PortfolioOptimisers.jl

Appearance

5

PortfolioOptimisersCovariance ​

PortfolioOptimisers.PortfolioOptimisersCovariance Type
julia
struct PortfolioOptimisersCovariance{T1, T2} <: AbstractCovarianceEstimator
    ce::T1
    mp::T2
end

Composite covariance estimator with post-processing.

PortfolioOptimisersCovariance is a flexible container type that combines any covariance estimator with a matrix post-processing step. This enables users to apply additional transformations or corrections (such as shrinkage, regularisation, or projection to positive definite) to the covariance or correlation matrix after it is estimated.

Fields

  • ce: The underlying covariance estimator.

  • mp: Matrix post-processing estimator.

Constructor

julia
PortfolioOptimisersCovariance(; ce::AbstractCovarianceEstimator = Covariance(),
                              mp::AbstractMatrixProcessingEstimator = DefaultMatrixProcessing())

Keyword arguments correspond to the fields above.

Examples

julia
julia> PortfolioOptimisersCovariance()
PortfolioOptimisersCovariance
  ce ┼ Covariance
     │    me ┼ SimpleExpectedReturns
     │       │   w ┴ nothing
     │    ce ┼ GeneralCovariance
     │       │   ce ┼ StatsBase.SimpleCovariance: StatsBase.SimpleCovariance(true)
     │       │    w ┴ nothing
     │   alg ┴ Full()
  mp ┼ DefaultMatrixProcessing
     │       pdm ┼ Posdef
     │           │   alg ┴ UnionAll: NearestCorrelationMatrix.Newton
     │   denoise ┼ nothing
     │    detone ┼ nothing
     │       alg ┴ nothing

Related

source
Statistics.cov Method
julia
cov(ce::PortfolioOptimisersCovariance, X::AbstractMatrix; dims = 1, kwargs...)

Compute the covariance matrix with post-processing using a PortfolioOptimisersCovariance estimator.

This method computes the covariance matrix for the input data matrix X using the underlying covariance estimator in ce, and then applies the matrix post-processing step specified by ce.mp. This enables workflows such as shrinkage, regularisation, or projection to positive definite after covariance estimation.

Arguments

  • ce: Composite covariance estimator with post-processing.

  • X: Data matrix of asset returns (observations × assets).

  • dims: Dimension along which to compute the covariance (1 = columns/assets, 2 = rows). Default is 1.

  • kwargs...: Additional keyword arguments passed to the underlying covariance estimator and matrix processing step.

Returns

  • sigma::Matrix{<:Real}: The processed covariance matrix.

Validation

  • dims is either 1 or 2.

Related

source
Statistics.cor Method
julia
cor(ce::PortfolioOptimisersCovariance, X::AbstractMatrix; dims = 1, kwargs...)

Compute the correlation matrix with post-processing using a PortfolioOptimisersCovariance estimator.

This method computes the correlation matrix for the input data matrix X using the underlying covariance estimator in ce, and then applies the matrix post-processing step specified by ce.mp. This enables workflows such as shrinkage, regularisation, or projection to positive definite after correlation estimation.

Arguments

  • ce: Composite covariance estimator with post-processing.

  • X: Data matrix of asset returns (observations × assets).

  • dims: Dimension along which to compute the correlation (1 = columns/assets, 2 = rows). Default is 1.

  • kwargs...: Additional keyword arguments passed to the underlying covariance estimator and matrix processing step.

Returns

  • rho::Matrix{<:Real}: The processed correlation matrix.

Validation

  • dims is either 1 or 2.

Related

source