ISSN:
1439-0523
Source:
Blackwell Publishing Journal Backfiles 1879-2005
Topics:
Agriculture, Forestry, Horticulture, Fishery, Domestic Science, Nutrition
Notes:
Alpha-designs have become popular in cultivar trials. Analysis is based on a mixed model. As a result of imbalance, inference tests require approximate methods. This paper investigates the Type I error control of different Satterthwaite approximations for the denominator degrees of freedom of Wald-type F-tests and t-tests in a two-factorial alpha-design with cultivars as the subplot factor and management intensities (fertilization, plant protection) as the main plot factor. Simulation results demonstrate good error control for cultivar comparison at the same intensity, with the need for an approximation which diminishes as the number of cultivars increases. By contrast, a comparison of intensities entails a more substantial departure from the nominal significance level, and this is not entirely offset by any of the approximations. The methods are demonstrated using two real data sets.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1046/j.1439-0523.2003.00964.x
Permalink