Optimality of circular neighbor-balanced designs for total effects with autoregressive correlated observations

This paper studies the optimality of circular neighbor-balanced designs (CNBDs) for total effects when the one-sided or two-sided neighbor effects are present in the model and the observation errors are correlated according to a first-order circular autoregressive (AR(1, C )) process. Some optimalit...

Full description

Saved in:
Bibliographic Details
Published in:Journal of statistical planning and inference 2009-07, Vol.139 (7), p.2293-2304
Main Authors: Ai, Mingyao, Yu, Yunlong, He, Shuyuan
Format: Article
Language:English
Subjects:
Autoregressive process
Block design
Combinatorics
Combinatorics. Ordered structures
Correlated errors
Designs and configurations
Exact sciences and technology
Experimental design
General topics
Mathematics
Probability and statistics
Sciences and techniques of general use
Statistics
Universal optimality
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper studies the optimality of circular neighbor-balanced designs (CNBDs) for total effects when the one-sided or two-sided neighbor effects are present in the model and the observation errors are correlated according to a first-order circular autoregressive (AR(1, C )) process. Some optimality results under some specified conditions are provided and the efficiency of a CNBD relative to the optimal block design is investigated. In order to discuss the efficiency of a CNBD among all possible block designs with the same size, the optimal equivalence classes of sequences under the one-sided neighbor effects model are characterized and the efficiencies of CNBDs with blocks of small size are illustrated.
ISSN:0378-3758
1873-1171
DOI:10.1016/j.jspi.2008.10.025