In addition to the poor performance of our black carbon LUR model in evaluation tests, the application of this model was further limited by our need to use PM2.5 monitoring data, as opposed to black carbon measurements, for seasonal adjustment.
In general, the most important part of model evaluation is testing whether the model better fits empirical data than other models.
Then both the phylogenetic tree and the transformed microarray data as a set of continuous data were read into the program CoMET (Continuous-character Model Evaluation and Testing) [ 85].
Using the Aurora 2 database, one GMM is trained for each known noise type, and the GMM that provides the best accumulated likelihood for the first 10 frames of the noisy test speech is chosen as the noise type model for evaluation testing.
Briefly, these stages consist of (1) segmentation of soft tissue, (2) registration of the left images to the right images, (3) bilateral subtraction of the coregistered images, (4) filtering of the images to enhance the signal and texture, (5) feature extraction, (6) multivariate models selection using a train set, and (7) model evaluation on a test set.
As Brauer et al. (2008) recount in their study, the LUR model performed poorly in evaluation tests and used PM2.5 data for temporal adjustment, because only annual black carbon data were available.
Finally, omnibus tests for model coefficients and Hosmer-Lemeshow (H-L) goodness of fit tests for model evaluation were also done in Tanzania from 2011 to 2012.
Variables derived from Herd Test Day profiles obtained after a test day model evaluation were used to define herd environment.
Model evaluation and simplification proceeded using Z-test and likelihood ratio tests (LRTs) [Bates et al., 2012].
Our model evaluation procedure is primarily a testbed for selecting an appropriate substitution model for stems, loops and neutrally-evolving sequence (see "Patterns of nucleotide substitution in non-coding RNA").
