[R-SIG-Finance] Is there R code for measuring information coefficient?

Brian G. Peterson brian at braverock.com
Wed Mar 14 03:13:19 CET 2012

On Tue, 2012-03-13 at 20:54 -0500, Michael wrote:
> Thanks Brian.
> I have read for example the following documents:
> http://cran.r-project.org/web/packages/PerformanceAnalytics/vignettes/PerformanceAnalyticsPresentation-UseR-2007.pdf
> However, I am looking for the "information coefficient" not
> "information ratio/sharpe ratio", etc. 

If you read carefully, as you clearly did not, Information Coefficient
(IC) is a function of the Information Ratio(IR).  So, you cannot be
looking for one without the other.

In my copy of Grinold and Kahn (second edition), Chapter 5 is about the
'Information Ratio' as implemented in PortfolioAnalytics.
Breadth is so trivial that I'm not even going to discuss it, as should
be obvious if you understand what you are reading.

The formula for Information Criteria[1] is

IR = IC + sqrt(BR)

I suspect that (even) you can figure out the algebraic substitution to
put IC on its own on one side of the equation with Information Ratio on
the other.

Grinold and Kahn, Active Portfolio Management. Second Edition. p. 148

Brian G. Peterson
Ph: 773-459-4973
IM: bgpbraverock

More information about the R-SIG-Finance mailing list