Regression analysis, as we know, is one of the most
important statistical techniques for model fitting. If a regression
model is appropriately selected, most observations should be
fairly close to the regression line or hyperplane. The
observations which are far away from the regression line or
hyperplane may not be “ideal” observations for the selected
model and could potentially be identified as the outliers for the
model. The least squares method is undoubtedly the most
popular parameter estimation technique