Design matrix for 2x2 factorial
In this 2x2 factorial experiment to investigate the effect of drought on tree growth, 2 different types of Populus tree were grown with 2 different amounts of water. In order to have one model coefficient per group, you need to first combine the two variables.
This exercise is part of the course
Differential Expression Analysis with limma in R
Exercise instructions
The ExpressionSet object eset
with the Populus data has been loaded in your workspace.
Combine the variables
type
(the type of tree) andwater
(normal vs. drought) into a single factor variable.Use
model.matrix
to create a design matrix with no intercept.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Create single variable
group <- with(___(eset), paste(___, ___, sep = "."))
group <- factor(group)
# Create design matrix with no intercept
design <- model.matrix(~___ + ___)
colnames(design) <- levels(group)
# Count the number of samples modeled by each coefficient
colSums(design)