Open AccessThe Application of Firth Bias Correction in Variance Components Estimation of Clustered Random Intercept Binary Model
Author(s) -
Restu Arisanti,
I Made Sumertajaya,
Khairil Anwar Notodiputro,
_ Indahwati
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1863/1/012028
Subject(s) - firth , variance (accounting) , statistics , binary data , variance components , binary number , random effects model , variation (astronomy) , estimation , generalized linear mixed model , mathematics , econometrics , computer science , engineering , physics , medicine , oceanography , meta analysis , accounting , arithmetic , systems engineering , astrophysics , business , geology
Firth Bias Correction has been discussed in literatures as an alternative method for reducing the bias of variance components in generalized linear mixed model. This paper discusses the application of Firth’s correction in a clustered random intercept binary model in which the penalized quasi likelihood method is utilized. The clustered random intercept binary model is usually applied in clustered data in which the data can be naturally clustered. In this paper the Firth’s correction has been applied to low birth weight data in Indonesia to investigate factors affecting the incidence of the low birth weight as well as its variation within and between clusters.