blocksdesign (2.9)

Nested and Crossed Block Designs for Factorial, Fractional Factorial and Unstructured Treatment Sets.

http://cran.r-project.org/web/packages/blocksdesign

Constructs D-optimal or near D-optimal nested and crossed block designs for unstructured or general factorial treatment designs. Where a structured treatment design is required, a D-optimal or near D-optimal treatment design is found based on a suitable model matrix design formula. The required block design is then found for the required treatment design based on a defined set of block factors. The block factors are added in sequence and each added block factor is optimized conditional on all previously added block factors. The block design can have repeated nesting down to any required depth of nesting with either a simple set of nested blocks or a crossed blocks design at each level of nesting. If a crossed blocks design has more than a single plot in each crossed blocks intersection, the determinant of a weighted combination of the information matrix for additive crossed blocks effects and the information matrix for multiplicative crossed blocks effects is used as the design criterion. Outputs include a table showing the allocation of treatments to blocks and tables showing the achieved D-efficiency factors for each block and treatment design.

Maintainer: Rodney Edmondson
Author(s): R. N. Edmondson.

License: GPL (>= 2)

Uses: crossdes, lme4, knitr, rmarkdown

Released over 1 year ago.