Skip to content

Principal Component Analysis – There is an Interesting Pattern in My Stock Portfolio

June 22, 2012

Principal component analysis is a technique used to form new variables that are linear combinations of some original variables (see Sharma 1996).

I have used seven financial ratios as input variables: return on equity, RE; return on assets, RA; operating margin, OM; solidity, S; quick ratio (liquidity indicator), QR; asset turnover, AT; and sales per employee, SPE. These ratios have been calculated for the stocks in my portfolio (based on annual reports for 2011).

SAS 9.2 is applied to perform the analysis.

It can be seen that the first three principal components — that is the number of new variables — collectively account for 84 % of the variation in data.


The two most prominent ratios for each component are marked bold. Prin1 mostly dependent on profitability, Prin2 depend on the corporations’ ability to pay its debt in the short- and long run, and Prin3 depend on efficiency.

The following graph shows components scores for the stocks. I have only included the first two components (they account for 65% of the variation) to make interpretation straightforward. Stocks which have outperformed the OMXSPI (Stockholm) index, since the beginning of this year, have been given a green colour (otherwise red).


A pattern appears. Stocks with positive values on the first- and especielly second principal component (corporations with good returns ehich are capable of repaying their debts) have overall been a good investment for me 2012. Buying these kinds of stocks seems like a sound strategy as well…

It would be interesting to extend the analysis to a general population and compare outcomes during different parts of the business cycle. Perhaps this will be done in a later post.


From → Finance

Leave a Comment

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: