Articles
CANONICAL DISCRIMINANT ANALYSIS IN KIWIFRUIT ROOTSTOCK RESEARCH
Article number
313_16
Pages
143 – 148
Language
Abstract
Canonical discriminant analysis (CDA) is a multivariate statistical technique that maximises the correlation between two sets of variables, generating linear combinations that can discriminate between groups of individuals.
CDA has not been used extensively in horticultural research.
It has applications when is desirable to find differences between groups of individuals or treatments, for example cultivars (Yourstone and Wallace, 1990) growth regulators, levels of irrigation, tree training systems, and where it is desired to understand the relationship between the several variables measured on those groups.
In a kiwifruit rootstock trial, CDA was used to separate vines on nine different rootstocks on the basis of yield, fruit size, number of fruits removed by thinning, percentage of flowers in a compound dichasium (‘triples’), and number of flowers per shoot.
Plants on two rootstocks achieved a higher field performance than vines on the remaining rootstocks, an effect which was associated with a heavy yield of large sized fruit.
CDA has not been used extensively in horticultural research.
It has applications when is desirable to find differences between groups of individuals or treatments, for example cultivars (Yourstone and Wallace, 1990) growth regulators, levels of irrigation, tree training systems, and where it is desired to understand the relationship between the several variables measured on those groups.
In a kiwifruit rootstock trial, CDA was used to separate vines on nine different rootstocks on the basis of yield, fruit size, number of fruits removed by thinning, percentage of flowers in a compound dichasium (‘triples’), and number of flowers per shoot.
Plants on two rootstocks achieved a higher field performance than vines on the remaining rootstocks, an effect which was associated with a heavy yield of large sized fruit.
Publication
Authors
J.G. Cruz-Castillo, B.R. MacKay, G.S. Lawes, D.J. Woolley
Keywords
Online Articles (40)