0
$\begingroup$

When I did my research with DiD, I saw that when I split the sample to subsample, while the coefficient in the whole sample is significant but this is no longer in the subsample. Can I ask what is the reason behind then?

$\endgroup$
2
$\begingroup$

There can be several reasons.

  1. In case the subsamples are not random, the variable may be significant on a subsample and not on another. This would be a case of omitted variables.

  2. The larger a sample, the stronger the statistical strength of the estimate, because the standard error of the estimator goes down with sample size. So it is quite possible that a non-zero coefficient is statistically significant if the sample is large, but the same coefficient is not statistically significant if the sample size is small.

$\endgroup$

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.