In order to evaluate the information added by our proposed features as compared to the previously widely used Adamic-Adar and overlap metrics, we compare our prediction results thus far with a simplified model using the Adamic-Adar and overlap features alone, while using the same predictive framework, and compare the change in average AUC scores between cities.
Using a novel t-test transformation of coevolution metrics, we systematically compared four tree-aware and five tree-ignorant coevolution algorithms, applying them to myoglobin and myosin.
To study the effect of modeling assumptions on the evaluated routing metrics, we also compare the analytical results with the results reported in an independently-conducted simulation study [8] and show that our modeling assumptions do not have a significant effect on the results.
For other metrics, we can compare minimum detectable effect sizes based on our study design with effect sizes observed in other studies.
To evaluate how well different forest management histories in our study region might provide habitat for fishers, we compared metrics of forest composition and configuration within fisher home ranges with metrics from forests managed under three distinct management histories.
To determine whether sets of genes identified by different metrics have unique properties, we compared the proportions of X-linked male- and female-biased genes among metrics.
To analyze the effect of the two optimization metrics on the performance, we compared the performance of the optimized queries with respect to the AUC, BEDROC, and awROCE5% performance on the external test splits.
When we compared metrics generated by evaluating the complete data and those extrapolated from random 5 Mb segments of the genome, the two sets of summary statistics were remarkably similar (see QPLOT webpage, e.g)., but computing time was reduced from 38 minutes to 13 minutes.
To assess differences in exposure classification between the two metrics in the context of an epidemiologic study, we compared the metrics as dichotomous and as continuous variables.
