0

It is known that many sectors/industries within the stock market are correlated with each other. For example, using VIF as a measure of correlation, I have the following result:

Sector  ENERGY   CONSUMER STAPLES   CONSUMER DISCR   MATERIALS   INFORMATION TECH   INDUSTIRALS   HEALTH CARE   FINANCIALS   UTILITIES   TELECOM SVC
 VIF    2.937214     4.268179      10.755497        6.150606     5.023864           14.064349       2.795279      6.054236     2.985639     3.360512

As you can see, VIF for most industries are greater than 5. I was just wondering if

1) there exists data for the uncorrelated sectors or

2) there eixsts a way to extract the "pure" part of a given return stream which is uncorrelated with other parts. I am not even sure if it's possible.

Jun Jang
  • 453
  • 2
  • 13
  • You can try multifactor model for the stock returns with the industry indicators as factors – Aksakal Aug 06 '18 at 14:16
  • The problem of a multifactor model is that of multi-collinearity. I am trying to remove the correlated portion of return stream and get the pure, uncorrelated portion. – Jun Jang Aug 06 '18 at 14:18
  • What do you mean by "pure portion"? – Aksakal Aug 06 '18 at 14:22
  • @Aksakal By pure portion, I mean a portion of the sector that is truly related to the variable and uncorrelated with other variables. The portion that truly and purely explains that variable – Jun Jang Aug 06 '18 at 14:27
  • Your definition is too vague, and probably meaningless. Imagine that you take a full PCA of your variables. You get the new set of variables which are uncorrelated. If you regress on these new variables, you get the same result, but now all correlations are "pure"? – Aksakal Aug 06 '18 at 14:30
  • @Aksakal never mind man – Jun Jang Aug 06 '18 at 14:31

0 Answers0