I am just beginning to learn econometrics, and am a little confused by my lecture notes.

They say that the conditional mean function has a known functional form, and is linear in parameter, e.g.,:

$$m(x_1,x_2) = \beta_0 + \beta_1 x_1 + \beta_2 x_2 + \beta_3 x_1^2 $$.

Okay - so looking above, whilst we have some non-linear regressors, the $\beta$'s are all linear, so this is what it means "linear in parameter"?

I think I understand so far.

Next, the notes say:

"There are cases in which linearity is not a binding constraint. This is sometimes referred to as a satiated model. For example, let $x_1$ and $x_2$ be binary variables, both taking values 0 and 1." In this case:

$$m(x_1,x_2) = m(0,0) + m(1,0)x_1(1-x_2)+m(0,1)(1-x_1)x_2 + m(1,1)x_1x_2 $$

I am really confused by what this sentence is trying to say or convey.

  • $\begingroup$ Saturated, not satiated? $\endgroup$
    – Russ Lenth
    Commented Mar 13, 2020 at 12:18
  • 2
    $\begingroup$ A satiated model has had all s/he desires. $\endgroup$
    – whuber
    Commented Mar 13, 2020 at 13:06

1 Answer 1


I believe this should be "saturated," rather than "satiated."

This just means you use regression to calculate four means for all the possible combinations of $x_1$ and $x_2$: $(0,0),(1,0),(0,1),(1,1)$

This is a kind of a non-parametric model, which is non-linear since it allows the means to be very flexible.

  • $\begingroup$ Thank you for your answer :) $\endgroup$ Commented Mar 14, 2020 at 5:53

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.