Estimating the number of block boundaries from diagonal blockwise matrices without penalization

DOI10.1111/SJOS.12266MaRDI QIDQ5738841zbMATH OpenOpenAlexFDO

Authors Vincent Brault, M. Delattre, Tristan Mary-Huard, Emilie Lebarbier, Céline Lévy-Leduc

Publication date 13 June 2017

Published in Scandinavian Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1506.03198

zbMATH Keywords

Hi-C datamodel selectionsegmentation

Mathematics Subject Classification ID

Density estimation (62G07) Statistical block designs (62K10) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Abstract: In computational biology, numerous recent studies have been dedicated to the analysis of the chromatin structure within the cell by two-dimensional segmentation methods. Motivated by this application, we consider the problem of retrieving the diagonal blocks in a matrix of observations. The theoretical properties of the least-squares estimators of both the boundaries and the number of blocks proposed by L'evy-Leduc et al. [2014] are investigated. More precisely, the contribution of the paper is to establish the consistency of these estimators. A surprising consequence of our results is that, contrary to the onedimensional case, a penalty is not needed for retrieving the true number of diagonal blocks. Finally, the results are illustrated on synthetic data.

Recommendations

• Efficient block boundaries estimation in block-wise constant matrices: an application to HiC data
• Nonparametric multiple change-point estimation for analyzing large Hi-C data matrices
• A model selection approach for multiple sequence segmentation and dimensionality reduction
• Local inference by penalization method for biclustering model
• Boundary Estimation

Cites work

• Consistencies and rates of convergence of jump-penalized least squares estimators
• Detecting multiple change-points in the mean of Gaussian process by model selection
• scientific article; zbMATH DE number 1688529 (Why is no real title available?)
• scientific article; zbMATH DE number 4169866 (Why is no real title available?)
• scientific article; zbMATH DE number 6303356 (Why is no real title available?)
• Least-squares estimation of an unknown number of shifts in a time series
• On the approximation of curves by line segments using dynamic programming
• Using penalized contrasts for the change-point problem

Cited in

(4)

• Nonparametric multiple change-point estimation for analyzing large Hi-C data matrices
• Efficient block boundaries estimation in block-wise constant matrices: an application to HiC data
• scientific article; zbMATH DE number 2208582 (Why is no real title available?)
• Covariance Matrix Estimation for High-Throughput Biomedical Data with Interconnected Communities

This page was built for publication: Estimating the number of block boundaries from diagonal blockwise matrices without penalization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5738841)