Maximum likelihood from spatial random effects models via the stochastic approximation expectation maximization algorithm

Abstract

We introduce a class of spatial random effects models that have Markov random fields (MRF) as latent processes. Calculating the maximum likelihood estimates of unknown parameters in SREs is extremely difficult, because the normalizing factors of MRFs and additional integrations from unobserved random effects are computationally prohibitive. We propose a stochastic approximation expectation-maximization (SAEM) algorithm to maximize the likelihood functions of spatial random effects models. The SAEM algorithm integrates recent improvements in stochastic approximation algorithms; it also includes components of the Newton-Raphson algorithm and the expectation-maximization (EM) gradient algorithm. The convergence of the SAEM algorithm is guaranteed under some mild conditions. We apply the SAEM algorithm to three examples that are representative of real-world applications: a state space model, a noisy Ising model, and segmenting magnetic resonance images (MRI) of the human brain. The SAEM algorithm gives satisfactory results in finding the maximum likelihood estimate of spatial random effects models in each of these instances.

Statistical Characterization of the State-of-Health of Lithium-Ion Batteries with Weibull Distribution Function—A Consideration of Random Effect Model in Charge Capacity Decay Estimation

“…Determine the maximum likelihood function value, L, of the battery charge capacity over time using the experimental data and apply Equation (9) that has P Q ij , φ ij , representing the probability density function of the nonlinear battery charge decay [34].…”

Fitting Nonlinear Ordinary Differential Equation Models with Random Effects and Unknown Initial Conditions Using the Stochastic Approximation Expectation–Maximization (SAEM) Algorithm

“…Our interest is in estimating the parameters in $\mathrm{bold-italic\theta }=false({\mathit{\beta }}^{\mathrm{T}},{\mathit{\theta }}_{\mathit{\mu }}^{\mathrm{T}},{\mathit{\theta }}_{\mathbf{\Lambda }}^{\mathrm{T}},{\mathit{\theta }}_{\mathit{\epsilon }}^{\mathrm{T}},{\mathit{\theta }}_{\mathit{b}}^{\mathrm{T}}false)$ via the SAEM algorithm (Zhu & Gu, 2007). Here, θ μ is a p μ × 1 (where p μ ≤ n y ) vector of freed parameters in μ , θ Λ is a p Λ × 1 vector containing all unknown factor loadings in Λ , θ ε is a p ε × 1 vector containing all the unknown parameters in Σ ε , and θ b is a p b × 1 vector containing all the unknown parameters in Σ b .…”

SGPP: spatial Gaussian predictive process models for neuroimaging data

“…Under the Bayesian framework, spatial correlations in imaging data have been modeled through various spatial priors, such as conditional autoregressive (CAR), Gaussian process, or Markov random field (MRF), to spatial component of the signal or the noise process (Groves et al, 2009; Penny et al, 2005; Brezger et al, 2007). Such spatial priors are commonly characterized by several tuning parameters, but it can be computationally prohibitive in calculating these tuning parameters (Zhu et al, 2007). Moreover, it can be restrictive to assume a specific type of correlation structure such as CAR and MRF, since such correlation structure may not accurately approximate the global and local spatial dependence structure of imaging data.…”