In article <[EMAIL PROTECTED]>, Tommer Wizansky <[EMAIL PROTECTED]> wrote: >I'm looking for a rigorous answer as to why the weight matrix is the >inverse of the covariance matrix, when creating a linear fit for a set >of data points with different errors. can anyone help?
Do the mathematics; it is easy enough if you "speak matrix". For an intuitive idea, the mean of a sample of size k has the same variance as the original variance divided by k, and has weight k. So the weight is like the reciprocal of the variance. The question asked is the multivariate version of this. -- This address is for information only. I do not claim that these views are those of the Statistics Department or of Purdue University. Herman Rubin, Deptartment of Statistics, Purdue University [EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
