ESTEP: Perform one accelerated E-step of the EM algorithm

In jasonxu90/bdsem: Analysis of discretely observed Birth-Death-Shift processes

Description

ESTEP performs one E-step of the EM algorithm, computing expected sufficient statistics given current settings of the parameters. This function is the "accelerated" version, meaning that intervals with no observed changes are computed more efficiently using closed form expressions, bypassing generating function and FFT calculations on these intervals.

Usage

  ESTEP(betaVec, t.pat, num.patients, PATIENTDATA,
    patients.design, s1.seq, s2.seq)

Arguments

betaVec	A vector, the setting of beta coefficients
t.pat	A number, the observation interval length
num.patients	An integer, number of unique patients
PATIENTDATA	A matrix in the form returned by MakePatientData containing the set of observation intervals
patients.design	A design matrix in the same form as returned by PatientDesignExample
s1.seq	A vector of complex arguments evenly spaced along the unit circle
s2.seq	A vector of complex arguments evenly spaced along the unit circle

Value

A list containing a matrix of the expected sufficient statistics as well as the observed log likelihood value

jasonxu90/bdsem documentation built on May 18, 2019, 5:54 p.m.