The SNP Interaction Discovery process performs a penalized logistic regression at different lambda levels (ranging from 2 through 4) and presents the cross validation statistics for these models and determine which level is best for prediction from that particular data set.
Cross validation consists of dividing the rows of a wide data set into two groups, labeling one as the test group and the other as the training group, and then, after setting aside the test group, fitting one or more predictive models only to the training set. The fitted models derived using the training set are then evaluated with the predictor variables of the test set to obtain predicted values. These values are then compared to the observed values. This process is repeated a specified number of times, using a different training/test division. Results are summarized and displayed side-by-side. Refer to Cross Validation Model Comparison for more information about this process.
Running this process using the GeneticMarkerExample sample setting generates the tabbed Results window shown below. Refer to the SNP Interaction Discovery process description for more information. Output from the process is organized into tabs. Each tab contains one or more plots, data panels, data filters, and other elements that facilitate your analysis.
The Results window contains the following panes:
This pane provides you with a space to view individual tabs within the Results window. Use the tabs to access and view the output plots and associated data sets.
|
•
|
RMSE: Displays results for the Root Mean Square Error performance criterion.
|
|
•
|
AUC: Present only when data contains binary dependent variables. Displays results for the area under the receiver operating characteristic (ROC) curve performance criterion.
|
|
•
|
Accuracy: Present only when data contains binary dependent variables. Displays results for the accuracy performance criterion.
|
|
•
|
Reliability Diagrams: Displays reliability diagrams for each method.
|
|
•
|
Model Effects: Hierarchically clusters effects chosen from each method.
|
|
•
|
Click to reveal the underlying data table associated with the current tab.
|
|
•
|
Click to reopen the completed process dialog used to generate this output.
|
|
•
|
|
•
|
Click to close all graphics windows and underlying data sets associated with the output.
|