Truncated beta nonlinear regression models for soil-water characteristic curves estimation.

摘要

We propose an alternative approach for estimating soil-water characteristic curves based on truncated beta nonlinear regression models. Thus, assuming that the response variable follows a truncated beta distribution. Maximum likelihood estimator of the curve parameters are obtained by direct maximization of the likelihood function and diagnostic analysis tools are considered to check for model adequacy under the two considered models. A soil prole from the Buriti Vermelho River Basin database is analyzed using the proposed methodology.