m_estep: Compute conditional expectations for EM algorithms of Cao et al. (2000)
Description
Computes conditional expectation of OD flows for E-step of
EM algorithm from Cao et al. (2000) for their locally IID
model.
Usage
m_estep(yt, lambda, phi, A, c, epsilon)
Arguments
yt
numeric vector (length m) of link loads from
single time
lambda
numeric vector (length k) of mean OD flows
from last M-step
phi
numeric scalar scale for covariance matrix of
xt
A
routing matrix (m x k) for network being
analyzed
c
power parameter in model of Cao et al. (2000)
epsilon
numeric nugget to add to diagonal of
covariance for numerical stability
Value
numeric vector of same size as lambda with conditional
expectations of x
References
J. Cao, D. Davis, S. Van Der Viel, and B. Yu. Time-varying
network tomography: router link data. Journal of the
American Statistical Association, 95:1063-75, 2000.