Steve, > All of my data sources are for medical data sets, so if someone could send > me a published example of a designed experiment in a non-medical area with > four or more equally spaced levels, please do so. Something in the physical > sciences area would be ideal. > > I'm also looking into Dr. Chambers' suggestion to take a subsample of the > data to enforce a uniform distribution on the cause and on the residual.
The use of roughly uniform factors is an attempt to obtain factorial designs. The most important thing is that we get combinations of the extremes of the orthogonal causal factors, so that we can contrast those conjoint causal events with the midrange conjunctions. Factorial designs are common in science. I am going to the internet to look for 2-way factorial anovas, without interactions. Interactions are what statisticians refer to as nonadditive factors. The base model for CR is y=x1+x2. This is an additive model in which there are no interactions. Therefore, 2-way factorial anovas with 4x4 or higher number of levels should provide good data. We need only make sure the data is real and not simulated. Best, Bill . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
