0
$\begingroup$

I have some panel data for various products (UPCs) below purchased at various price points across various stores across time (the data is by shopper-date-store-product).

I'm trying to sort out the best way to do price elasticity/optimzation modeling with this data and was leaning towards either MNL or just regular log-log regressions. The problem with MNL is that I don't always have the alternative prices for each store-date combination to use. Looking for any suggestions on a good way to model elasticity here.

enter image description here

Improve this question
$\endgroup$
3
  • $\begingroup$ Lee Cooper's 1988 Market Share Analysis book is probably the single best introduction to panel data price elasticity models in marketing science. Forget that it's about 'market share' since few modelers use that DV these days and substitute unit sales in the text instead. He structures price elasticity data matrices sensibly using SAS but, so what? Any software can be plugged in its place. Despite all the substitutions, it remains a kind of bible. Obviously, there are more recent and sophisticated texts wrt panel data models but they aren't as specific to your query as Cooper's book. $\endgroup$ Commented Mar 30 at 15:00
  • $\begingroup$ Here's a link to an online copy of Cooper's book. anderson.ucla.edu/faculty/lee.cooper/MCI_Book/BOOKI2010.pdf $\endgroup$ Commented Mar 30 at 15:06
  • $\begingroup$ Awesome, I was looking for some good books on the topic but there wasn't much. Will give this a full read. $\endgroup$ Commented Mar 30 at 15:39

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.