I'm looking to build a fixed effects or random effects model. The aim is to find the impact of non-performing loan ratio (NPLR) and capital adequacy ratio (CAR) on return on equity (ROE) for banks. But I want to add a bank specific time-invariant variable into the model. Are there any suggestions?

  • 2
    $\begingroup$ If you use a fixed-effects model, then there's no need to explicitly specify a bank-specific time-invariant variable, nor can you even do so, since the effect of any such variable cannot be identified separately from the panel (bank-) specific intercept, and it will be dropped in the estimation. $\endgroup$ – The Laconic Feb 25 '17 at 3:23

Your Answer

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

Browse other questions tagged or ask your own question.