A friend of mine is estimating the following model, using ols:

$y=\alpha + \beta X + u$,

where $y$ and $X$ are continious variables, $\alpha$ and $\beta$ are parameters and $u$ is an error component. In a second step, he then splits the sample at the median of the residuals. He then estimates the following regression:

$y=\alpha + \beta X + \gamma Dummy(above\_Median=1) + \delta X \times Dummy(above\_Median=1)$ + v,

where $Dummy(.)$ is one if an observation is above the median and zero otherwise. My feeling is that this procedure is extremely strange and the estimates are probably biased. But I currently cannot depict/formalize the problem. What potential problems do you see? Can this be done? What do you think about this procedure?


1 Answer 1


This amounts to discretizing (specifically: dichotomizing) a continuous variable. Your friend fits a model that has a discrete jump as an observation moves from the "below median" to the "above median" group. This almost certainly doesn't make sense. Read more here: What is the benefit of breaking up a continuous predictor variable?

If there is remaining nonlinearity, which you could detect, e.g., in plotting residuals against actuals or against fitted values, then it's far better to refit a model with .

Friends don't let friends discretize continuous variables.

  • $\begingroup$ Thanks a lot. Just as a follow up. His problem is that residuals in his model have "a deeper interpretation" and he is interested in modelling heterogeneity in this componend (i.e. heterogeneity in $\beta$). I don't see how this can be done without using sort of a proxy for the residuals. $\endgroup$
    – bachelor
    Commented Nov 14, 2017 at 9:46
  • $\begingroup$ Hm. Is he looking for an interaction term? Or does he want to model heteroskedasticity? $\endgroup$ Commented Nov 14, 2017 at 10:04
  • $\begingroup$ He is rather interested in interaction terms. $\endgroup$
    – bachelor
    Commented Nov 14, 2017 at 10:15
  • $\begingroup$ Then I'd recommend that he explicitly models it as such. $\endgroup$ Commented Nov 14, 2017 at 10:16
  • 1
    $\begingroup$ Well, to me it does, too. An interaction with residuals sounds very much like conditional heteroskedasticity to me. If you have a statistician available, I'd recommend your friend buy him a cup of coffee and explain his setup to him. $\endgroup$ Commented Nov 14, 2017 at 11:06

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.