Table 3:

Top: model odds ratio $O_{M_{\rm A},M_{\rm B}}$ for scenario 1 to 5 (which include l=2 modes). Bottom: odds ratio for scenario 6, comparing 4 models (identifications A and B, with or without l=2).
Scenario $O_{M_{\rm A},M_{\rm B}}$
1 $2 \times 10^{48}$
2 $7 \times 10^{26}$
3 $1.5 \times 10^4$
4 7.209
5 1.578

Scenario 6
$M^l_k \backslash M^{l'}_{k'}$ $M^1_{\rm A}$ $M^1_{\rm B}$ $M^2_{\rm A}$ $M^2_{\rm B}$ $P_{\rm R}(M^l_k\vert y,I)$
$M^1_{\rm A}$ 1 4.6104 92.6707 2.9385 $64 \%$
$M^1_{\rm B}$ 0.2169 1 20.1003 0.6374 $13\%$
$M^2_{\rm A}$ 0.0317 0.0495 1 0.0108 $1\%$
$M^2_{\rm B}$ 0.3403 1.5690 31.5373 1 $22\%$
The identification is indicated as the subscript of the model, the highest l modes as the exponent. Scenario 6 does not include l=2 modes and thus the correct model is $M^1_{\rm A}$. The values of the matrix represent the odds ratio. Note the correct model only reaches a probability of 64%.

Source LaTeX | All tables | In the text

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.