CycDesigN

CycDesigN is a computer package for the generation of optimal or near-optimal experimental designs. It provides the most comprehensive design generation package yet available for experimenters, particularly those involved in field, glasshouse and laboratory trials.

The designs include cyclic, alpha and factorial designs in blocks or in rows and columns, resolvable and non-resolvable designs, t-latinized and partially-latinized designs as well as spatial designs. The authors are leading researchers and, as a result, the algorithms incorporate the most recent developments in the construction of experimental designs.

There are two additional modules within the package:

CycXover – a sub-system that generates optimal or near-optimal experimental designs for use in crossover experiments. A crossover experiment involves the application of sequences of treatments to several subjects over a number of time periods.

The observations made on each subject at the end of a time period may depend on the direct effect of the treatment applied in the current period, and the carry-over effects of the treatments applied in one or more periods. Crossover designs are also known as change-over or carry-over designs.

CycAnalysis  allows you to tailor your output from a CycDesigN or CycXOver session in a form ready for analysis. It also gives you the option to generate either GenStat or SAS code for the analysis of the design you have chosen. CycDesigN’s focus is on the types of design that are needed when you have large numbers of treatments, as in variety trials.

In contrast, GenStat concentrates on the more traditional designs, such as randomized-complete blocks, split-plots and strip plots, criss-cross designs, Latin and Graeco squares, Lattices, confounded and partially-confounded block designs. CycDesigN is written in Visual C++ and runs under Windows 95, 98, NT, 2000, XP, Vista and Windows 7.

Current users can download it here.