A Comparative Assessment of Parametric and Semi- parametric Regression Models for Functional Difficulties among Children Aged 5–17 Years in Bangladesh

Background Functional difficulties among children are becoming a major public health challenge in Bangladesh. It is affecting children’s development, education, and daily life. Understanding the determinants of these difficulties is required to develop effective strategies to reduce this burden. Objective The present study aimed to identify the key socio-demographic determinants of child functional difficulties among children aged 5–17 years in Bangladesh and further compare the performance of the semi-parametric transition model with the parametric count regression models. Methods Analyzing data from the 2019 MICS (37,579 children aged 5–17), this study examined child functional difficulties derived from 13 domains. Key variables were identified using one-way ANOVA. After fitting multiple classical count regression models (Poisson, Negative Binomial, discrete Lindley, and discrete Weibull), the discrete Weibull model was selected based on AIC and dispersion criteria. Its performance was then evaluated against the semi-parametric transition model. Finally, transition models were used to analyze the data and determine critical risk factors of child functional difficulties. Results Functional difficulties were less common among children aged 5–9 years. Maternal functional difficulty was significantly associated with functional difficulties in children (incidence rate ratio [IRR]: 2.31, 95% confidence interval [CI]: 2.09–2.57). In addition, administrative division, household wealth index, children’s educational status, and the sex of the household head were identified as significant determinants of functional difficulties among children. Conclusion The semi-parametric transition model provides robust estimates compared to the best-performing parametric model without requiring distributional assumptions, making it a reliable alternative to parametric models. The findings of this study can help policymakers to develop evidence-based policies to reduce the burden of child functional difficulties in Bangladesh.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-19
DOI
https://doi.org/10.21203/rs.3.rs-11719861/v1
Primary Topic
Statistical Methods and Bayesian Inference
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

A Comparative Assessment of Parametric and Semi- parametric Regression Models for Functional Difficulties among Children Aged 5–17 Years in Bangladesh

Sourav Roy, Anamul Haque Sajib, Sahera Akter, Jafar Ahmed Khan
Research Square
Statistical Methods and Bayesian Inference
preprint

A Comparative Assessment of Parametric and Semi- parametric Regression Models for Functional Difficulties among Children Aged 5–17 Years in Bangladesh

Sourav Roy, Anamul Haque Sajib, Sahera Akter, Jafar Ahmed Khan
preprint en

Abstract

Background Functional difficulties among children are becoming a major public health challenge in Bangladesh. It is affecting children’s development, education, and daily life. Understanding the determinants of these difficulties is required to develop effective strategies to reduce this burden. Objective The present study aimed to identify the key socio-demographic determinants of child functional difficulties among children aged 5–17 years in Bangladesh and further compare the performance of the semi-parametric transition model with the parametric count regression models. Methods Analyzing data from the 2019 MICS (37,579 children aged 5–17), this study examined child functional difficulties derived from 13 domains. Key variables were identified using one-way ANOVA. After fitting multiple classical count regression models (Poisson, Negative Binomial, discrete Lindley, and discrete Weibull), the discrete Weibull model was selected based on AIC and dispersion criteria. Its performance was then evaluated against the semi-parametric transition model. Finally, transition models were used to analyze the data and determine critical risk factors of child functional difficulties. Results Functional difficulties were less common among children aged 5–9 years. Maternal functional difficulty was significantly associated with functional difficulties in children (incidence rate ratio [IRR]: 2.31, 95% confidence interval [CI]: 2.09–2.57). In addition, administrative division, household wealth index, children’s educational status, and the sex of the household head were identified as significant determinants of functional difficulties among children. Conclusion The semi-parametric transition model provides robust estimates compared to the best-performing parametric model without requiring distributional assumptions, making it a reliable alternative to parametric models. The findings of this study can help policymakers to develop evidence-based policies to reduce the burden of child functional difficulties in Bangladesh.

Research Square
University of Dhaka (BD)
Statistical Methods and Bayesian Inference
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon