Help: Non-positive semi-definite message

From: stuart@c255.ucsf.edu Date: Wed, 15 Aug 2001 11:55:53 -0700 (PDT) This is in reply to the following question from Alan Xiao. >Can any one systematically address the possible causes of and >possible solutions to the message of "Nonpositive semidefinite >but nonsingular" ? I will not endeavor to systematically address the possible causes for and solutions to the message. These can be many, and they are very specific to the user's problem. We can make this one general remark regarding the message: Your point estimate is neither a local nor a global mimimum. It is a saddle point, and therefore, it may not be a suitable point estimate. You say you have tried different initial estimates and other perturbations of your model and still, the message arises. This makes me think that there is something fundamentally wrong with your setup. But it is not easy, and it may be impossible, to diagnose this by means of interaction over the NONMEM Users Network. Stuart Beal