Revision as of 18:13, 22 May 2006

Overview

Note - as of 5/22/2006 this page is being redrafted, should be complete on 5/23/2006.

In this tutorial, you will:

• Discuss the background for using Student's t-Test to evaluate data.
• Load a predefined matrix format microarray dataset.
• Select classes of arrays to compare.
• Apply a t-Test.
• Apply a multi t-test.
• Visualize the results in the Color Mosaic and Volcano Plot components.
• Note the creation of resulting marker lists and visualization objects.

Preparation

The file "webmatrix_quantile_log2_dev1_mv0.exp" is contained in the downloadable zip archive tutorial_data.zip. See the Download area.

For tips on loading data files, see the section Tutorial - Projects and Data Files.

t-Test

A t-Test analysis can be used to identify markers with statistically significant differential expression between two sets of microarrays. The t-test determines, for each marker, if there is a significant difference between the two groups (case and control). To perform this analysis, you must classify the sets, set the analysis parameters and view the results in the visualization components. The t-test implementation in geWorkbench offers several options for multiple testing correction and evaluation of the test statistic. A detailed description of the t-Test parameters is also available in online help.

P-value parameters:

The p-value can be estimated from 1. the t-statistic (the default) or 2. by permutation.

Alpha corrections

For multiple testing (alpha) correction, the following options are offered: 1. no correction 2. Standard Bonferonni Correction 3. Adjusted (step down) Bonferonni Correction. 4. Additional methods are available if the p-value is being estimated by permuation.

Degrees of Freedom

Group variances can be declared as: 1. unequal (Welch approximation) (the default) 2. Equal.

Classification

The desired sets arrays should be activated in the Arrays/Phenotypes component.

The t-test requires two groups of microarrays to compare. geWorkbench distinguishes the two groups by one being labeled as "Case". By default, all others are labeled control. Note that in the Arrays/Phenotypes component, more than one set of arrays can be marked "Case". All remaining (activated) arrays will then be in the "Control" group.

Set Analysis Parameters

1. From the Analysis Panel, select T-Test Analysis.
2. Populate the below parameters values and click on Analyze.

• Alpha-corrections tab: Just Alpha.
• P-Value Parameters tab: p-values based on t-distribution. Note that the default alpha (critical p-value) is set to 0.01.
• Degree of Freedom tab: Welch approximation - unequal group variances.

t-Test Results

T_multi-t-test_ProjectFolders_result.png

T_multi-t-test_Set_selection_BCELL.png

T_t-test_Arrays_case-set_BCELL_webm_qldm.png

T_t-test_bonferroni_BCELL_webm_qldm.png

T_t-test_colormosaic_BCELL_webm_qldm.png

T_t-test_dof.png

T_t-test_Markers_BCELL_result.png

T_t-test_ProjectFolders_result.png

T_t-test_p-values.png

T_t-test_set_Case_BCELL_webm_qldm.png

T_t-test_Set_selection_BCELL.png

T_t-test_volcano_BCELL_webm_qldm.png

Multi t-test

• The Multi t-test component allows more than two groups to be compared simultaneously. Its shows each Array Set that has been defined. It will compare in pairwise fashion all selected sets.

• A step-down Bonferonni type correction is used to account for multiple testing of markers.
• As currently implemented, it does not correct for multiple pairwise t-tests being run on the various array sets.
• Results can be viewed in the Volcano Plot and in the Color Mosaic components.

References

t-test [1]