", and if I had to block out the subject matter every time I think of these terms, I would have been hopelessly confused.

Posted by: amused | Mar 26, 2011 1:41:56 AM

I always call them "false positive" and "false negative". Why use the terminology that confuses everyone, including the speaker? It's only words. Switch to "false positive", and everyone's lives will improve.

Posted by: amused | Mar 26, 2011 1:37:48 AM

And what type of error is the reference to "Type I error" in the final parenthetical of the post?

Posted by: Michael Herz | Mar 25, 2011 7:30:16 PM

And it's Scott for the win - his I'll remember. (I hope.)

Posted by: Mark D. White | Mar 25, 2011 5:36:35 AM

To follow up on Matt with a mnemonic, it's very "positive" to be No. 1, and (for some) pretty negative to come in "2nd."

Posted by: Scott Dodson | Mar 24, 2011 5:34:12 PM

I have to admit that I've never understood why "type I" and "type II" was used rather than "false positive" and "false negative". False positive/negative seem highly intuitive to me, while of course type I/type II is jargon (not necessarily of the bad kind, but jargon nonetheless, and needlessly baffling to anyone who doesn't know it.)

Posted by: Matt Lister | Mar 24, 2011 3:38:53 PM

The comments to this entry are closed.