Least squares estimation in the monotone single index model

DOI10.3150/18-BEJ1090MaRDI QIDQ2325372zbMATH OpenFDO

Authors Fadoua Balabdaoui, Cécile Durot, Hanna Jankowski

Publication date 25 September 2019

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1610.06026, https://projecteuclid.org/euclid.bj/1569398766

zbMATH Keywords

least squaresmaximum likelihoodmonotonesemi-parametricshape-constraintssingle-index model

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) General nonlinear regression (62J02)

Abstract: We study the monotone single index model where a real response variable $Y$ is linked to a $d$-dimensional covariate $X$ through the relationship $E[Y|X]=Ps{i}_0(alph{a}_0^{T}X)$ almost surely. Both the ridge function, $Ps{i}_0$, and the index parameter, $alph{a}_0$, are unknown and the ridge function is assumed to be monotone on its interval of support. Under some regularity conditions, without imposing a particular distribution on the regression error, we show the $n^{-1/3}$ rate of convergence in the $el{l}_2$-norm for the least squares estimator of the bundled function $ps{i}_0({alpha}_0^{T}cdot),$ and also that of the ridge function and the index separately. Furthermore, we show that the least squares estimator is nearly parametrically rate-adaptive to piecewise constant ridge functions.

Review text

The authors study the semi-parametric single index model, where the conditional expectation of the outcome variable is a nonlinear transform of a linear combination of the explanatory variables. The authors additionally assume that this nonlinear transformation is monotone. The regression function can be estimated by the least square estimator and the authors show that this estimator is not unique, but converges in \(L_2\) to the true regression function with rate \(n^{(-1/3)}\) under some assumptions (mainly boundedness of the covariates and some conditions on their density). They also show that the estimator of the coefficients of the linear combination converges with the same rate. The \(n^{(-1/3)}\)-rate is illustrated in a simulation study. An alternative estimator based on splitting the sample into two parts is also discussed. The proof is based on results about the bracketing entropy of the class of regression functions.

Recommendations

• Score estimation in the monotone single-index model
• Estimating a monotonic link function in single-index models
• Adaptivity and optimality of the monotone least-squares estimator
• Rank estimators for monotonic index models
• Score estimation of monotone partially linear index model

Cites work

• An introduction to generalized linear models
• Current status linear regression
• Current status regression.
• Direct estimation of the index coefficient in a single-index model
• Distribution-Free Maximum Likelihood Estimator of the Binary Choice Model
• Elliptically Symmetric Distributions: A Review and Bibliography
• Generalized additive and index models with shape constraints
• High-dimensional estimation with geometric constraints
• scientific article; zbMATH DE number 3822936 (Why is no real title available?)
• scientific article; zbMATH DE number 3390139 (Why is no real title available?)
• Identifiability of single-index models and additive-index models
• Least squares estimation in the monotone single index model
• Non-parametric analysis of a generalized regression model. The maximum rank correlation estimator
• Nonparametric econometrics. Theory and practice.
• On the optimality of the random hyperplane rounding technique for MAX CUT
• Optimal smoothing in single-index models
• Quasi-Likelihood Regression with Multiple Indices and Smooth Link and Variance Functions
• Regression analysis under link violation
• Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
• Structured Signal Recovery From Non-Linear and Heavy-Tailed Measurements
• The Number of Linearly Inducible Orderings of Points in d-Space
• Weak convergence and empirical processes. With applications to statistics

Cited in

(29)

• Shape constraints in economics and operations research
• Limit theory in monotone function estimation
• Nonparametric shape-restricted regression
• Estimating the index of increase via balancing deterministic and random data
• Sample selection models with monotone control functions
• Convergence guarantee for the sparse monotone single index model
• Least squares estimation in the monotone single index model
• Estimating a monotonic link function in single-index models
• A note on least squares sensitivity in single-index model estimation and the benefits of response transformations
• A PERMUTATION-BASED ESTIMATOR FOR MONOTONE INDEX MODELS
• Partial Least Squares Estimator for Single-Index Models
• Score estimation of monotone partially linear index model
• Score estimation in the monotone single-index model
• Profile Least Squares Estimators in the Monotone Single Index Model
• On the population least‐squares criterion in the monotone single index model
• Semiparametric Efficiency in Convexity Constrained Single-Index Model
• Distributional (Single) Index Models
• Isotonic recalibration under a low signal-to-noise ratio
• Behaviour of the monotone single index model under repeated measurements
• Empirical Bayes Mean Estimation With Nonparametric Errors Via Order Statistic Regression on Replicated Data
• Empirical likelihood inference for monotone index model
• A monotone single index model for missing-at-random longitudinal proportion data
• Single-index mixture cure model under monotonicity constraints
• Robust estimators of functional single index models for longitudinal data
• GLS under monotone heteroskedasticity
• Estimation and convergence rates in the distributional single index model
• A monotone single index model for spatially referenced multistate current status data
• Oracle-efficient M-estimation for single-index models with a smooth simultaneous confidence band
• Rates of convergence of the constrained least squares estimator in high-dimensional monotone single-index models

Describes a project that uses

Uses Software

• scar
• dobson

This page was built for publication: Least squares estimation in the monotone single index model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2325372)