Spatial Multivariate Design in the Plane

• Activity Number: 183
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Jie Li*+ and Dale Zimmerman
• Companies: Eli Lilly and Company and The University of Iowa
• Keywords: spatial ; optimal design ; multivariate ; collocated ; design criteria

Abstract

In environmental studies, the results of spatial data analyses can be substantially affected by the spatial configuration of the sites where measurements on multiple variables are taken. Hence, it is useful to study optimal designs which result in data guaranteeing efficient statistical inferences. In this talk I will discuss optimal design in the plane, where Euclidean distance is used. Three different design criteria will be discussed. Optimal designs for a small example and a relatively large example will be discussed. The impact of asymmetry in the cross covariance function on the spatial multivariate design and the relationship between multivariate optimal design and univariate optimal design if the multivariate design is restricted to be completely collocated will be discussed.