Hi - I am working with Panel data comprising 820 companies across 19 years. My data includes financial parameters such as revenue, leverage, Return on Sales etc. Iw ill be running panel data fe regression. I wanted to know whether I should normalise all my variables before running the xtreg?

Even before waiting for a response on this forum, I actually tried normalising the Revenue variable through a log transformation. Rather strangely, before and after the transformation, the Pr(skewness) and Pr (Kurtosis) remained 0 (zero.) Please refer to results pasted below. I would imagine that LnRev should show the normal transformation results.

.. sktest Revenue

Skewness and kurtosis tests for normality
----- Joint test -----
Variable | Obs Pr(skewness) Pr(kurtosis) Adj chi2(2) Prob>chi2
-------------+-----------------------------------------------------------------
Revenue | 10,904 0.0000 0.0000 . .

. sktest LnRev

Skewness and kurtosis tests for normality
----- Joint test -----
Variable | Obs Pr(skewness) Pr(kurtosis) Adj chi2(2) Prob>chi2
-------------+-----------------------------------------------------------------
LnRev | 10,722 0.0000 0.0000 565.59 0.0000


.