Statistical Analysis for Correlated Paired-plot Designs

Dilermando Perecin *

Departamento Ciências Exatas, FCAV, Universidade Estadual Paulista, UNESP, Via de Acesso Prof. Paulo Donato Castellane, s/n, CEP:14884-900, Jaboticabal-SP, Brasil

Guilherme Moraes Ferraudo

Monsanto do Brasil LTDA, Av. das Nações Unidas 12901, Torre Norte, Brooklin, CEP 04578-910, São Paulo SP, Brasil

Carlos Alberto Mathias Azania

Centro de Cana IAC, Rod. Prefeito Antonio Duarte Nogueira, km 321, CEP 14001-970, Ribeirão Preto SP, Brasil

Ana Regina Schiavetto

Centro de Cana IAC, Rod. Prefeito Antonio Duarte Nogueira, km 321, CEP 14001-970, Ribeirão Preto SP, Brasil

*Author to whom correspondence should be addressed.


Abstract

This work is aimed to evaluate different statistical analysis with a randomized complete block design for paired-plot studies of herbicide selectivity in sugarcane experiments. Two  procedures were considered: i) the construction of a t-test to assess the hypothesis of the paired-plot mean  difference to be zero in each treatment; or ii) the use  of an analysis of variance where the treated and paired  plots were considered in a split-plot model and the interaction is sliced  by treatment. By simulation with normal  bivariate  distributions, with  uniform (zero, 0.11, 0.33, 0.44, 0.67 or 0.89)  or heterogeneous correlations, the two procedures showed similar performance. The power of the tests increases as the correlation of paired-plot increases.

Keywords: Selectivity, herbicides, sugarcane, multiple comparisons, simulation


How to Cite

Perecin, Dilermando, Guilherme Moraes Ferraudo, Carlos Alberto Mathias Azania, and Ana Regina Schiavetto. 2015. “Statistical Analysis for Correlated Paired-Plot Designs”. Journal of Experimental Agriculture International 9 (6):1-7. https://doi.org/10.9734/AJEA/2015/20722.

Downloads

Download data is not yet available.