JSM 2004 - Toronto

Abstract #300935

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 432
Type: Contributed
Date/Time: Thursday, August 12, 2004 : 10:30 AM to 12:20 PM
Sponsor: Section on Physical and Engineering Sciences
Abstract - #300935
Title: An Empirical Comparison of Several Popular Designs for Computer Experiments
Author(s): Ofelia Marin*+ and William Notz and Thomas J. Santner
Companies: Ohio State University and Ohio State University and Ohio State University
Address: Dept.t of Statistics, Columbus, OH, 43210,
Keywords: EBLUP ; MSPE ; ML ; REML ; prediction accuracy ; computer experiments
Abstract:

We perform an empirical comparison of several popular designs for computer experiments. The comparisons are in terms of the prediction accuracy of a cubic model fit using least squares and four Empirical Best Linear Unbiased Predictors (EBLUPs) obtained by using either the Matern or Power Exponential correlation function with correlation parameters estimated by maximum likelihood (ML) or restricted maximum likelihood (REML). The prediction accuracy was determined by computing the mean squared prediction error (MSPE) over sets of 50 random surfaces obtained as slightly contaminated cubic functions, using the Hartman 6 family of test functions and as EBLUP-type interpolators generated using the krigifier of Trosset (1999) and Trosset and Padula (2000). Among the designs studied are Latin hypercube designs, uniform designs, Sobol and Niederreiter sequences, D-optimal designs, good lattice points and scrambled nets.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004