quantile to calculate inverse CDF
skewness (default = 0)
excess kurtosis (kurtosis - 3) (default = 0)
import mir.test: shouldApprox; 0.5.cornishFisherInvCDF.shouldApprox == 0; 0.5.cornishFisherInvCDF(1).shouldApprox == -0.1666667; 0.5.cornishFisherInvCDF(-1, 0).shouldApprox == 0.1666667; 0.9.cornishFisherInvCDF(0.1, 0).shouldApprox == 1.292868; 0.9.cornishFisherInvCDF(0.1, 1).shouldApprox == 1.220374; 0.9.cornishFisherInvCDF(0.1, -1).shouldApprox == 1.365363; 0.99.cornishFisherInvCDF(0.1, 0).shouldApprox == 2.396116; 0.99.cornishFisherInvCDF(0.1, 1).shouldApprox == 2.629904; 0.99.cornishFisherInvCDF(0.1, -1).shouldApprox == 2.162328; 0.01.cornishFisherInvCDF(0.1, 0).shouldApprox == -2.249053 ; 0.01.cornishFisherInvCDF(0.1, 1).shouldApprox == -2.482841; 0.01.cornishFisherInvCDF(0.1, -1).shouldApprox == -2.015265;
Ditto, but assumes mu = 0 and std = 1