The model summary table shows several statistics that can help you evaluate how well the final model fits the data.

·    S is measured in the units of the response variable and represents the standard distance that data values fall from the regression line. For a given study,  the better the equation predicts the response, the lower S is.

·    R (R-Sq) describes the amount of variation in the observed response values that is explained by the terms in the final model. R always increases with additional predictors.

·    Adjusted R (R-sq(adj)) is a modified R that is adjusted for the number of terms in the model. Unlike R, adjusted R may be smaller when the model contains more terms. Use adjusted R to compare models that have different numbers of predictors.

·    Predicted R (R-sq(pred)) is a measure of how well the model predicts the response for new observations. This statistic is more useful than adjusted R for comparing models because it is calculated with observations that are not included in the model calculation. Larger values of predicted R suggest models of greater predictive ability.

For the pill data, both R (92.39%) and adjusted R (90.10%) are close to 100%, which indicates that the model fits the data well. The predicted R (85.22%) is also reasonably high, which indicates that the model is useful for predicting new observations.