GitHub

Cross-Sectional Forecast History Carry

The carry fold of a CrossSectionalFactorPrior dispatches on its orthogonal forecast fit at one step, and a new rule of AbstractOrthogonalForecastFit can add a method for it. The other names of this topic are private, and the private page documents them.

PortfolioOptimisers.orthogonal_forecast_step — Function
orthogonal_forecast_step(ofit::AbstractOrthogonalForecastFit, rfe, P::NamedTuple,
                         csfm::CrossSectionalFactorModel, fs,
                         cre::AbstractCrossSectionalRegressionEstimator)
orthogonal_forecast_step(ofit::OrthogonalPartCalibration, rfe, P::NamedTuple,
                         csfm::CrossSectionalFactorModel, fs,
                         cre::AbstractCrossSectionalRegressionEstimator)

Runs a step of the Return Forecast of the carry fold of a Cross-Sectional Factor Prior under its Orthogonal Forecast Fit, as orthogonal_forecast_result fits it in the batch fit.

Algorithm

The method that Julia selects is the algorithm.

  1. OrthogonalPartCalibration: call return_forecast_step with cre, so the fold state also carries the regression of κ⊥. The batch fit calls orthogonal_forecast_result with cre for every member under this rule, and the prior refuses a member that answers false to calibrates_orthogonal_part, so the step does the same for every member that it accepts.
  2. Any other rule: call return_forecast_step with no cre.

Arguments

  • ofit: The Orthogonal Forecast Fit of the prior.
  • rfe: The Return Forecast Estimator that the step fits.
  • P: The scores, the weights and the group labels of the rows of the step.
  • csfm: The factor-model block of the rows of the step.
  • fs: The fold state that the state carries, or nothing.
  • cre: Cross-Sectional Regression Estimator of the prior.

Returns

Related

source