Compute HHI Index for panel data

[Viktor Christian]

Hi all,

I am writing my masters thesis on the effect of market competition on risk-taking behavior of banks. My main explanatory variable will be a measure of market concentration (HHI index or entropy).

I am working with the Call Report data for US banks which is a panel data set that has all the banks in the US per year (2000 - 2020) and I would like to generate the HHI index per company per the respective year however I think my approach is wrong. I attempted to use the following code:

entropyetc Assets, by(cert)

"Assets" being all the assets under management and "Cert" representing the unique ID of each bank.

When I run the code however the output says "nothing to do"

I would appreciate any input on this!

Viktor

[Nick Cox]

The help for entropyetc (from SSC) says

Optionally, results may be listed. Optionally, new variables may be generated containing results. Hence the syntax supports those who want a listing, but not new variables, and conversely.

However, if you don't specify either possibility, then you've given the command nothing to do.

There are some more fundamental misunderstandings that are a little harder to diagnose. The help also says

entropyetc treats varname, which may be numeric or string, as a categorical variable, so that distinct values define distinct categories

Assets doesn't sound to me like a categorical variable. Also, there is nothing in your command that will ensure results separately by year.

I am guessing that you need something more like

entropyetc cert [w=Assets], by(year) gen(4=HHI)

[Viktor Christian]

Thank you Nick for the quick help and explanation, the new code indeed yields what I was looking for.