SELECTION OF COVARIATES IN A LOGISTIC REGRESSION MODEL FOR THE PREDICTION OF RESISTANCE TO RICE BLAST

Main Article Content

Momate Emate OSSIFO
http://orcid.org/0000-0002-5425-4087
Marciel Lelis Duarte
http://orcid.org/0000-0002-3896-5428
Antônio Policarpo Souza CARNEIRO
http://orcid.org/0000-0002-9043-3242
Vinicios Silva dos Santos
http://orcid.org/0000-0002-8387-2917
Sebastião Martins Filho
http://orcid.org/0000-0002-8317-4318

Abstract

Rice (Oryza sativa L.) has been one of the most consumed foods on the planet, with economic and social importance. Diseases, mainly blast, caused by the fungus Pyricularia oryzae, are limiting factors for the production of rice. The present work aimed to select covariables that can influence resistance to rice blast, using the selection strategy proposed by Collett. Logistic regression models were adjusted to predict disease resistance, using the ROC curve to assess the predictive capacity. The data used were obtained from a population of 413 plants, with phenotypic information collected in 82 countries and classified into five subpopulations. The research found that, out of over fifteen variables embedded to assess the disease, only three revealed to be relevant for the final adjusted model, namely: width of flag leaf (V4), the mean number of primary panicle branches (V8) and the amount of amylose from ground grains (V15). The variable V4 presented the most significant influence on disease resistance. Additionally, for each unit increase in V4, V8 and V15, it is expected to obtain 279.3, 31.9 and 9.4% increases, respectively, in the probability of resistance to rice blast.

Article Details

How to Cite
OSSIFO, M. E., Lelis Duarte, M., CARNEIRO, A. P. S., Santos, V. S. dos, & Martins Filho, S. (2022). SELECTION OF COVARIATES IN A LOGISTIC REGRESSION MODEL FOR THE PREDICTION OF RESISTANCE TO RICE BLAST. Brazilian Journal of Biometrics, 40(2). https://doi.org/10.28951/bjb.v40i2.559
Section
Articles