arXiv subjects

Emilie Lebarbier

Publications and source records attributed to Emilie Lebarbier.

12 recordsLinked to original sources

arXiv2025

Classification of multiple segmented profiles, application to the study of the neuronal protein Tau

This work is motivated by an application in neuroscience, in particular by the study of the (dys)functioning of a protein called Tau. The objective is to establish a classification of intensity profiles, according to the presence or absence of the protein and its monomer or dimer proportion. For this, we propose a Gaussian mixture model with a fixed number of clusters whose mean parameters are constrained and shared by the clusters. The inference of this model is done via the classical EM algorithm. The performance of the method is evaluated via simulation studies and an application on real data is done.

stat.ME↗

arXiv2020

A new segmentation method for the homogenisation of GNSS-derived IWV time-series

Homogenization is an important and crucial step to improve the usage of observational data for climate analysis. This work is motivated by the analysis of long series of GNSS Integrated Water Vapour (IWV) data which have not yet been used in this context. This paper proposes a novel segmentation method that integrates a periodic bias and a heterogeneous, monthly varying, variance. The method consists in estimating first the variance using a robust estimator and then estimating the segmentation and periodic bias iteratively. This strategy allows for the use of the dynamic programming algorithm that remains the most efficient exact algorithm to estimate the change-point positions. The statistical performance of the method is assessed through numerical experiments. An application to a real data set of 120 global GNSS stations is presented. The method is implemented in the R package GNSSseg that will be available on the CRAN.

stat.ME↗

arXiv2018

A factor model approach for the joint segmentation with between-series correlation

We consider the segmentation of set of correlated time-series, the correlation being allowed to take an arbitrary form but being the same at each time-position. We show that encoding the dependency in a factor model enables us to use the dynamic programming algorithm for the inference of the breakpoints, which remains one the most efficient algorithm. We propose a model selection procedure to determine both the number of breakpoints and the number of factors. This proposed method is implemented in the FASeg R package, which is available on the CRAN. We demonstrate the performances of our procedure through simulation experiments and an application to geodesic data is presented.

stat.ME↗

arXiv2018

A breakpoint detection in the mean model with heterogeneous variance on fixed time-intervals

This work is motivated by an application for the homogeneization of GNSS-derived IWV (Integrated Water Vapour) series. Indeed, these GPS series are affected by abrupt changes due to equipment changes or environemental effects. The detection and correction of the series from these changes is a crucial step before any use for climate studies. In addition to these abrupt changes, it has been observed in the series a non-stationary of the variability. We propose in this paper a new segmentation model that is a breakpoint detection in the mean model of a Gaussian process with heterogeneous variance on known time-intervals. In this segmentation case, the dynamic programming (DP) algorithm used classically to infer the breakpoints can not be applied anymore. We propose a procedure in two steps: we first estimate robustly the variances and then apply the classical inference by plugging these estimators. The performance of our proposed procedure is assessed through simulation experiments. An application to real GNSS data is presented.

stat.ME↗

arXiv2017

Variational inference for coupled Hidden Markov Models applied to the joint detection of copy number variations

Hidden Markov models provide a natural statistical framework for the detection of the copy number variations (CNV) in genomics. In this paper, we consider a Hidden Markov Model involving several correlated hidden processes at the same time. When dealing with a large number of series, maximum likelihood inference (performed classically using the EM algorithm) becomes intractable. We thus propose an approximate inference algorithm based on a variational approach (VEM). A simulation study is performed to assess the performance of the proposed method and an application to the detection of structural variations in plant genomes is presented.

stat.ME↗

arXiv2017

A Bayesian approach for the segmentation of series corrupted by a functional part

We propose a Bayesian approach to detect multiple change-points in a piecewise-constant signal corrupted by a functional part corresponding to environmental or experimental disturbances. The piecewise constant part (also called segmentation part) is expressed as the product of a lower triangular matrix by a sparse vector. The functional part is a linear combination of functions from a large dictionary. A Stochastic Search Variable Selection approach is used to obtain sparse estimations of the segmentation parameters (the change-points and the means over the segments) and of the functional part. The performance of our proposed method is assessed using simulation experiments. Applications to two real datasets from geodesy and economy fields are also presented.

math.ST↗

arXiv2015

SegCorr: a statistical procedure for the detection of genomic regions of correlated expression

