Table 4.
Posterior odds ratios for models CP1 and TN expressed in log10 scale.
| Dataset | 0% | 0.3% | 1% | 5% | 10% |
|---|---|---|---|---|---|
| OneF | −0.295(4) | −0.231(5) | 0.141(6) | 4.9 | 4.9 |
| TwoF | 0.598(9) | 0.415(8) | 0.81(1) | 2.9(2) | 4.9 |
| MultiF | −0.035(8) | −0.057(8) | −0.155(8) | 1.67(3) | – |
Notes. Posterior odds ratios refer to the from the model comparison between CP1 and TN for the datasets, and percentages of outliers studied. For the MultiFMultiF+10Y (MF+10Y) dataset, this analysis has not been performed in the scenario of 10% of outliers injected in the data. Uncertainty over the final digit is indicated by the number in parentheses. We refer to uncertainties as those implemented in the odds_ratio function of the enterprise_extension. Briefly, these uncertainties are obtained by summing in quadrature the normalized differences between the samples drawn from each model and the number of transactions between the models.
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.