Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Notice: We are no longer accepting new posts, but the forums will continue to be readable.

Topic: Level of Significance
Replies: 5   Last Post: Jan 6, 2000 6:28 AM

 Messages: [ Previous | Next ]
 Pat Ballew Posts: 356 Registered: 12/3/04
RE: Level of Significance
Posted: Jan 6, 2000 6:28 AM

I think the pyschology here is "no tails" rather than "5% probability" For
instance, I think the number of people who would doubt the run HHTHHHTHHH would
be much smaller. We are more prone to believe in total fraud (a two headed
coin) than in marginal fraud (a coin biased to 75% heads). Something about the
black/white nature of our judgement systems.

Pat Ballew,
Misawa, Jp

"Statistics means never having to say you're certain."

Math Words & Other Words
http://www.geocities.com/paris/rue/1861/etyindex.html

The Mathboy's page http://www.geocities.com/paris/rue/1861

-----Original Message-----
From: Chuck Tiberio <tiberio@tiac.net> at edu-internet
Sent: Wednesday, January 05, 2000 1:39 AM
To: apstat-l@etc.bc.ca at EDU-INTERNET
Subject: Level of Significance

story......
As I heard it, Fred Mosteller from Harvard used to bring a two headed
coin to his prob/stat class. He would take it out, flip it and record
the class would raise their hands to question the fairness of the
coin. After the fifth head in a row, the other half of the class
would join them. Pr(4 heads in a row given a fair coin) = .0625 and
Pr(5 heads in a row given a fair coin) = .03125. So apparently most
people start "feeling uncomfortable" somewhere between .0625 and
.03125. So .05 was chosen as a convenient compromise. I do, however,
totally agree with everything Chris said. Statistics means never
having to live or die by .05!

Chuck
=======================================================================
To UNSUBSCRIBE send a message to majordomo@etc.bc.ca containing:
unsubscribe apstat-l <email address used to subscribe>
Discussion archives are at
http://forum.swarthmore.edu/epigone/apstat-l
Problems with the list or your subscription? mailto://jswift@sd70.bc.ca
=======================================================================

=======================================================================
To UNSUBSCRIBE send a message to majordomo@etc.bc.ca containing:
unsubscribe apstat-l <email address used to subscribe>
Discussion archives are at
http://forum.swarthmore.edu/epigone/apstat-l
Problems with the list or your subscription? mailto://jswift@sd70.bc.ca
=======================================================================

Date Subject Author
1/3/00 Chuck Tiberio
1/5/00 Paul Velleman
1/5/00 S. Killingsworth
1/5/00 Michael Ernst
1/5/00 Lucinda Thomas
1/6/00 Pat Ballew