ewstats
Expected return and covariance from return time series
Syntax
Description
[
computes estimated expected returns (ExpReturn
,ExpCovariance
,NumEffObs
] = ewstats(RetSeries
)ExpReturn
), estimated covariance matrix (ExpCovariance
), and the number of effective observations (NumEffObs
). These outputs are maximum likelihood estimates which are biased.
[
adds optional input arguments forExpReturn
,ExpCovariance
,NumEffObs
] = ewstats(___,DecayFactor
,WindowLength
)DecayFactor
andWindowLength
.
Examples
Input Arguments
Output Arguments
Algorithms
For a return seriesr(1),…,r(n), where (n) is the most recent observation, andwis the decay factor, the expected returns (ExpReturn
) are calculated by
where the number of effective observationsNumEffObs
is defined as
E(r) is the weighed average ofr(n),…,r(1
). The unnormalized weights arew,w2, …,w(n-1). The unnormalized weights do not sum up to1
, soNumEffObs
rescales the unnormalized weights. After rescaling, the normalized weights (which sum up to1
) are used for averaging. Whenw=1
, thenNumEffObs
=n, which is the number of observations. Whenw<1
,NumEffObs
is still interpreted as the sample size, but it is less thanndue to the down-weight on the observations of the remote past.
Note
There is no relationship betweenewstats
function and the RiskMetrics® approach for determining the expected return and covariance from a return time series.