Listy Biometryczne - Biometrical Letters Vol. 37(2000), No. 2, 107-116


Show full-size cover
BIVARIATE ADJUSTMENTS FOR INTERPLOT COMPETITION
IN VARIETY TRIALS

Olivier David1, Anita Dobek2, Romana Głowicka2

1Unité de Biometrie, Institut National de la Recherche Agronomique,
Jouy-en-Josas, France
2Department of Mathematical and Statistical Methods,
August Cieszkowski Agricultural University, Poznań, Poland


Bivariate models are proposed to adjust for interplot competition in crop variety trials. The models include competition effects related to the variables of the models and take account of the correlation between these variables. Parameters are estimated by maximum likelihood. The bivariate adjustments are tested using data for yield and plant height from an experiment aimed at studying competition in winter wheat variety trials. In this experiment, they reduced bias due to competition but were not more efficient than univariate height adjustments.


competition, interference, likelihood.