In the `CART_Dummy`

dataset, the output is a categorical variable, and we built a classification tree for it. In Chapter 6, *Linear Regression Analysis*, the linear regression models were built for a continuous random variable, while in Chapter 7, *The Logistic Regression Model*, we built a logistic regression model for a binary random variable. The same distinction is required in CART, and we thus build classification trees for binary random variables, where regression trees are for continuous random variables. Recall the rationale behind the estimation of regression coefficients for the linear regression model. The main goal was to find the estimates of the regression coefficients, which minimize the error sum ...

Start Free Trial

No credit card required