MultipleProbeTest.pdf

From Array Suite Wiki

Multiple Probe Test

The "Multiple Probe Test" module will do a ranking of probes based on their differential effects between two groups of samples. The module will calculate gene scores from a dataset of probe construct profiles.

MultProbeTest0.png

General

Input/Output

The window includes a dropdown box to select the Project and Data object on which the command will be run.

  • Selections can be made on which variables should be included in the Paired Group Test (options include "all", "selected", "visible", and any pre-generated Lists).
  • Selections can also be made on which observations should be included in the Paired Group Test. (options include "all", "selected", "visible", and any pre-generated Lists).

Options

  • Test Type - The tests available are TTest, Wilcoxon and KSTest.

Note: The KS test has VERY low power for small sample size (actually it may require as many as 50) and we would not recommend using this test. We believe that the best test is paired t-test (which requires log-2 scaled data for which there is an option to perform log-2 transformation for the test in the dialog).

  • The Group can be selected from the dropdown box (and comes from columns in the Design Table). This would be the Design Table column that the user is interested in comparing.
  • The "Compare to" value can be selected from the dropdown box (and comes from columns in the Design Table). This would be the value that is to be compared to.
  • The user has the option of setting a Multiplicity test (None, FDR_BH, FDR_BY, Bonferroni, Sidak, StepDownBonferroni, StepDownSidak, StepUp and QValue--with BDR_BH being the default option) and an Alpha level (pvalue cutoff) to be used for the generation of the List.

Note: The Multiplicity adjustment takes into account the total number of tests performed within a given analysis. There is the ability to set the default option to adjust p-values on a per-test basis. Please refer to the "[ Statistics]" section in the User Guide.

  • Selecting the "Generate significant list" checkbox will generate a List of the significant rows based on the test using a default Alpha level of 0.05. The user can also select the option to "Split the significant list by change direction (i.e. a list for up and a separate list for down.
  • Selecting the "Generate fold change" checkbox will result in a column of fold change values in the output table.
  • Perform Log-2 transformation on the data - This option should be selected if the input data has not already be log-2 transformed.
  • The user has the option to name the Table to be generated.

Clicking Submit will generate a Table in the Inference tab of the Solution Explorer for the requested test.

OmicScript

[[]]