Hello, good project, I had been looking for something like this and is really great.
I am trying to do something similar but with weighted samples.

I have a question in the formulation in http://pythonhosted.org/DynStatCov/usage/background.html#updating.

When you update A is something like A_{n+1}=A_{n}+(x_{n+1}* ((x_{x-1})^{T})

I don't understand the second sub-index of the x (x_{x-1}) ¿what is that x representing ?