Generalized Linear Models with 1-Bit Measurements: Asymptotics of the Maximum Likelihood Estimator

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shah, Jaimin, Cardone, Martina, Rush, Cynthia, Dytso, Alex
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912223982518272
author Shah, Jaimin
Cardone, Martina
Rush, Cynthia
Dytso, Alex
author_facet Shah, Jaimin
Cardone, Martina
Rush, Cynthia
Dytso, Alex
contents This work establishes regularity conditions for consistency and asymptotic normality of the multiple parameter maximum likelihood estimator(MLE) from censored data, where the censoring mechanism is in the form of $1$-bit measurements. The underlying distribution of the uncensored data is assumed to belong to the exponential family, with natural parameters expressed as a linear combination of the predictors, known as generalized linear model (GLM). As part of the analysis, the Fisher information matrix is also derived for both censored and uncensored data, which helps to quantify the impact of censoring and assess the performance of the MLE. The choice of GLM allows one to consider a variety of practical examples where 1-bit estimation is of interest. In particular, it is shown how the derived results can be used to analyze two practically relevant scenarios: the Gaussian model with both unknown mean and variance, and the Poisson model with an unknown mean.
format Preprint
id arxiv_https___arxiv_org_abs_2501_04937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalized Linear Models with 1-Bit Measurements: Asymptotics of the Maximum Likelihood Estimator
Shah, Jaimin
Cardone, Martina
Rush, Cynthia
Dytso, Alex
Statistics Theory
Systems and Control
Audio and Speech Processing
Signal Processing
This work establishes regularity conditions for consistency and asymptotic normality of the multiple parameter maximum likelihood estimator(MLE) from censored data, where the censoring mechanism is in the form of $1$-bit measurements. The underlying distribution of the uncensored data is assumed to belong to the exponential family, with natural parameters expressed as a linear combination of the predictors, known as generalized linear model (GLM). As part of the analysis, the Fisher information matrix is also derived for both censored and uncensored data, which helps to quantify the impact of censoring and assess the performance of the MLE. The choice of GLM allows one to consider a variety of practical examples where 1-bit estimation is of interest. In particular, it is shown how the derived results can be used to analyze two practically relevant scenarios: the Gaussian model with both unknown mean and variance, and the Poisson model with an unknown mean.
title Generalized Linear Models with 1-Bit Measurements: Asymptotics of the Maximum Likelihood Estimator
topic Statistics Theory
Systems and Control
Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2501.04937