From the course: Introduction to Stata 15

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Diagnostics

Diagnostics - Stata Tutorial

From the course: Introduction to Stata 15

Start my 1-month free trial

Diagnostics

- [Narrator] All logit and probit models have access to a variety of postestimation commands including tests, predictions, and marginal analysis. In this session, we'll focus on diagnostic tests that tell us something about the goodness-of-fit of these models. The first thing to note is that there is no simple R squared equivalence for binary choice models. Various alternatives exist, but there is some debate in the literature which one is best. We'll explore some of these in this session, but first you should be clear what the terms sensitivity and specificity mean, as some of the diagnostic commands report on these measures. Sensitivity measures the proportion of actual positives, and specificity measures the proportion of actual negatives. The commands that we'll use are the previously used commands, predict and ttest. And the new commands of estat classification and fitstat. The last command is a user-written command and you'll first have to install it. Ensure that you obtain the…

Contents