DS AdvancedLesson 19Free preview
DS Linear Regression
This lesson is part of Data Science · All levels
Summary
Linear regression models the relationship between independent variables (predictors) and dependent variables (targets) to predict numerical values, e.g. house prices based on land area. The simple model is y = mx + c, and its quality is assessed from the difference between real values and predictions called residuals. The main assumption is that the relationship is linear.
Key points
- The target (dependent) is predicted from the predictor (independent).
- The simple model: y is equal to mx + c with one predictor.
- Residual = real value - predictive value.
- Assumption: linear relationships and residuals are homoscedastic.
- Suitable for predicting and interpreting the influence of variables.
Full lesson
Code examples and quizzes
Full lessons, code examples, and quizzes are available to subscribers. 5 questions.