ItemConference Paper

Corrected Score Estimation of Regression with Autocorrelation Under Measurement Errors

Title
Corrected Score Estimation of Regression with Autocorrelation Under Measurement Errors
Creator
Thomas, Anna; John, Nimitha; Pereira, Lizan Meryl; Pokhriyal, Himanshu
Description
In regression models with autocorrelated errors, measurement errors in the covariates can lead to biased and inconsistent estimation of the regression coefficients. Measurement error refers to the discrepancy between the observed values of a variable and its true values. It occurs during the data collection process due to various factors such as inaccuracies in measurement instruments, limitations in the measuring process, human errors, or environmental influences. These errors can introduce bias into collected data, impacting the reliability and validity of statistical analyses and model outcomes. Recognizing the importance of time dependencies, our study extends to time series regression models in the presence of measurement error. A score function is the derivative of the log-likelihood function with respect to the parameters. In this paper, a correction for score function in regression with autocorrelated errors is considered to account for the impact of measurement errors on parameter estimation, and it attempts to provide a two-step estimation procedure to resolve the bias caused by both these challenges. Further, the efficiency of these estimates is compared with least square estimates by carrying out a simulation study for finite samples, and we conclude the proposed methodology provides more accurate results. The applicability of the proposed model has been illustrated using the Phillips Curve dataset and it was found that in the presence of measurement error, corrected score estimation gives more accurate estimates than OLS estimates. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
Source
Lecture Notes in Networks and Systems;Volume;1122;pp.179-189
Date
01-01-2025
Publisher
Springer Science and Business Media Deutschland GmbH
Subject
Autocorrelation; Corrected score; Measurement errors
Coverage
Thomas A., Department of Statistics and Data Science, CHRIST (Deemed to be University), Bengaluru, India; John N., Department of Statistics and Data Science, CHRIST (Deemed to be University), Bengaluru, India; Pereira L.M., Department of Statistics and Data Science, CHRIST (Deemed to be University), Bengaluru, India; Pokhriyal H., Department of Statistics, Cochin University of Science and Technology, Cochin, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 23673370; ISBN: 978-981977425-8;
Format
online
Language
English
Type
Conference paper

Citation

Thomas, Anna; John, Nimitha; Pereira, Lizan Meryl; Pokhriyal, Himanshu, “Corrected Score Estimation of Regression with Autocorrelation Under Measurement Errors,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/25636.

Output Formats