Skip to main content

Table 28 Selection of the best parametric model as a function of s, M and \(M'\) for the measure \(R_t^{s}\) computed on Netflix real data

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

Model selection for \(R_t^{s}\)-NETFLIX

M=80%

Lognormal

 

Exponential

 

Weibull

 

Gamma

 

\(M' \mid s=0\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

1.0361e+03

1.0418e+03

1.3764e+03

1.3792e+03

1.0778e+03

1.0834e+03

1.2958e+03

1.3015e+03

\(40\%\)

1.0380e+03

1.0437e+03

1.3744e+03

1.3772e+03

1.0802e+03

1.0959e+03

1.2843e+03

1.2900e+03

\(50\%\)

1.0323e+03

1.0380e+03

1.3702e+03

1.3730e+03

1.0753e+03

1.0809e+03

1.2800e+03

1.2856e+03

\(M' \mid s=5\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

1.0783e+03

1.0839e+03

1.2926e+03

1.2955e+03

1.1236e+03

1.1293e+03

1.1915e+03

1.1972e+03

\(40\%\)

989.0394

994.7120

1.2154e+03

1.2183e+03

1.0407e+03

1.0463e+03

1.1026e+03

1.1083e+03

\(50\%\)

868.0608

873.7333

1.1150e+03

1.1178e+03

933.0974

938.7699

993.1070

998.7796

\(M' \mid s=50\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

1.0509e+03

1.0566e+03

1.2530e+03

1.2558e+03

1.1014e+03

1.1071e+03

1.0576+03

1.0633e+03

\(40\%\)

967.5316

973.2041

1.2033e+03

1.2061e+03

1.0295e+03

1.0351e+03

1.1093e+03

1.1150e+03

\(50\%\)

905.9353

911.6079

1.1770e+03

1.1799e+03

971.1089

976.7815

1.1713e+03

1.1770e+03

\(M' \mid s=100\)

AIC

BIC

AIC

BIC

AIC

BIC

AIC

BIC

\(30\%\)

960.0611

965.7337

1.2244e+03

1.2272e+03

1.0199e+03

1.0255e+03

1.1135e+03

1.1191e+03

\(40\%\)

921.6886

927.3612

1.1855e+03

1.1883e+03

982.9280

988.6005

1.0662e+03

1.0719e+03

\(50\%\)

849.4650

855.1376

1.1589e+03

1.1618e+03

917.0612

922.7337

1.0087e+03

1.0143e+03

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