03-07-2015 05:26 PM
I asked this question on the SAS statistical procedures community and was advised that I should also ask it on the Mathematical Optimization and Operations Research community.
I have data with daily prices for different companies, and for each company I have 2 conditions which are the same for the entire year.
These two conditions are proportions and each ranges from 0 to 1, and the sum of the two conditions for each company is = 1.
What I want to do is to find if there are optimal portfolios based on these conditions, as measured by the % change in price from the start period to the end period.
Initially I wanted to construct 10 portfolios: (0=< cond1 <0.1) -------- (0.9=<cond1=<1) and to see which of these portfolios gives the greatest price increase, but I am not sure if this is the correct method from a statistical point of view.