Table 1.
Preliminary Evaluation of different models. We observe that iterative fitting of Inverse Weibull performs significantly better than iterative fitting of other distributions like Gaussian, Beta (4-parameter), Fisher-Tippet (Extreme Value distribution), and Log Normal. The lowest value of MSE/MAPE and highest values of R2 among all distributions are shown in bold.
| Country | MSE | R2 | MAPE | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Weibull | Gaussian | Beta 4 | Fisher-Tippet | Log Normal | Weibull | Gaussian | Beta 4 | Fisher-Tippet | Log Normal | Weibull | Gaussian | Beta 4 | Fisher-Tippet | Log Normal | |
| World | 2.41E+07 | 3.78E+07 | 2.99E+07 | 2.89E+07 | 2.99E+07 | 0.98 | 0.97 | 0.98 | 0.97 | 0.97 | 49.14 | 49.14 | 50.39 | 48.12 | 46.19 |
| India | 6.97E+03 | 7.09E+03 | 6.89E+03 | 6.89E+03 | 7.00E+03 | 0.97 | 0.97 | 0.98 | 0.97 | 0.97 | 18.33 | 18.33 | 18.49 | 21.69 | 20.69 |
| United States | 8.37E+06 | 1.11E+07 | 8.63E+05 | 9.47E+06 | 9.78E+06 | 0.95 | 0.93 | 0.94 | 0.93 | 0.94 | 24.33 | 24.33 | 40.23 | 71.64 | 111.63 |
| United Kingdom | 2.00E+05 | 2.22E+05 | 2.12E+05 | 2.02E+05 | 2.07E+05 | 0.95 | 0.95 | 0.95 | 0.95 | 0.95 | 21.46 | 21.46 | 20.43 | 21.52 | 17.42 |
| Italy | 1.56E+05 | 3.38E+05 | 2.10E+05 | 2.09E+05 | 2.35E+05 | 0.96 | 0.92 | 0.95 | 0.95 | 0.94 | 14.98 | 14.98 | 20.00 | 19.62 | 170.63 |