Skip to main content Skip to main navigation menu Skip to site footer
Articles
Published: 2025-12-23

Business Intelligence Architect/AI and ML Engineer

ISSN 3066-6813

Assessing Normality in Healthcare Expenditure Data: A Shapiro-Wilk Test Approach In Python

Authors

  • Rakesh Mittapally Business Intelligence Architect/AI and ML Engineer

Keywords

Catastrophic health expenditure, Universal health coverage, Health care financing, Health insurance coverage

Abstract

Healthcare financing remains a critical challenge in India, where 58.7% of all medical costs are paid for out of pocket, pushing families towards catastrophic expenses and poverty. This study examines the factors that contribute to catastrophic health costs in Indian households, focusing on aspects such as family structure, socioeconomic status, and insurance coverage, which are less explored in existing studies. Primary data were collected from 1,018 respondents using a structured questionnaire during July-September 2025. Due to the non-normal distribution of the data, non-parametric statistical methods such as Mann-Whitney U tests, Kruskal-Wallis tests, and Spearman's correlation were employed [21].Despite moderate insurance coverage adequacy (mean=2.73), a significant financial burden persists. Out-of-pocket spending on medical expenses (mean=2.71) and families primarily relying on personal savings (mean=3.28) are observed. Lifestyle changes are common (mean=3.45), however, accessing treatment for chronic diseases remains challenging (mean=3.18).Significant gaps exist in India's healthcare financing system. Comprehensive policy interventions, including increased public funding, strengthened insurance schemes, and reduction in drug prices, are essential to achieve universal health coverage and prevent catastrophic expenditures.

Make a Submission

Current Issue

Browse

Published

2025-12-23

How to Cite

Mittapally, R. (2025). Assessing Normality in Healthcare Expenditure Data: A Shapiro-Wilk Test Approach In Python. International Journal of Computer Science and Data Engineering, 2(4), 1-8. https://doi.org/10.55124/csdb.v2i4.272