Advanced

Likelihood-free stochastic approximation EM for inference in complex models

Picchini, Umberto LU (2019) In Communications in Statistics: Simulation and Computation 48(3). p.861-881
Abstract
A maximum likelihood methodology for the parameters of models with an intractable likelihood is introduced. We produce a likelihood-free version of the stochastic approximation expectation-maximization (SAEM) algorithm to maximize the likelihood function of model parameters. While SAEM is best suited for models having a tractable "complete likelihood" function, its application to moderately complex models is a difficult or even impossible task. We show how to construct a likelihood-free version of SAEM by using the "synthetic likelihood" paradigm. Our method is completely plug-and-play, requires almost no tuning and can be applied to both static and dynamic models. Four simulation studies illustrate the method, including a stochastic... (More)
A maximum likelihood methodology for the parameters of models with an intractable likelihood is introduced. We produce a likelihood-free version of the stochastic approximation expectation-maximization (SAEM) algorithm to maximize the likelihood function of model parameters. While SAEM is best suited for models having a tractable "complete likelihood" function, its application to moderately complex models is a difficult or even impossible task. We show how to construct a likelihood-free version of SAEM by using the "synthetic likelihood" paradigm. Our method is completely plug-and-play, requires almost no tuning and can be applied to both static and dynamic models. Four simulation studies illustrate the method, including a stochastic differential equation model, a stochastic Lotka-Volterra model and data from g-and-k distributions. MATLAB code is available as supplementary material. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
maximum likelihood, SAEM, sequential Monte Carlo, synthetic likelihood;, state space model, Stochastic differential equation
in
Communications in Statistics: Simulation and Computation
volume
48
issue
3
pages
26 pages
publisher
Taylor & Francis
external identifiers
  • scopus:85041005919
ISSN
0361-0918
DOI
10.1080/03610918.2017.1401082
project
Stochastic modelling of protein folding and likelihood-free statistical inference methods
language
English
LU publication?
yes
id
b4e72775-a092-4b85-9ccc-cc3694998fab
alternative location
https://arxiv.org/abs/1609.03508
date added to LUP
2016-09-13 10:51:54
date last changed
2020-01-13 00:24:16
@article{b4e72775-a092-4b85-9ccc-cc3694998fab,
  abstract     = {A maximum likelihood methodology for the parameters of models with an intractable likelihood is introduced. We produce a likelihood-free version of the stochastic approximation expectation-maximization (SAEM) algorithm to maximize the likelihood function of model parameters. While SAEM is best suited for models having a tractable "complete likelihood" function, its application to moderately complex models is a difficult or even impossible task. We show how to construct a likelihood-free version of SAEM by using the "synthetic likelihood" paradigm. Our method is completely plug-and-play, requires almost no tuning and can be applied to both static and dynamic models. Four simulation studies illustrate the method, including a stochastic differential equation model, a stochastic Lotka-Volterra model and data from g-and-k distributions. MATLAB code is available as supplementary material.  },
  author       = {Picchini, Umberto},
  issn         = {0361-0918},
  language     = {eng},
  number       = {3},
  pages        = {861--881},
  publisher    = {Taylor & Francis},
  series       = {Communications in Statistics: Simulation and Computation},
  title        = {Likelihood-free stochastic approximation EM for inference in complex models},
  url          = {http://dx.doi.org/10.1080/03610918.2017.1401082},
  doi          = {10.1080/03610918.2017.1401082},
  volume       = {48},
  year         = {2019},
}