arXiv subjects

Maud Delattre

Publications and source records attributed to Maud Delattre.

11 recordsLinked to original sources

arXiv2026

Extending the saemix package for R to fit non Gaussian outcomes

Background and Objectives: Longitudinal data are increasingly collected in clinical trials to provide information on treatment action and disease evolution. The trajectory of continuous biomarkers such as target hormone concentrations or viral loads can then be modelled in relationship to the occurrence of events such as recovery or hospitalisation. Other studies may include repeated measurements of discrete pain scores, number of episodes (count) or occurrence of events (survival). Non-linear mixed-effect models (NLMEM) can handle individual differences in trajectories while modelling the underlying population evolution and are the natural choice for their analysis. The saemix package for R is one of the few open-source solutions and the most flexible. In this paper, we extend it to accommodate a variety of models for non-Gaussian data. Methods: The saemix package estimates parameters through the Stochastic Approximation Expectation-Maximisation (SAEM) algorithm. Within the package, non-Gaussian models are specified by their log-likelihood functions, affording maximal control over model formulation. We extend estimation algorithms as well as exploratory and diagnostic plots for non-Gaussian data. Bootstrap approaches were implemented to estimate parameter uncertainty. To evaluate the performance of saemix, we performed a simulation study based on the toenail dataset, containing repeated binary data from a randomised clinical trial. Results: saemix showed good performance to recover the true parameter values in the simulation study, and was stable across different starting values for the parameters. An algorithm jointly searching for covariate and interindividual variability model was also implemented to build the covariate model and applied to categorical and survival-type data.

stat.ME↗

arXiv2026

A forward-only scheme for online learning of proposal distributions in particle filters

We introduce a new online approach for constructing proposal distributions in particle filters using a forward scheme. Our method progressively incorporates future observations to refine proposals. This is in contrast to backward-scheme algorithms that require access to the entire dataset, such as the iterated auxiliary particle filters (Guarniero et al., 2017, arXiv:1511.06286) and controlled sequential Monte Carlo (Heng et al., 2020, arXiv:1708.08396) which leverage all future observations through backward recursion. In comparison, our forward scheme achieves a gradual improvement of proposals that converges toward the proposal targeted by these backward methods. We show that backward approaches can be numerically unstable even in simple settings. Our forward method, however, offers significantly greater robustness with only a minor trade-off in performance, measured by the variance of the marginal likelihood estimator. Numerical experiments on both simulated and real data illustrate the enhanced stability of our forward approach.

stat.CO↗

arXiv2025

Quasi-likelihood inference for SDE with mixed-effects observed at high frequency

We consider statistical inference for a class of dynamic mixed-effect models described by stochastic differential equations whose drift and diffusion coefficients simultaneously depend on fixed- and random-effect parameters. Assuming that each process is observed at high frequency and the number of individuals goes to infinity, we propose a stepwise inference procedure and prove its theoretical properties. The methodology is based on suitable quasi-likelihood functions by profiling the random effect in the diffusion coefficient at the first stage, and then integrating out the Gaussian random effect in the drift coefficient to obtain the marginal distribution in the second stage, resulting in a fully explicit and computationally convenient method. It is also the strength of the proposed approach that the proposed method allows a wide variety of distributions for the random effects in the diffusion coefficient.

math.ST↗

arXiv2024

Posterior contraction rates in a sparse non-linear mixed-effects model

Recent works have shown an interest in investigating the frequentist asymptotic properties of Bayesian procedures for high-dimensional linear models under sparsity constraints. However, there exists a gap in the literature regarding analogous theoretical findings for non-linear models within the high-dimensional setting. The current study provides a novel contribution, focusing specifically on a non-linear mixed-effects model. In this model, the residual variance is assumed to be known, while the regression vector and the covariance matrix of the random effects are unknown and must be estimated. The prior distribution for the sparse regression coefficients consists of a mixture of a point mass at zero and a Laplace distribution, while an Inverse-Wishart prior is employed for the covariance parameter of the random effects. First, the effective dimension of this model is bounded with high posterior probabilities. Subsequently, we derive posterior contraction rates for both the covariance parameter and the prediction term of the response vector. Finally, under additional assumptions, the posterior distribution is shown to contract for recovery of the unknown sparse regression vector at a rate similar to that established in the linear case.