Motivation: Detecting local correlations in expression between neighbor genes along the genome has proved to be an effective strategy to identify possible causes of transcriptional deregulation in cancer. It has been successfully used to illustrate the role of mechanisms such as copy number variation (CNV) or epigenetic alterations as factors that may significantly alter expression in large chromosomic regions (gene silencing or gene activation). Results: The identification of correlated regions requires segmenting the gene expression correlation matrix into regions of homogeneously correlated genes and assessing whether the observed local correlation is significantly higher than the background chromosomal correlation. A unified statistical framework is proposed to achieve these two tasks, where optimal segmentation is efficiently performed using dynamic programming algorithm, and detection of highly correlated regions is then achieved using an exact test procedure. We also propose a simple and efficient procedure to correct the expression signal for mechanisms already known to impact expression correlation. The performance and robustness of the proposed procedure, called SegCorr, are evaluated on simulated data. The procedure is illustrated on cancer data, where the signal is corrected for correlations possibly caused by copy number variation. The correction permitted the detection of regions with high correlations linked to DNA methylation. Availability and implementation: R package SegCorr is available on the CRAN.

stat.ME↗

arXiv2015

Model selection for the segmentation of multiparameter exponential family distributions

We consider the segmentation problem of univariate distributions from the exponential family with multiple parameters. In segmentation, the choice of the number of segments remains a difficult issue due to the discrete nature of the change-points. In this general exponential family distribution framework, we propose a penalized log-likelihood estimator where the penalty is inspired by papers of L. Birgé and P. Massart. The resulting estimator is proved to satisfy an oracle inequality. We then further study the particular case of categorical variables by comparing the values of the key constants when derived from the specification of our general approach and when obtained by working directly with the characteristics of this distribution. Finally, a simulation study is conducted to assess the performance of our criterion for the exponential distribution, and an application on real data modelled by the categorical distribution is provided.

math.ST↗

arXiv2014

Segmentation of multiple series using a Lasso strategy

We propose a new semi-parametric approach to the joint segmentation of multiple series corrupted by a functional part. This problem appears in particular in geodesy where GPS permanent station coordinate series are affected by undocumented artificial abrupt changes and additionally show prominent periodic variations. Detecting and estimating them are crucial, since those series are used to determine averaged reference coordinates in geosciences and to infer small tectonic motions induced by climate change. We propose an iterative procedure based on Dynamic Programming for the segmentation part and Lasso estimators for the functional part. Our Lasso procedure, based on the dictionary approach, allows us to both estimate smooth functions and functions with local irregularity, which permits more flexibility than previous proposed methods. This yields to a better estimation of the bias part and improvements in the segmentation. The performance of our method is assessed using simulated and real data. In particular, we apply our method to data from four GPS stations in Yarragadee, Australia. Our estimation procedure results to be a reliable tool to assess series in terms of change detection and periodic variations estimation giving an interpretable estimation of the functional part of the model in terms of known functions.

stat.ME↗

arXiv2013

Segmentor3IsBack: an R package for the fast and exact segmentation of Seq-data

Genome annotation is an important issue in biology which has long been addressed with gene prediction methods and manual experiments requiring biological expertise. The expanding Next Generation Sequencing technologies and their enhanced precision allow a new approach to the domain: the segmentation of RNA-Seq data to determine gene boundaries. Because of its almost linear complexity, we propose to use the Pruned Dynamic Programming Algorithm, which performances had been acknowledged for CGH arrays, for Seq-experiment outputs. This requires the adaptation of the algorithm to the negative binomial distribution with which we model the data. We show that if the dispersion in the signal is known, the PDP algorithm can be used and we provide an estimator for this dispersion. We then propose to estimate the number of segments, which can be associated to coding or non-coding regions of the genome, using an oracle penalty. We illustrate the results of our approach on a real data-set and show its good performance. Our algorithm is available as an R package on the CRAN repository.

stat.CO↗

arXiv2013

Segmentation of the Poisson and negative binomial rate models: a penalized estimator

We consider the segmentation problem of Poisson and negative binomial (i.e. overdispersed Poisson) rate distributions. In segmentation, an important issue remains the choice of the number of segments. To this end, we propose a penalized log-likelihood estimator where the penalty function is constructed in a non-asymptotic context following the works of L. Birgé and P. Massart. The resulting estimator is proved to satisfy an oracle inequality. The performances of our criterion is assessed using simulated and real datasets in the RNA-seq data analysis context.

math.ST↗

arXiv2010

Exact posterior distributions over the segmentation space and model selection for multiple change-point detection problems

In segmentation problems, inference on change-point position and model selection are two difficult issues due to the discrete nature of change-points. In a Bayesian context, we derive exact, non-asymptotic, explicit and tractable formulae for the posterior distribution of variables such as the number of change-points or their positions. We also derive a new selection criterion that accounts for the reliability of the results. All these results are based on an efficient strategy to explore the whole segmentation space, which is very large. We illustrate our methodology on both simulated data and a comparative genomic hybridisation profile.

stat.CO↗