Skip to main content

Table 32 Selection of the best parametric model as a function of s, M and \(M'\) for the measure \(R_t^{s}\) computed on APPLE simulated data

From: Drawdown-based risk indicators for high-frequency financial volumes

Model selection for \(R_t^{s}\)-simulated data for APPLE

M=80%

Lognormal

 

Exponential

 

Weibull

 

Gamma

 

\(M' \mid s=0\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

1.1635e+03

1.692e+03

1.3839e+03

1.3868e+03

1.2043e+03

1.2099e+03

1.3705e+03

1.3762e+03

\(40\%\)

1.0663e+03

1.0719e+03

1.2982e+03

1.3010e+03

1.1181e+03

1.1237e+03

1.2279e+03

1.2336e+03

\(50\%\)

952.0155

957.6881

1.0814e+03

1.0842e+03

996.7772

1.0024e+03

1.0383e+03

1.0440e+03

\(M' \mid s=5\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

1.1715e+03

1.0682e+03

1.3693e+03

1.3722e+03

1.2146e+03

1.2203e+03

1.3535e+03

1.3592e+03

\(40\%\)

1.0682e+03

1.0739e+03

1.2301e+03

1.2329e+03

1.1145e+03

1.1201e+03

993.4517

999.1242

\(50\%\)

957.2985

962.9711

1.0039e+03

1.0067e+03

982.4105

988.0830

993.4517

999.1242

\(M' \mid s=50\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

1.0515e+03

1.0572e+03

1.1927+03

1.1956+03

1.1000+03

1.1057e+03

1.1523e+03

1.1580e+03

\(40\%\)

955.5430

961.2155

1.0827+03

1.0855+03

1.0091+03

1.0147+03

1.0509+03

1.0566+03

\(50\%\)

852.3765

858.0491

933.0831

935.9094

901.2634

906.9360

920.7401

926.4127

\(M' \mid s=100\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

1.0343e+03

1.0400e+03

1.1503e+03

1.1531e+03

1.0686e+03

1.0743e+03

1.1031e+03

1.1087e+03

\(40\%\)

957.3771

963.0496

1.0217e+03

1.0245e+03

985.0520

990.7245

998.5607

1.0042e+03

\(50\%\)

868.0799

873.7524

933.0373

935.9094

900.6337

906.3062

914.7511

920.4237

  1. The best parametric model is chosen by means of the AIC and BIC criteria. The smallest AIC and BIC values are in bold