Modeling persistent trends in distributions

DOI10.1080/01621459.2017.1341412zbMATH Open1402.62074arXiv1511.04486OpenAlexW3106439869WikidataQ62488892 ScholiaQ62488892MaRDI QIDQ4559709FDOQ4559709

Authors: Jonas Müller, David K. Gifford, Tommi S. Jaakkola 

Publication date: 4 December 2018

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Abstract: We present a nonparametric framework to model a short sequence of probability distributions that vary both due to underlying effects of sequential progression and confounding noise. To distinguish between these two types of variation and estimate the sequential-progression effects, our approach leverages an assumption that these effects follow a persistent trend. This work is motivated by the recent rise of single-cell RNA-sequencing experiments over a brief time course, which aim to identify genes relevant to the progression of a particular biological process across diverse cell populations. While classical statistical tools focus on scalar-response regression or order-agnostic differences between distributions, it is desirable in this setting to consider both the full distributions as well as the structure imposed by their ordering. We introduce a new regression model for ordinal covariates where responses are univariate distributions and the underlying relationship reflects consistent changes in the distributions over increasing levels of the covariate. This concept is formalized as a "trend" in distributions, which we define as an evolution that is linear under the Wasserstein metric. Implemented via a fast alternating projections algorithm, our method exhibits numerous strengths in simulations and analyses of single-cell gene expression data.

Full work available at URL: https://arxiv.org/abs/1511.04486

Recommendations

• Wasserstein gradients for the temporal evolution of probability distributions
• A compositional model to assess expression changes from single-cell RNA-seq data
• Distributional (Single) Index Models
• Contrastive latent variable modeling with application to case-control sequencing experiments
• Modelling of repeated ordered measurements by isotonic sequential regression

zbMATH Keywords

quantile regressionWasserstein distancepool adjacent violators algorithmbatch effectsingle cell RNA-seq

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites Work

• Permutation tests. A practical guide to resampling methods for testing hypotheses
• Noncrossing quantile regression curve estimation
• Resampling-based multiple testing for microarray data analysis (With comments)
• Quantile Estimation in Dependent Sequences
• Comparing the continuous representation of time-series expression profiles to identify differentially expressed genes
• Estimation of conditional densities and sensitivity measures in nonlinear dynamical systems
• The bootstrap: To smooth or not to smooth?
• Methods for Estimating a Conditional Distribution Function
• Title not available (Why is that?)
• Correctness of Kruskal's algorithms for monotone regression with ties
• Small-Sample Quantile Estimators in a Large Nonparametric Model
• Title not available (Why is that?)

Cited In (1)

• Dynamic Trends in Distributions

Uses Software

• RUVseq
• ConsensusPathDB

This page was built for publication: Modeling persistent trends in distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4559709)