Re: Minimum value of objective function..

From: Scott VanWart <scott.vanwart@cognigencorp.com> Subject: Re: Minimum value of objective function.. Date: Fri, 05 Oct 2001 10:03:50 -0400 Dear Beautyemy, The minimum value of the objective function can be thought of as the overall error in the prediction of drug concentrations based upon observed data. It is therefore logical that the more data you have, the more likely it is that the objective function value will be larger. Comparing the objective function value usually comes into play when when you are trying to evaluate hierarchal models to see which model produced the smallest sum of weighted squared residuals. However, you should pay more attention to other criteria which would let you know how representative your model is to the system you are trying to characterize. Some possible suggestions would be to look at the following goodness of fit criteria: 1. Diagnostic plots - predicted vs. Observed Cp will give you an overall sense of how well the model is doing. Weighted residuals vs. predicted Cp, residuals vs. time, and weighted residuals vs. time will also help diagnose potential errors related to the model selected and the variance structure. 2. Check the values estimated for your parameters as well as their precision (standard errors). Do the results agree with historical data? If precisions are bad, your model may be overparameterized. 3. Check the correlation matrix to make sure parameters are not highly correlated, which would result in some identifiability issues with your model. Hope this helps! Scott Van Wart ------------------------------- Scott Van Wart Population PK/PD Scientist Cognigen Corporation 395 Youngs Road Williamsville, NY 14221 Tel. (716) 633-3463 Ext 241 Fax. (716) 633-7404 email: scott.vanwart@cognigencorp.com Web: www.cognigencorp.com