Use of Simultaneous Autoregressive Models in Balanced Incomplete Block and Lattice Square Designs.
Technical summary rept.,
WISCONSIN UNIV-MADISON MATHEMATICS RESEARCH CENTER
Pagination or Media Count:
Simultaneous autoregressive models are applied to balance incomplete block and lattice square designs. Relationships between the resulting maximum likelihood estimators and standard analyses are explored and clarified. Also, it is shown that the Papadakis estimator, as applied to these designs, has the characteristics of the standard analyses, but simply involves fewer plots in the adjustment procedure for treatment averages. A worked example illustrates the differences in treatment estimates in a lattice square design, for standard inter-block analysis and for simultaneous autoregressive assumptions. Author
- Statistics and Probability