Dear all,

I've got a question regarding the cross-sectional t-test when determining the significance of CAAR in an event study (market model) with a sample of 538 transactions. When calculating the standard deviation of CAAR with the following formula, I am not sure about the degree of freedoms:

How would the first part of this equation look like: 1) =sqrt(1/(538(538(538-536))*sum...), or 2) =sqrt(1/(538(538(538-2))*sum...), or even different?
I know that this might be a stupid question but I am kind of stuck atm and need to clarify this issue first before being able to continue with the rest of the analysis.

Thank you very much in advance!