I am doing analysis on sales person behavior. I am measuring what effect certain sales behaviors have on revenue. An example of measured behaviours might be: number of phone dials, time on the phone, and time demoing products.

At first I am doing this as a pooled regression with all sales people. But I was curious about trying to control for the individual sales person. The thought would be to isolate what effect the behaviours have on revenue and exclude the 'ability' of the individiual. Would a fixed effect panel regression acomplish this goal?

Are there any pitfalls to watch out for? Alternate suggesions?

This dataset has about 100 sales people at any given time with varying lengths of stay.

  • $\begingroup$ In general, yes. But also look at the random effects model. You might also want to control for the time period as well, especially if you have sub-year periods in your sales data (or test if that control seems necessary). $\endgroup$ – Helix123 Jun 23 '16 at 8:24

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.