Table 22 Selection of the best parametric model as a function of s and M for the measure \(T_c^{s}\) computed on Netflix real data
From: Drawdown-based risk indicators for high-frequency financial volumes
Model selection for \(T_c^{s}\)-NETFLIX | ||||||||
|---|---|---|---|---|---|---|---|---|
Lognormal | Exponential | Weibull | Gamma | |||||
\(M \mid s=0\) | AIC | BIC | AIC | BIC | AIC | BIC | AIC | BIC |
\(30\%\) | 214.8728 | 220.5454 | 397.8642 | 400.7005 | 391.7151 | 397.3876 | 397.3270 | 402.9996 |
\(40\%\) | 239.5499 | 245.2224 | 458.7985 | 461.6347 | 423.4447 | 429.1172 | 458.1477 | 463.8203 |
\(80\%\) | 290.7235 | 296.3961 | 807.2353 | 810.0716 | 499.1320 | 504.8046 | 634.9171 | 640.5896 |
\(M \mid s=5\) | AIC | BIC | AIC | BIC | AIC | BIC | AIC | BIC |
|---|---|---|---|---|---|---|---|---|
\(30\%\) | 465.3088 | 470.9813 | 560.9757 | 563.8120 | 551.4480 | 557.1206 | 562.6032 | 568.2758 |
\(40\%\) | 516.3383 | 522.0108 | 606.3285 | 609.1647 | 595.2202 | 600.9277 | 607.8449 | 613.5174 |
\(80\%\) | 625.0440 | 630.7166 | 886.3748 | 889.2111 | 723.3731 | 729.0456 | 806.3157 | 811.9883 |
\(M \mid s=50\) | AIC | BIC | AIC | BIC | AIC | BIC | AIC | BIC |
|---|---|---|---|---|---|---|---|---|
\(30\%\) | 347.7825 | 353.4550 | 482.4938 | 485.3300 | 471.1201 | 476.7927 | 484.4893 | 490.1619 |
\(40\%\) | 411.3672 | 417.0398 | 549.4779 | 552.3142 | 523.5930 | 529.2656 | 548.3202 | 553.9927 |
\(80\%\) | 472.9047 | 478.5772 | 843.5308 | 846.3671 | 612.1396 | 617.8121 | 720.6387 | 726.3113 |
\(M \mid s=100\) | AIC | BIC | AIC | BIC | AIC | BIC | AIC | BIC |
|---|---|---|---|---|---|---|---|---|
\(30\%\) | 282.1726 | 287.8452 | 424.6410 | 427.4773 | 424.5338 | 430.2064 | 418.8807 | 424.5532 |
\(40\%\) | 347.8117 | 353.4842 | 500.4179 | 503.2541 | 484.4048 | 490.0773 | 502.4159 | 508.0884 |
\(80\%\) | 424.3772 | 430.0498 | 825.0327 | 827.8689 | 585.6312 | 591.3037 | 702.1969 | 707.8695 |