On 23 Feb 2001, dennis roberts wrote:
> is this situation of n=10 ... really a true binomial case where p for
> success is 1/3 under the assumption that simple guessing were the way in
> which tasters made their decisions?
[ also snipped the followup posting hypothesizing that strategic guessing
could influence the supposed 1/3 prob. of random success ]
Why not do a trial experiment where you in fact have one type of pizza?
Order all the same pizzas, and then split them into two (identical)
groups. Perform the experiment by randomly picking from the two groups
(as before) and feed the students three pieces as initially described,
make them choose the "different" one, and measure the "success" rate. Use
this as your binomial 'p'.
In this trial experiment you will be directly assessing how students guess
when they cannot truly tell the difference because there is none (and have
taken the visual element out, since they all come from the same place).
Empirical frequentism is my middle name.
-Aaron
--
o ~ ~ ~ ~ ~ ~ o
/ Aaron J Mackey \
\ Dr. Pearson Laboratory /
\ University of Virginia \
/ (804) 924-2821 \
\ [EMAIL PROTECTED] /
o ~ ~ ~ ~ ~ ~ o
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
