WinCross performs a T-Test for the differences between independent means (for example, males versus females or between age groups) to determine if significant differences exist with respect to the row's variable. For these tests, when more than two columns are compared, all paired combinations of the columns are tested individually with significant differences annotated accordingly.
You can choose if the calculation should be based on equal or unequal variances or let WinCross make the decision whether to use the test for equal or unequal variances.
Select one of the following tests:
Note: When Use general formula for standard error (Treat weights as replicates) is selected on the Statistics tab of Job Settings, the Means test of Independent (based on test for equal variances) is not a valid test for this option. |
When more than two columns are compared, all paired combinations of the columns are tested individually and significant differences are annotated accordingly.
When a "Total" column is being used and denoted as such in a comparison group, given the possibility of finding "significant" differences due only to the degree of overlap of the part to the whole (Total), WinCross has adopted the safeguard of declaring all such differences not significant if the fraction of the part to the whole is less than 5% or greater than 95%.
T-Test Options
The significance value is the probability of the test concluding that there is a significant difference in fact when there is none. The confidence level, on the other hand, is the complement of the significance level. It measures the probability of the test concluding that there is no significant difference when in fact there is none.
Confidence levels
Show significance indicators in banner
Displays the significance annotation displayed for each banner column.
Related topics: