Salvato in:
Dettagli Bibliografici
Autori principali: He, Peilun, Shang, Han Lin, Zou, Nan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.04138
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914238545526784
author He, Peilun
Shang, Han Lin
Zou, Nan
author_facet He, Peilun
Shang, Han Lin
Zou, Nan
contents This paper proposes distributed estimation procedures for three scalar-on-function regression models: the functional linear model (FLM), the functional non-parametric model (FNPM), and the functional partial linear model (FPLM). The framework addresses two key challenges in functional data analysis, namely the high computational cost of large samples and limitations on sharing raw data across institutions. Monte Carlo simulations show that the distributed estimators substantially reduce computation time while preserving high estimation and prediction accuracy for all three models. When block sizes become too small, the FPLM exhibits overfitting, leading to narrower prediction intervals and reduced empirical coverage probability. An example of an empirical study using the \textit{tecator} dataset further supports these findings.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04138
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On the Distributed Estimation for Scalar-on-Function Regression Models
He, Peilun
Shang, Han Lin
Zou, Nan
Computation
This paper proposes distributed estimation procedures for three scalar-on-function regression models: the functional linear model (FLM), the functional non-parametric model (FNPM), and the functional partial linear model (FPLM). The framework addresses two key challenges in functional data analysis, namely the high computational cost of large samples and limitations on sharing raw data across institutions. Monte Carlo simulations show that the distributed estimators substantially reduce computation time while preserving high estimation and prediction accuracy for all three models. When block sizes become too small, the FPLM exhibits overfitting, leading to narrower prediction intervals and reduced empirical coverage probability. An example of an empirical study using the \textit{tecator} dataset further supports these findings.
title On the Distributed Estimation for Scalar-on-Function Regression Models
topic Computation
url https://arxiv.org/abs/2601.04138