From the course: Advanced and Specialized Statistics with Stata

Unlock the full course today

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

Continuous by continuous interactions

Continuous by continuous interactions - Stata Tutorial

From the course: Advanced and Specialized Statistics with Stata

Start my 1-month free trial

Continuous by continuous interactions

“

- [Instructor] Not all interactions need to be with the same variables. For example, we'd might want to include an interaction effect between two continuous variables such as age and education. Such a specification would allow the effect of education on a dependent variable Y to vary by age. A problem with such interactions is they can be hard to understand and to visualize, as they result in complicated multi-dimensional relationships. Here's an example of what I mean. Imagine that we want to estimate the following relationship where we regress grade experience and union membership on hourly wages. In this particular setup, grade and experience are continuously measured variables, and they are fully interacted with each other. This produces three coefficients that are linked. Ignoring significance for a moment, there is a positive relationship between education grade and wages. There is a negative…

Contents