The document discusses robust regression methods for dealing with outliers in data, including M estimation, S estimation, and MM estimation. M estimation extends maximum likelihood estimation and uses an iterative reweighted least squares procedure. S estimation is based on M estimation residuals but uses the residual standard deviation. MM estimation first applies S estimation to obtain scale estimates, then performs M estimation. Algorithms for each method are presented. The methods are applied to maize production data to determine the best regression model.