math.ST↗

arXiv2024

Bayesian high-dimensional covariate selection in non-linear mixed-effects models using the SAEM algorithm

High-dimensional variable selection, with many more covariates than observations, is widely documented in standard regression models, but there are still few tools to address it in non-linear mixed-effects models where data are collected repeatedly on several individuals. In this work, variable selection is approached from a Bayesian perspective and a selection procedure is proposed, combining the use of a spike-and-slab prior and the Stochastic Approximation version of the Expectation Maximisation (SAEM) algorithm. Similarly to Lasso regression, the set of relevant covariates is selected by exploring a grid of values for the penalisation parameter. The SAEM approach is much faster than a classical MCMC (Markov chain Monte Carlo) algorithm and our method shows very good selection performances on simulated data. Its flexibility is demonstrated by implementing it for a variety of nonlinear mixed effects models. The usefulness of the proposed method is illustrated on a problem of genetic markers identification, relevant for genomic-assisted selection in plant breeding.

math.ST↗

arXiv2023

Efficient preconditioned stochastic gradient descent for estimation in latent variable models

Latent variable models are powerful tools for modeling complex phenomena involving in particular partially observed data, unobserved variables or underlying complex unknown structures. Inference is often difficult due to the latent structure of the model. To deal with parameter estimation in the presence of latent variables, well-known efficient methods exist, such as gradient-based and EM-type algorithms, but with practical and theoretical limitations. In this paper, we propose as an alternative for parameter estimation an efficient preconditioned stochastic gradient algorithm. Our method includes a preconditioning step based on a positive definite Fisher information matrix estimate. We prove convergence results for the proposed algorithm under mild assumptions for very general latent variables models. We illustrate through relevant simulations the performance of the proposed methodology in a nonlinear mixed effects model and in a stochastic block model.

math.ST↗

arXiv2023

Estimating Fisher Information Matrix in Latent Variable Models based on the Score Function

The Fisher information matrix (FIM) is a key quantity in statistics as it is required for example for evaluating asymptotic precisions of parameter estimates, for computing test statistics or asymptotic distributions in statistical testing, for evaluating post model selection inference results or optimality criteria in experimental designs. However its exact computation is often not trivial. In particular in many latent variable models, it is intricated due to the presence of unobserved variables. Therefore the observed FIM is usually considered in this context to estimate the FIM. Several methods have been proposed to approximate the observed FIM when it can not be evaluated analytically. Among the most frequently used approaches are Monte-Carlo methods or iterative algorithms derived from the missing information principle. All these methods require to compute second derivatives of the complete data log-likelihood which leads to some disadvantages from a computational point of view. In this paper, we present a new approach to estimate the FIM in latent variable model. The advantage of our method is that only the first derivatives of the log-likelihood is needed, contrary to other approaches based on the observed FIM. Indeed we consider the empirical estimate of the covariance matrix of the score. We prove that this estimate of the Fisher information matrix is unbiased, consistent and asymptotically Gaussian. Moreover we highlight that none of both estimates is better than the other in terms of asymptotic covariance matrix. When the proposed estimate can not be directly analytically evaluated, we present a stochastic approximation estimation algorithm to compute it. This algorithm provides this estimate of the FIM as a by-product of the parameter estimates. We emphasize that the proposed algorithm only requires to compute the first derivatives of the complete data log-likelihood with respect to the parameters. We prove that the estimation algorithm is consistent and asymptotically Gaussian when the number of iterations goes to infinity. We evaluate the finite sample size properties of the proposed estimate and of the observed FIM through simulation studies in linear mixed effects models and mixture models. We also investigate the convergence properties of the estimation algorithm in non linear mixed effects models. We compare the performances of the proposed algorithm to those of other existing methods.

stat.ME↗

arXiv2021

Inference in Gaussian state-space models with mixed effects for multiple epidemic dynamics

