DS AdvancedLesson 20Free preview

DS Regression Table

This lesson is part of Data Science · All levels

Summary

The regression results table (e.g. OLS output from statsmodels) summarizes all the important information about the model: R-squared, coefficients of each predictor, standard error, t-value, and p-value. The coef column reads the magnitude of the variable influence, whereas the std err indicates how accurate the estimate is. The interpretation of the model should consider these columns simultaneously.

Key points

The regression table contains R-squared, coefficients, std err, t-value, p-value.
Coef = the weight of each predictor in the regression equation.
Std err = uncertainty of the estimate of the coefficient; the smaller the more accurate.
Const (intercept) = prediction of the target when all predictors are zero.
Get a summary through model.summary() on statsmodels.

Full lesson

Code examples and quizzes

Full lessons, code examples, and quizzes are available to subscribers. 5 questions.