Hi, I am trying to implement LDA on some fMRI data. Trying to do it myself rather that using a package as I'd like to understand whats going on under the bonnet as it were.

I have obtained a weight vector, \mathbf{w}, according to the formula

\mathbf{w} \propto \mathbf{\Sigma}^{-1}_{w} (\mathbf{m}_{2} - \mathbf{m}_{1})

where \mathbf{\Sigma}^{-1}_{w} is the (inverse of the) total within-class covariance matrix and \mathbf{m} denotes the mean of a class (class 2 and 1 in this case)

I can renormalise \mathbf{w} to counter any numerical issues, since it is the direction and not the magnitude of this vector that is important. So far so good.


I should then be able to find a discriminant c, such that a new datum \mathbf{x} is classified as belong to class 1 if \mathbf{w} \cdot \mathbf{x} > c and class 2 otherwise.

I see intuitively that if the prior on each class is the same then (I think) c = 1/2 \cdot (\mathbf{w} \cdot \mathbf{m}_{1} + \mathbf{w} \cdot \mathbf{m}_{2})

Is that correct? But more importantly, is there a simple but principled way to establish c in the case of asymmetric priors?

Many thanks in advance, MD