Accelerating the pool-adjacent-violators algorithm for isotonic distributional regression

06/09/2020
by   Alexander Henzi, et al.
0

In this note we describe in detail how to apply the pool-adjacent-violators algorithm (PAVA) efficiently in the context of estimating stochastically ordered distribution functions. The main idea is that the solution of a weighted monotone least squares problem changes only little if one component of the target vector to be approximated is changed.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset