sric {SharpeR} | R Documentation |
Sharpe Ratio Information Coefficient
Description
Computes the Sharpe Ratio Information Coefficient of Paulsen and Soehl, an asymptotically unbiased estimate of the out-of-sample Sharpe of the in-sample Markowitz portfolio.
Usage
sric(z.s)
Arguments
z.s |
an object of type |
Details
Let X
be an observed T \times k
matrix whose
rows are i.i.d. normal. Let \mu
and \Sigma
be
the sample mean and sample covariance. The Markowitz portfolio is
w = \Sigma^{-1}\mu,
which has an in-sample Sharpe of
\zeta = \sqrt{\mu^{\top}\Sigma^{-1}\mu}.
The Sharpe Ratio Information Criterion is defined as
SRIC = \zeta - \frac{k-1}{T\zeta}.
The expected value (over draws of X
and of future returns)
of the SRIC
is equal to the expected value of the out-of-sample
Sharpe of the (in-sample) portfolio w
(again, over the same draws.)
Value
The Sharpe Ratio Information Coefficient.
Author(s)
Steven E. Pav shabbychef@gmail.com
References
Paulsen, D., and Soehl, J. "Noise Fit, Estimation Error, and Sharpe Information Criterion." arxiv preprint (2016): https://arxiv.org/abs/1602.06186
See Also
Other sropt Hotelling:
inference()
Examples
# generate some sropts
nfac <- 3
nyr <- 5
ope <- 253
# simulations with no covariance structure.
# under the null:
set.seed(as.integer(charToRaw("fix seed")))
Returns <- matrix(rnorm(ope*nyr*nfac,mean=0,sd=0.0125),ncol=nfac)
asro <- as.sropt(Returns,drag=0,ope=ope)
srv <- sric(asro)