|
|
|
|
Fall 2007
| |
Max Morris
Department of Statistics
Iowa State University
"Composite Response Surface Designs for Factors with Jointly Symmetric Effects"
3:00 Refreshments in 241 Schaeffer Hall
3:30 Talk in 140 Schaeffer Hall
In applications of response surface analysis based on polynomial regression, complete first- or
second-order linear models are often used to represent the functional relationships between independent
variables and the expected responses. However, there are situations in which knowledge of
the physical system under study suggests modifications in the model form. One such situation is in
"mixture problems" (e.g. Cornell, 1990) where constraints on the independent proportions imply
a reduction in the number of model terms for polynomials of any order. Model reduction is also
appropriate when a subset of the experimental factors is known to have a kind of jointly symmetric
effect on the responses of interest. We describe an experiment of this type, part of a research
program focused on the design of a control system for an agricultural combine, and consider how
the model can be simplified in this context and how standard second-order composite designs can
be modified to take advantage of this structure.
|
|
|
All talks are free and open to the public.
To receive colloquium reminders via email, please send a request to statistics@uiowa.edu.
The 37th Annual Craig Lectures will be on October 11 and 12. Our speaker this year is Nancy Reid from the University of Toronto.
Past colloquia:
Spring 2007 |
Fall 2006 | Spring 2006 |
Fall 2005 |
Spring 2005 | Fall 2004 | Spring 2004 | Fall 2003 | Spring 2003 | Fall 2002 | Spring 2002 | Fall 2001 | Spring 2001 | Fall 2000 | Spring 2000 | Fall 1999 | Spring 1999 | Fall 1998 | Spring 1998
|
