Deterministic Imputation in Multienvironment Trials. (20th October 2013)

• Record Type: Journal Article
• Authors: Arciniegas-Alarcón, Sergio; García-Peña, Marisol; Krzanowski, Wojtek Janusz; dos Santos Dias, Carlos Tadeu
• Other Names: Escobar-Gutierrez A. Academic Editor.; Williams W. P. Academic Editor.
• Is Part Of: ISRN agronomy. Volume 2013(2013)
• Publication Date: 2013-10-20
• Subjects: Agronomy -- Periodicals; Agronomy; Agricultural Technology; Periodicals; Electronic journals; 630
• DOI: 10.1155/2013/978780
• Languages: English
• ISSNs: 2090-7656

Abstract

Abstract : This paper proposes five new imputation methods for unbalanced experiments with genotype by-environment interaction (G × E ). The methods use cross-validation by eigenvector, based on an iterative scheme with the singular value decomposition (SVD) of a matrix. To test the methods, we performed a simulation study using three complete matrices of real data, obtained from G × E interaction trials of peas, cotton, and beans, and introducing lack of balance by randomly deleting in turn 10%, 20%, and 40% of the values in each matrix. The quality of the imputations was evaluated with the additive main effects and multiplicative interaction model (AMMI), using the root mean squared predictive difference (RMSPD) between the genotypes and environmental parameters of the original data set and the set completed by imputation. The proposed methodology does not make any distributional or structural assumptions and does not have any restrictions regarding the pattern or mechanism of missing values.