Shalom.
I have some problems in the BsProb procedure.
I construct a full orthogonal factorial experimental design of 26 when the
response is from random sampling from normal distribution with expectancy
that depends on factor A (equal 2 when A=-1 and equal 0.5 when A=1).
On primary analysis using GLM I accept (as expected) factor A with big
influence.
When Running the BsProb procedure I get posteriors probabilities that equal
0, on factor A and on all factors.
I was trying to run it over a difference size of sample without any change
on the result.
What can be the problem?
What can I do to solve it?
Thank you,
Respectfully,
I attach the results of the primary analysis and the R output and program:
lastsave7.txt - R output and program
Sas output.html � the GLM procedure for y depend on effect A, you can see
on the ANOVA analysis the large influence of this effect on y.
[[alternative HTML version deleted]]
______________________________________________
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
