Thursday, April 26, 2018

kalman - How to find optimal noise covariance matrices Q & R



I am trying to use the discrete Kalman filter for forecasting and I wonder what is commonly considered as the optimal way of determining the measurement noise covariance constants (Q and R) for a given time series? Do you recommend some approaches based on your research/experience?



Answer



I recently blogged about this very topic.


Essentially, there are 3 ways to estimate Q & R.



  1. approximate

    • calculate variate estimate of error in a controlled environment

    • if z doesn't change, calculate variance estimate of z

    • if z does change, calculate variance of regression estimate of z




  2. guess

    • use some constant multiplied by the identity matrix

    • higher the constant, higher the noise



  3. MLE


    • pykalman's em

    • unfortunately, non-convex problem => local optima




Check out the rest of my post here


No comments:

Post a Comment

technique - How credible is wikipedia?

I understand that this question relates more to wikipedia than it does writing but... If I was going to use wikipedia for a source for a res...