The estimation from available data of parameters governing epidemics is a major challenge. In addition to usual issues (data often incomplete and noisy), epidemics of the same nature may be observed in several places or over different periods. The resulting possible inter-epidemic variability is rarely explicitly considered. Here, we propose to tackle multiple epidemics through a unique model incorporating a stochastic representation for each epidemic and to jointly estimate its parameters from noisy and partial observations. By building on a previous work, a Gaussian state-space model is extended to a model with mixed effects on the parameters describing simultaneously several epidemics and their observation process. An appropriate inference method is developed, by coupling the SAEM algorithm with Kalman-type filtering. Its performances are investigated on SIR simulated data. Our method outperforms an inference method separately processing each dataset. An application to SEIR influenza outbreaks in France over several years using incidence data is also carried out, by proposing a new version of the filtering algorithm. Parameter estimations highlight a non-negligible variability between influenza seasons, both in transmission and case reporting. The main contribution of our study is to rigorously and explicitly account for the inter-epidemic variability between multiple outbreaks, both from the viewpoint of modeling and inference.

stat.ME↗

arXiv2021

Inference for partially observed epidemic dynamics guided by Kalman filtering techniques

Despite the recent development of methods dealing with partially observed epidemic dynamics (unobserved model coordinates, discrete and noisy outbreak data), limitations remain in practice, mainly related to the quantity of augmented data and calibration of numerous tuning parameters. In particular, as coordinates of dynamic epidemic models are coupled, the presence of unobserved coordinates leads to a statistically difficult problem. The aim is to propose an easy-to-use and general inference method that is able to tackle these issues. First, using the properties of epidemics in large populations, a two-layer model is constructed. Via a diffusion-based approach, a Gaussian approximation of the epidemic density-dependent Markovian jump process is obtained, representing the state model. The observational model, consisting of noisy observations of certain model coordinates, is approximated by Gaussian distributions. Then, an inference method based on an approximate likelihood using Kalman filtering recursion is developed to estimate parameters of both the state and observational models. The performance of estimators of key model parameters is assessed on simulated data of SIR epidemic dynamics for different scenarios with respect to the population size and the number of observations. This performance is compared with that obtained using the well-known maximum iterated filtering method. Finally, the inference method is applied to a real data set on an influenza outbreak in a British boarding school in 1978.

stat.AP↗

arXiv2020

A review on asymptotic inference in stochastic differential equations with mixed-effects

This paper is a survey of recent contributions on estimation in stochastic differential equations with mixed-effects. These models involve N stochastic differential equations with common drift and diffusion functions but random parameters that allow for differences between processes. The main objective is to estimate the distribution of the random effects and possibly other fixed parameters that are common to the N processes. While many algorithms have been proposed, the theoretical aspects related to estimation have been little studied. This review article focuses only on theoretical inference for stochastic differential equations with mixed-effects. It has so far only been considered in some very specific classes of mixed-effect diffusion models, observed without measurement error, where explicit estimators can be defined. Within this framework, the asymptotic properties of several estimators, either parametric or nonparametric, are discussed. Different schemes of observations are considered according to the approach, associating a large number of individuals with, in most cases, high-frequency observations of the trajectories.

math.ST↗

arXiv2020

An iterative algorithm for joint covariate and random effect selection in mixed effects models

We consider joint selection of fixed and random effects in general mixed-effects models. The interpretation of estimated mixed-effects models is challenging since changing the structure of one set of effects can lead to different choices of important covariates in the model. We propose a stepwise selection algorithm to perform simultaneous selection of the fixed and random effects. It is based on BIC-type criteria whose penalties are adapted to mixed-effects models. The proposed procedure performs model selection in both linear and nonlinear models. It should be used in the low-dimension setting where the number of covariates and the number of random effects are moderate with respect to the total number of observations. The performance of the algorithm is assessed via a simulation study, that includes also a comparative study with alternatives when available in the literature. The use of the method is illustrated in the clinical study of an antibiotic agent kinetics.

stat.ME↗