An EM algorithm for the model fitting of Markovian binary trees

Markovian binary trees form a class of continuous-time branching processes where the lifetime and reproduction epochs of individuals are controlled by an underlying Markov process. An Expectation-Maximization (EM) algorithm is developed to estimate the parameters of the Markov process from the continuous observation of some populations, first with information about which individuals reproduce or die (the distinguishable case), and second without this information (the indistinguishable case). The performance of the EM algorithm is illustrated with some numerical examples. Fits resulting from the distinguishable case are shown not to be significantly better than fits resulting from the indistinguishable case using some goodness of fit measures.

[1]  Sren Asmussen,et al.  Phase-Type Distributions and Related Point Processes: Fitting and Recent Advances , 1996 .

[2]  Eugene Seneta,et al.  ESTIMATION THEORY FOR GROWTH AND IMMIGRATION RATES IN A MULTIPLICATIVE PROCESS , 1972 .

[3]  C. O'Cinneide.  On non-uniqueness of representations of phase-type distributions , 1989 .

[4]  Gábor Horváth,et al.  A minimal representation of Markov arrival processes and a moments matching method , 2007, Perform. Evaluation.

[5]  M. Olsson,et al.  Estimation of phase type distributions from censored samples , 1993 .

[6]  S. Asmussen,et al.  Marked point processes as limits of Markovian arrival streams , 1993 .

[7]  Niels Keiding,et al.  Estimation theory for continuous-time branching processes , 1977 .

[8]  Miklós Telek,et al.  Extension of some MAP results to transient MAPs and Markovian binary trees , 2013, Perform. Evaluation.

[9]  Guy Latouche,et al.  The Markovian binary tree applied to demography , 2012, Journal of mathematical biology.

[10]  C. C. Heyde,et al.  Remarks on efficiency in estimation for branching processes , 1975 .

[11]  Peter Buchholz,et al.  An EM-Algorithm for MAP Fitting from Real Traffic Data , 2003, Computer Performance Evaluation / TOOLS.

[12]  G. Sankaranarayanan.  Branching Processes and Its Estimation Theory , 1989 .

[13]  Lothar Breuer,et al.  An EM Algorithm for Batch Markovian Arrival Processes and its Comparison to a Simpler Estimation Procedure , 2002, Ann. Oper. Res..

[14]  P. Holgate,et al.  Matrix Population Models. , 1990 .

[15]  Xiaoming Liu,et al.  Markov Aging Process and Phase-Type Law of Mortality , 2007 .

[16]  New York Dover,et al.  ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM , 1983 .

[17]  Lothar Breuer,et al.  An EM Algorithm for Markovian Arrival Processes Observed at Discrete Times , 2010, MMB/DFT.

[18]  L. M. Pedroso,et al.  Letter to the Editor: Computing multiple integrals involving matrix exponentials , 2008 .

[19]  Ren Asmussen,et al.  Fitting Phase-type Distributions via the EM Algorithm , 1996 .

[20]  Guy Latouche,et al.  Transient features for Markovian binary trees , 2009, VALUETOOLS.

[21]  Lothar Breuer.  Parameter Estimation for a Class of BMAPs , 2000 .

[22]  William J. J. Roberts,et al.  An EM Algorithm for Markov Modulated Markov Processes , 2009, IEEE Transactions on Signal Processing.

[23]  G. McLachlan,et al.  The EM Algorithm and Extensions: Second Edition , 2008 .

[24]  J. Dion.  Estimation of the Variance of a Branching Process , 1975 .

[25]  T. Rydén.  An EM algorithm for estimation in Markov-modulated Poisson processes , 1996 .

[26]  T. Dohi,et al.  An EM Algorithm for a Superposition of Markovian Arrival Processes (Theory and Application of Decision Analysis in Uncertain Situation) , 2008 .

[27]  J. Dion.  Estimation of the mean and the initial probabilities of a branching process , 1974, Journal of Applied Probability.

[28]  C. C. Heyde.  ON ESTIMATING THE VARIANCE OF THE OFFSPRING DISTRIBUTION IN A SIMPLE BRANCHING PROCESS , 1974 .

[29]  Tobias Rydén.  On identifiability and order of continuous-time aggregated Markov chains, Markov-modulated Poisson processes, and phase-type distributions , 1996 .

[30]  J. Gillespie.  The causes of molecular evolution , 1991 .

[31]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[32]  Peter G. Taylor,et al.  Transient Markov arrival processes , 2003 .

[33]  A. Veen,et al.  Estimation of Space–Time Branching Process Models in Seismology Using an EM–Type Algorithm , 2006 .