Art Kendall <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>... > I don't think it stands for anything. I think it was just chosen to to > make a distinction from R factor analysis which was done on an R > (correlation) matrix. It was a very old method of cluster analysis, > first standardizing the variables then correlating cases. The factors > were interpreted as clusters of cases. > > That's my recollection as well - "R" factor analysis "clustered" variables, so the clustering on the case or person dimension was called "Q".
There might be a reference to this terminology in Stephenson (Stevenson?), "The Play Theory of Mass Communication", which is from the early 1960's or late 1950's. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
