2
$\begingroup$

Borusyak, 2021 has a sentence

First, we note that failing to rule out anticipation effects in “fully-dynamic” specifications (with all leads and lags of treatment included) leads to an underidentification problem, where the dynamic path of anticipation and treatment effects over time is not point-identified

I am wondering what do "underidentification" and "point-identified" mean in this case? I ask these words here because these words are not in the vocabulary (I checked with Cambridge dictionary) and I believe it belongs to econometrics words.

$\endgroup$
3
7
$\begingroup$

A parameter is "identified" if it can be known from an infinite amount of data. "Underidentified" thus means, "even if we had infinite data, we could never learn the true parameter".

"Point identified" contrasts with "set identified" with "point" meaning, "we know the exact value" and "set" meaning "we have a set and know the true value is in the set".

$\endgroup$
3
  • 1
    $\begingroup$ Thank @Michael, I am wondering if "Identified" also means if we have enough data, we will have the more precise result, or something similar to that? $\endgroup$
    – Louise
    Sep 15 at 22:37
  • 1
    $\begingroup$ And, a very clear and great answer, thank Micheal! $\endgroup$
    – Louise
    Sep 15 at 22:43
  • 1
    $\begingroup$ "Identified" makes no comment on the variance (precision) of an estimator. "Efficiency" or a presentation of the asymptotic distribution are the key things to look for regarding precision. $\endgroup$ Sep 16 at 7:36

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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