The summary function is a generic function used to produce summary statistics. In this case, it computes and returns a list of the summary statistics of the fitted linear model. Here, it will output information such as residuals, coefficient standard error R-squared, f-statistic, and a degree of freedom. In the Call section, the function called to generate the fitted model is displayed. In the Residuals section, it provides a quick summary (min, 1Q, median, 3Q, max) of the distribution.

In the Coefficients section, each coefficient is a Gaussian random variable. Within this section, Estimate represents the mean distribution of the variable; Std.Error displays the standard error of the variable; the t value is Estimate divided by Std.Error and the p-value indicates the probability of getting a value larger than the t value.

Residual standard error outputs the standard deviation of residuals, while the degree of freedom indicates the differences between the observation in training samples and the number used in the model. Multiple R-squared is obtained by dividing the sum of squares. One can use R-squared to measure how close the data is to fit into the regression line. Mostly, the higher the R-squared, the better the model fits your data. However, it does not necessarily indicate whether the regression model is adequate. This means you might get a good model with a low R-squared or you can have a bad model with a high R-squared. Since multiple R-squared ignores a degree of freedom, the calculated score is biased. To make the calculation fair, an adjusted R-squared (0.6327) uses an unbiased estimate, and will be slightly less than multiple R-squared (0.64).