Full text in pdf format

 

Effects of errors of variables on the stability analysis of a group of maize experiments*

 

 

Lindolfo StorckI; Roland VencovskyII

IDepartamento de Fitotecnia, Universidade Federal de Santa Maria, 97119-900 Santa Maria, RS, Brasil. Send correspondence to L.S.
IIDepartamento de Genética, ESALQ-USP, 13418-260 Piracicaba, SP, Brasil

 

 

ABSTRACT

A group of 42 maize cultivars was evaluated ill 16 localities of the State of Rio Grande do Sul. Yield data were submitted to a joint analysis of variance and to a stability analysis based on a discontinuous bi-segmented regression model with and without corrections to compensate for measurement errors of the independent variable and for the covariance between the errors of the dependent and independent variables. Results indicated that the effect of corrections on estimates of angular and discontinuity parameters was neglegible. Ignoring corrections, however, resulted in a downwards bias (average of 14%) of the variance due to deviations from the model. The importance of the corrected analytical procedure increased as the number of treatments and or replications was reduced.

Keywords: Errors of variables; Stability analysis; Maize.

 

 

REFERENCES

Cruz, C.D., Torres, R.A.A. and Vencovsky, R. (1989). An alternative approach lo the stability analysis proposed by Silva and Barreto. Rev. Bras. Genét. 12: 567-580.

Eberhart, S.A. and Russell, W.A. (1966). Stability parameters for comparing varieties. Crop Science 6: 36-40.

Finlay, K.W. and Wilkinson, G.N. (1963). The analysis of adaptation in a plant-breeding programme. Aust. J. Agricult. Res. 14: 742-754.

Silva, J.G.C. and Barreto, J.N. (1985). Aplicação da regressão linear segmentada em estudos da interação genótipo x ambiente. In: Proceedings of Simpósio de Experimentação Agrícola, 1, Piracicaba, 1985. Campinas, Fundação Cargill, pp. 49-50.

Storck, L. (1989). Modelo de regressão bi-segmentado descontinuo com erros de medida aplicado na análise de estabilidade de cultivares. Doctoral Thesis. ESALQ-USP, Piracicaba.

Verma, M.M., Chahal, G.S. and Murty, B.R. (1978). Limitations of conventional regression analysis, a proposed modification. Theor. Appl. Genet. 53: 89-91.

 

 

* Work developed at the Departamento de Matemática e Estatística of ESALQ/USP, as a part of the Doctoral Thesis of the first author.