Scott Sycamore wrote: For Gaussian distribution, can anyone point me to a reference that explains the relationship between the number of samples and the expected accuracy of their mean with that of the actual mean? If you have access to the STatistics Toolbox, you may want to look at the SAMPSIZEPWR function: help sampsizepwr SAMPSIZEPWR Sample size and power calculation for hypothesis

--- On Sat, 6/21/08, Ingrid K. Friberg <ikf@HOTMAIL.COM> wrote: From: Ingrid K. Friberg <ikf@HOTMAIL.COM> Subject: NLMIXED - Class variable - p-value To: SAS-L@LISTSERV.UGA.EDU Date: Saturday, June 21, 2008, 11:30 AM Hello, I am getting ready to do a survival analysis in NLMIXED and have worked with my statistician to figure out how to code it. Now I have a new, simple

"Ingrid K. Friberg" <ikf@HOTMAIL.COM> wrote Hello, I am getting ready to do a survival analysis in NLMIXED and have worked with my statistician to figure out how to code it. Now I have a new, simple problem and don't want to bother him. I know that NLMIXED cannot use variables with three levels in it. Therefore I have recoded this with 2 dummy variables. How do I calculate a p-value

I actually suspect that your "supremum" and "infimum" functions are the problem here -- they look like they might be accumulating thunks and blowing your stack. But beyond this, they're also o(n) for what could be effectively an o(log n) operation at the least, if you used ordered sets. I'd start improving performance here with some profiling, and then some strictness annotations, and then go

hi, all: i use linprog solving a linear problem. however, looking into the solution, it seems like the linprog algorithm ignored the equality constraints. a part code of the problem is as following: [p,N] = size(Y); ue = eye(p,p); A = kron(Y',ue); sigma = -ones(p*N,1); A = [A,sigma]; sigma1 = zeros(1,p*p); sigma1 = [sigma1,1]; A = -[A;sigma1]; b = zeros(p*N+1,1); u1 = ones(1