Your pizza taste test seems simple enough to me, but I may be missing something. The binomial has four assumptions: 1. N trials of an experiment. 2. Two possible outcomes. 3. Probability of success is the same for each trial. 4. Trials are independent. 1 and 2 are trivial. Using subjects only once and running each subject at a different time would satisfy 4. 3 is true under the null hypothesis. Remember that your null hypothesis is that students cannot determine pizza brands at a rate better than random guessing. The distribution under the alternative might be a bit trickier. For example, some students may be better at distinguishing pizza brands than others. It is my understanding though, that unless there are large variations in the probability of success from trial to trial, the binomial probability formulas are pretty robust to this violation of assumptions. To really make the experiment fun, use beer consumption during the taste test as a second factor or as a covariate. Steve Simon, [EMAIL PROTECTED], Standard Disclaimer. STATS: STeve's Attempt to Teach Statistics. http://www.cmh.edu/stats ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================
