Bayesian ridge regression shows the best fit for SSR markers in Psidium guajava among Bayesian models

Abstract Markers are an important tool in plant breeding, which can improve conventional phenotypic generating more accurate information outcoming better decision making. This study aimed to apply and compare the fit of different Bayesian models BRR, BayesA, BayesB, BayesB (setting value from very low $$\pi$$ π = $${10}^{-5}$$ 10 - 5 ), BayesC Lasso (LASSO) for predictions genomic genetic values productivity quality traits a guava population. The were fitted fruit mass, pulp soluble solids content, number, production per prediction with SSR markers, obtained through CTAB extraction method 200 primers. ridge regression model showed best results all was chosen predict individual’s according cross-validation data. A good stabilization Markov Monte Carlo chains observed mean close means. Heritabilities predictive accuracy. strong correlations between some traits, allowing indirect selection.