{"title":"Sample size for canonical correlation analysis in corn","authors":"A. Cargnelutti Filho, M. Toebe","doi":"10.1590/1678-4499.20210335","DOIUrl":null,"url":null,"abstract":": The canonical correlation analysis has been successfully used in many areas aiming to extract important information from a pair of data sets. Thus, the objective of this work was to determine the sample size (number of plants) required to estimate the canonical correlations in corn characteristics. Six characteristics were measured in 361, 373, and 416 plants, respectively, of the single, three-way and double cross hybrids of the 2008/2009 crop year and in 1,777, 1,693, and 1,720 plants, respectively, of the single, three-way, and double cross hybrids (2009/2010 crop) (six cases). The canonical correlation analyses were carried out between characteristics group of the plant architecture (plant height at harvest and ear insertion height) versus grain production (hundred grains mass and grains mass per plant) (scenario 1), and dimensions of ear (ear length and ear diameter) versus grain production (hundred grains mass and grains mass per plant) (scenario 2). The sample size (number of plants) for the estimation of canonical correlations was determined by resampling with replacement and application of the model linear response with plateau. Measuring 270 plants is sufficient to estimate the canonical correlation between groups with two characteristics in each group for corn. This sample size can be used as reference for reliable canonical correlation analysis.","PeriodicalId":9260,"journal":{"name":"Bragantia","volume":null,"pages":null},"PeriodicalIF":1.2000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bragantia","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1590/1678-4499.20210335","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
: The canonical correlation analysis has been successfully used in many areas aiming to extract important information from a pair of data sets. Thus, the objective of this work was to determine the sample size (number of plants) required to estimate the canonical correlations in corn characteristics. Six characteristics were measured in 361, 373, and 416 plants, respectively, of the single, three-way and double cross hybrids of the 2008/2009 crop year and in 1,777, 1,693, and 1,720 plants, respectively, of the single, three-way, and double cross hybrids (2009/2010 crop) (six cases). The canonical correlation analyses were carried out between characteristics group of the plant architecture (plant height at harvest and ear insertion height) versus grain production (hundred grains mass and grains mass per plant) (scenario 1), and dimensions of ear (ear length and ear diameter) versus grain production (hundred grains mass and grains mass per plant) (scenario 2). The sample size (number of plants) for the estimation of canonical correlations was determined by resampling with replacement and application of the model linear response with plateau. Measuring 270 plants is sufficient to estimate the canonical correlation between groups with two characteristics in each group for corn. This sample size can be used as reference for reliable canonical correlation analysis.
期刊介绍:
Bragantia é uma revista de ciências agronômicas editada pelo Instituto Agronômico da Agência Paulista de Tecnologia dos Agronegócios, da Secretaria de Agricultura e Abastecimento do Estado de São Paulo, com o objetivo de publicar trabalhos científicos originais que contribuam para o desenvolvimento das ciências agronômicas.
A revista é publicada desde 1941, tornando-se semestral em 1984, quadrimestral em 2001 e trimestral em 2005.
É filiada à Associação Brasileira de Editores Científicos (ABEC).