ABSTRACT
The difference in slopes between the regression line with all the data and the regression line with the ith point missing will mostly be small, except for influential points. Lots of possibilities exist. These regressors may be separate variables, products of separate variables, powers of the same variable, or functions of the same variable. One goal when modeling is to “fit” the model by estimating the parameters based on the sample. For the regression model the method of least squares is used. In particular, the linear model should be appropriate for the mean value of the yi, and the error distribution should be normally distributed and independent. A scatterplot of the data with the regression line can show quickly whether the linear model seems appropriate for the data. If the general trend is not linear, either a transformation or a different model is called for.
