The genus Stylosanthes includes diverse species adapted to low-fertility soils and resistant to adverse conditions, with potential for use in animal feeding. This study aims to determine the repeatability and determination coefficients and to establish the minimum number of measurements needed to predict the real value for each morphological trait evaluated in ten Stylosanthes spp. genotypes from different locations in the tropical semiarid region. The repeatability (r) and determination (R-2) coefficients were estimated using two models of analysis of variance (ANOVA 1 and 2); principal components based on the covariance (PCACOV) or correlation (PCACOR) matrixes; and structural analysis based on the correlation matrix (SACOR). All the morphological traits presented high values for r and R-2 (r >= 0.62 and R-2 >= 92%). Higher r and R-2 values were observed for PCACOV and PCACOR methods and lower for ANOVA 1 and 2. Regardless of the method and R-2 considered, the minimum number of measurements to predict the real value of the characteristics was higher for petiole length, central and lateral leaflet width, and lower for height and stem diameter. The different methods predict between one and six measurements needed to predict the real value for each trait, at R-2 = 90%. The use of principal component analysis provides greater accuracy in the estimation of r and R-2 for morphological traits in Stylosanthes spp. genotypes from the semiarid region.