I am conducting Fixed Effects Regression Analyses (Panel Regression) to analyze characteristics of firm-disclosures. My dependent variable is a disclosure characteristic (e.g. length, sentiment, ..). Obviously, I have one observation for each firm-year (firm-level). However, my independent variables also include manager data (e.g. age). I have data for multiple managers for each firm-year (manager-level), which I all want to include.

Simplified Data:

enter image description here

As priorly described, the green dependent variable (Length) is repeated for the manager-level perspective. However, manager-level data vary within firm-years. Fixed Effects are included for years and firms.

From a statistical perspective - can I run such regression analyses? If not, what is a proper procedure?

  • 1
    $\begingroup$ One approach would be to bring the manager data to the same level as the firm data, e.g., by taking averages of the managers' age per firm-year. However, your inference would then be on this aggregated level of age. $\endgroup$ – Helix123 Nov 23 at 16:40
  • $\begingroup$ Thanks for your response - I decided to focus on the CEO and drop other manager data! Best, M. $\endgroup$ – Michael Mü Nov 23 at 21:41

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.