Histogram of p-values

After performing the test, confirm that the model was properly specified by inspecting the distribution of p-values for each contrast. Recall that a uniform distribution of p-values is expected for a contrast with few differentially expressed genes, and a right skewed distribution is expected for a contrast with many differentially expressed genes.

This exercise is part of the course

Differential Expression Analysis with limma in R

View Course

Exercise instructions

The fitted model object fit2 has been loaded in your workspace. The limma package is already loaded.

Use topTable to obtain the summary statistics for every gene for the contrast "dox_wt". Set the number of genes to return equal the number of rows of fit2.
Repeat for the contrasts "dox_top2b" and "interaction".
Use hist to create a histogram of p-values for each of the three contrasts.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Obtain the summary statistics for the contrast dox_wt
stats_dox_wt <- ___(fit2, coef = ___, number = ___,
                         sort.by = "none")
# Obtain the summary statistics for the contrast dox_top2b
stats_dox_top2b <- ___(fit2, coef = ___, number = ___,
                            sort.by = "none")
# Obtain the summary statistics for the contrast interaction
stats_interaction <- ___(fit2, coef = ___, number = ___,
                              sort.by = "none")

# Create histograms of the p-values for each contrast
___(stats_dox_wt[___])
___(stats_dox_top2b[___])
___(stats_interaction[___])

Edit and Run Code