Dear All,
I am currently writing a thesis on IPO valuation of U.S. unicorns. My sample comprises around 55-60 companies for which I collected information on around 8 independent variables.
My idea was to study the effect of the predictors on two dependent variables:
1- EV/sales, which is a ratio used for valuation
2- Percentage change in stock price after 1 day
I was thinking of using multivariate regression, in particular I read that Partial Least Square may be suitable, but I am not sure whether the sample is too small for this kind of analysis. Do you have opinions on the matter or suggestions regarding alternative models to use.
Regarding the model test I found out that AICc, among others, is a good test for the model when the sample size is small.
Thank you for the help.