Speaker：Prof. Timothy E. O’Brien

                        Loyola University Chicago

Title:     Curvature, Robustness Optimal Design in Applied Generalized Nonlinear Regression Modelling

       Time：23 Dec 2019, 16:00

Location：实验楼105

Abstract:    Researchers often find that nonlinear regression models are more applicable for modelling various biological, physical chemical processes than are linear ones since they tend to fit the data well since these models (model parameters) are more scientifically meaningful.  These researchers are thus often in a position of requiring optimal or near-optimal designs for a given nonlinear model.  A common shortcoming of most optimal designs for nonlinear models used in practical settings, however, is that these designs typically focus only on (first-order) parameter variance or predicted variance, thus ignore the inherent nonlinear of the assumed model function.  Another shortcoming of optimal designs is that they often have only p support points, where p is the number of model parameters.

Measures of marginal curvature, first introduced in Clarke (1987) further developed in Haines et al (2004), provide a useful means of assessing this nonlinearity.  Other relevant developments are the second-order volume design criterion introduced in Hamilton Watts (1985) extended in O’Brien (2010), the second-order MSE criterion developed illustrated in Clarke Haines (1995).

This talk examines various robust design criteria those based on second-order (curvature) considerations.  These techniques, coded in the GAUSS SAS/IML software packages, are illustrated with several examples including one from a preclinical dose-response setting encountered in a recent consulting session.

        Speaker  Introduction：

·Professor of Applied Environmental Statistics; Graduate Program Director (Statistics), Loyola University Chicago, since 2010. (Asst. Professor: 1998 – 2004; Assoc. Professor: 2004 – 2010)

· Post-Doctoral Fellow, Universität Augsburg, 1995.

· Post-Doctoral Fellow, Institut Nationale de la Recherche Agronomique, Laboratoire de Biometrie, 1994.  

· Ph.D., Statistics, North Carolina State University, June, 1993.

联系人：周达副教授