hari_s_nath@YAHOO.COM wrote to me personally instead of to SAS-L: > Thanks for showing me a non-macro way of doing things and for your time. > > >[2] What are you trying to do here? It looks like you are trying to > >pick out the biggest differences against a concentration of 150. > >Let me tell you whatever i know about this. We have two different >treatments here, and our hypothesis is to see if there is a significant >difference in treatments and if so, how much. So, the signal to noise >ratio is taken as an end measure here(the one with the less noise). The >minimum differences between products - Is that meaningful, ie., then they >are checked back with digital images to see if they actually make sense. > > >If you are trying to do that, then you have made several serious > >methodological errors, and you should re-think your entire approach. > >If you have a 'control' that you're testing against, then you are using > >the wrong testing method. > >I dont see that as a control, but as far as the experiments are concerned, >they are analysed with the support of experienced statisticians. So, I >think it should be reliable. > > >So write back to SAS-L and explain what you are *really* trying to do. > >Why are you trying to generate all this stuff? What are you doing with > >it? Let us know, and someone here nad direct you toward a better > >answer. > >I may/ may not have given you the entire picture, but hope this tells >something.

Well, it is (of course) totally unfair of me to expect you to control the statistical design, or - in this case - to explain what the heck your bosses are doing.

But I think it is important to point these aspects out. Your bosses may not have given you enough direction here, and that's their fault. Go back and make sure they know what you are coding up, and why.

It may be that they'll have some helpful suggestions for you. Or it may be that we can work out a more effective approach to achieve your goals. I'm still not clear on why you have coded your project the way that you have.

And please write back to SAS-L, instead of to me personally. Thanks. David -- David L. Cassell mathematical statistician Design Pathways 3115 NW Norwood Pl. Corvallis OR 97330

_________________________________________________________________ Is your PC infected? Get a FREE online computer virus scan from McAfeeŽ Security. http://clinic.mcafee.com/clinic/ibuy/campaign.asp?cid=3963