Enrichment Widgets
Enrichment widgets are located on the list analysis page. There are a number of different types of enrichment widgets, but all list a term, a count and an associated p-value. The term can be something like a publication name or a GO term. The count is the number of times that term appears for objects in your list. The p-value is the probability that result occurs by chance, thus a lower p-value indicates greater enrichment.
Method
The p-value is calculated using the Hypergeometric distribution. Four numbers are used to calculate each p-value:
- n = the number of objects in your list
- N = the number of objects in the reference population
- k = the number of objects annotated with this item in your list
- M = the number of objects annotated with item in the reference population
(M choose k) (N-M choose n-k)
P = -----------------------------
N choose n
See: Hypergeometric.java
Multiple Test Correction
The greater number of tests that are run increases the chance for error. Each enrichment widget has three test correction options:
None
No test correction performed, these are the raw results. These p-values will be lower than if test correction was applied.
Benjamini Hochberg
Benjamini-Hochberg test correction applied.
Bonferroni
Bonferroni is the simplest and most conservative method of multiple test correction. The number of tests run (the number of terms associated with objects in the list) is multiplied by the alpha value (the significance value). The value is then added to the p-value of each term.
See: Bonferroni.java
