Comparison of variance estimation methods in semiparametric accelerated failure time models for multivariate failure time data

Kyuhyun Kim; Jungyeol Ko; Sangwook Kang

doi:10.1007/s42081-021-00126-y

Comparison of variance estimation methods in semiparametric accelerated failure time models for multivariate failure time data

Kyuhyun Kim, Jungyeol Ko, Sangwook Kang

Department of Applied Statistics

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

The semiparametric accelerated failure time (AFT) model is a log-linear model of failure times with an unspecified random error term. The rank-based estimator has been a popular estimation method for regression parameters in this model. An induced smoothing method has reduced computational complexity and instability in the original non-smooth rank-based estimator. This paper briefly reviews and compares the recently proposed computationally efficient variance estimation methods for the semiparametric AFT models in multivariate failure times settings. Comparisons are made via extensive simulation experiments. Based on our findings, we may recommend using ‘Diff-Boot’ and ‘Diff-Closed’ methods with a one-step iteration. These variance estimators are then illustrated with the well-known Diabetic retinopathy study data.

Original language	English
Pages (from-to)	1179-1202
Number of pages	24
Journal	Japanese Journal of Statistics and Data Science
Volume	4
Issue number	2
DOIs	https://doi.org/10.1007/s42081-021-00126-y
Publication status	Published - 2021 Dec

Bibliographical note

Funding Information:
This work was partly supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1A2C1A0101313911) and the Graduate School of YONSEI University Research Scholarship Grants in 2020.

Publisher Copyright:
© 2021, Japanese Federation of Statistical Science Associations.

All Science Journal Classification (ASJC) codes

Statistics and Probability
Computational Theory and Mathematics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/s42081-021-00126-y

Cite this

@article{e30180a60f3641b5b39b244bc5f58361,

title = "Comparison of variance estimation methods in semiparametric accelerated failure time models for multivariate failure time data",

abstract = "The semiparametric accelerated failure time (AFT) model is a log-linear model of failure times with an unspecified random error term. The rank-based estimator has been a popular estimation method for regression parameters in this model. An induced smoothing method has reduced computational complexity and instability in the original non-smooth rank-based estimator. This paper briefly reviews and compares the recently proposed computationally efficient variance estimation methods for the semiparametric AFT models in multivariate failure times settings. Comparisons are made via extensive simulation experiments. Based on our findings, we may recommend using {\textquoteleft}Diff-Boot{\textquoteright} and {\textquoteleft}Diff-Closed{\textquoteright} methods with a one-step iteration. These variance estimators are then illustrated with the well-known Diabetic retinopathy study data.",

author = "Kyuhyun Kim and Jungyeol Ko and Sangwook Kang",

note = "Funding Information: This work was partly supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1A2C1A0101313911) and the Graduate School of YONSEI University Research Scholarship Grants in 2020. Publisher Copyright: {\textcopyright} 2021, Japanese Federation of Statistical Science Associations.",

year = "2021",

month = dec,

doi = "10.1007/s42081-021-00126-y",

language = "English",

volume = "4",

pages = "1179--1202",

journal = "Japanese Journal of Statistics and Data Science",

issn = "2520-8764",

publisher = "Springer Science and Business Media B.V.",

number = "2",

}

TY - JOUR

T1 - Comparison of variance estimation methods in semiparametric accelerated failure time models for multivariate failure time data

AU - Kim, Kyuhyun

AU - Ko, Jungyeol

AU - Kang, Sangwook

N1 - Funding Information: This work was partly supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020R1A2C1A0101313911) and the Graduate School of YONSEI University Research Scholarship Grants in 2020. Publisher Copyright: © 2021, Japanese Federation of Statistical Science Associations.

PY - 2021/12

Y1 - 2021/12

N2 - The semiparametric accelerated failure time (AFT) model is a log-linear model of failure times with an unspecified random error term. The rank-based estimator has been a popular estimation method for regression parameters in this model. An induced smoothing method has reduced computational complexity and instability in the original non-smooth rank-based estimator. This paper briefly reviews and compares the recently proposed computationally efficient variance estimation methods for the semiparametric AFT models in multivariate failure times settings. Comparisons are made via extensive simulation experiments. Based on our findings, we may recommend using ‘Diff-Boot’ and ‘Diff-Closed’ methods with a one-step iteration. These variance estimators are then illustrated with the well-known Diabetic retinopathy study data.

AB - The semiparametric accelerated failure time (AFT) model is a log-linear model of failure times with an unspecified random error term. The rank-based estimator has been a popular estimation method for regression parameters in this model. An induced smoothing method has reduced computational complexity and instability in the original non-smooth rank-based estimator. This paper briefly reviews and compares the recently proposed computationally efficient variance estimation methods for the semiparametric AFT models in multivariate failure times settings. Comparisons are made via extensive simulation experiments. Based on our findings, we may recommend using ‘Diff-Boot’ and ‘Diff-Closed’ methods with a one-step iteration. These variance estimators are then illustrated with the well-known Diabetic retinopathy study data.

UR - http://www.scopus.com/inward/record.url?scp=85117242642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85117242642&partnerID=8YFLogxK

U2 - 10.1007/s42081-021-00126-y

DO - 10.1007/s42081-021-00126-y

M3 - Article

AN - SCOPUS:85117242642

SN - 2520-8764

VL - 4

SP - 1179

EP - 1202

JO - Japanese Journal of Statistics and Data Science

JF - Japanese Journal of Statistics and Data Science

IS - 2

ER -

Comparison of variance estimation methods in semiparametric accelerated failure time models for multivariate failure time data

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this