3 ways to interpret regression estimates

3 Ways to Interpret Regression Estimates

Suppose we got the data on exercise habits measured in minutes, and age at death measured in years. In this Learn through Econometrics Model, you ran the regression of death at age on exercise and got the result: 

age at death = 60 + 0.1 exercise

Let’s have a look at how we can interpret and report this result.

Descriptive Interpretation

This is based on Conditional Expectation. Given the value of Exercise, you interpret the age at death. Suppose, I grab two people and find that one exercises one minute more than the other, according to our equation, this person will live one-tenth of a year longer than the other person.

Causal Interpretation

Here, we show the cause-effect relationship between the independent and dependent variable estimates. According to this, if I exercise one minute more, my life expectancy will rise by one tenth of a year

Forecasting Interpretation

Here, we take some value of the explanatory variable and predict the outcome based on the result. For example, if my friend is exercising daily for 30 minutes, then we can predict he can live up to 63 years.