Two Group Test
The Two Group Test module allows the user to perform a two-sample t-test or Wilcoxon test to determine whether the means of two independent groups differ, and will generate an Inference table.
However, this menu option is not the recommended method for a T-test. Use of the General Linear Model is preferred for a more complete statistical inference test.
To run this module, type MicroArray | Inference | Other Tests | Two Group Test.
Input Data Requirements
This module works on -Omic data types. The Design metadata table should have a column by which the samples can be sub-grouped.
- Project & Data: The window includes a dropdown box to select the Project and Data object to be filtered.
- Variables: Selections can be made on which variables should be included in the filtering (options include All variables, Selected variables, Visible variables, and Customized variables (select any pre-generated Lists)).
- Observations: Selections can be made on which observations should be included in the filtering (options include All observations, Selected observations, Visible observations, and Customized observations (select any pre-generated Lists).
- Output name: The user can choose to name the output data object.
- Test Type: Sets the Test type (TTest, WilcoxonTest, KSTest and ModeratedTTest). TTest and ModeratedTTest are parametric tests, while the WilcoxonTest and KSTest are non-parametric tests.
- Group: Choose the factor from the design table to test whether two levels in the factor have different means.
- Compare to: Choose which covariate level to compare to.
- Multiplicity: The option allows the user to specify the Multiplicity test (None, FDR_BH, FDR_BY, Bonferroni, Sidak, StepDownBonferroni, StepDownSidak, and StepUp--with BDR_BH being the default option)
- Assume equal variance: Checking this box assumes samples with different factor levels share the same error variance.(checked by default).
- Generate significant list: Checking this box generates a List of significant rows based on the test.
- Calculate medians: Selecting this option will compare the medians of different groups, rather than the means, of different groups.
- Alpha level: Specify the p-value cutoff to be used for the generation of the List.
- Split the significant list by change direction: Generate two significant lists, split by the sign of estimates.
- Generate fold change: Checking this box will generate a column of fold-change values in the output table. The fold change transformation options include Exp2, Exp. Exp10 and Ratio.
- Bootstrap without replacement: The user can select this method for assigning measures of accuracy to sample estimates.
- Group 1 Size - Number of samples to include in group 1
- Group 2 Size - Number of samples to include in group 2
- Bootstrap number (10-100000): As many samples as is reasonable given available computing power and time should be used.
Clicking "Submit" will generate a Table in the Inference tab of the Solution Explorer for the requested test as shown below:
The user can append other Views, such as a Volcano plot:
In addition, several Views are available in the task tab, including the Intensity/Estimate View: