Beyond Financial Protection: Empirical Decomposition of Willingness-to-Pay in Health Microinsurance - Nepal 2008-2009 Dataset and Replication Package

This repository contains the complete dataset, analysis code, and replication materials for the manuscript "Beyond Financial Protection: An Empirical Proof of Concept for Decomposing Willingness to Pay in Health Microinsurance" by David M. Dror. The repository provides empirical validation of a three-component framework for decomposing willingness-to-pay (WTP) in health microinsurance contexts. Using household survey data from rural Nepal (N=2,001, collected 2008-2009), the study demonstrates that WTP can be quantitatively decomposed into: (1) Financial Protection, (2) Trust/Preference Alignment, and (3) Social Capital. Key findings: In nascent health microinsurance markets with low institutional trust (Nepal, 2008), Trust/Preference Alignment accounts for 98.2% of the explained variance in WTP, while Financial Protection contributes only 1.8%. Five independent advanced statistical tests (Dominance Analysis, LMG Relative Importance, Quantile Regression, Commonality Analysis, and Bayesian MCMC) converge on this finding, with heterogeneity observed at the lowest WTP quantile (Q0.25) where financial constraints bind. REPOSITORY CONTENTS: RAW DATA (01_Raw_Data/): Original household survey data from 4 districts in Nepal, enrollment and retention data, ethics approvals, and documentation. Sample: N=2,001 rural households. ANALYSIS-READY DATASETS (02_Analysis_Ready_Datasets/): Nepal_Analysis_Ready_20251224.csv (CSV format), Nepal_Analysis_Ready_20251224.dta (Stata format), Nepal_Composite_Scores_20251224 (composite variables in CSV and Stata formats). DATA PROCESSING SCRIPTS (03_Data_Processing_Scripts/): Scripts for cleaning and preparing raw data, variable construction, and validation code. ANALYSIS SCRIPTS (04_Analysis_Scripts/): Complete R code for all analyses reported in manuscript, including Confirmatory Factor Analysis (CFA), OLS regression with bootstrap validation, and five advanced robustness tests: Dominance Analysis, LMG Relative Importance, Quantile Regression, Commonality Analysis, and Bayesian Regression (MCMC). ANALYSIS RESULTS (05_Analysis_Results/): Main results (component weights, bootstrap distributions), tables (descriptive statistics, regression results, robustness tests), figures (conceptual framework, distributions), and sensitivity analyses. REPLICATION PACKAGE (06_Replication_Package/): Quick-start guide for replication, expected output files for verification, step-by-step replication instructions, and verification tools. MANUSCRIPT MATERIALS (07_Manuscript_Materials/): Tables and figures as they appear in the manuscript and supplementary materials. DOCUMENTATION (08_Documentation/): Complete codebooks and variable catalogs, analysis plans and protocols, dataset inventories, and replication checklists. All analyses were conducted using R version 4.5.0. Complete package dependencies documented in scripts. The framework is generalizable across contexts, while component weights are context-specific. Future research should validate in mature microinsurance markets to test theoretical predictions about shifts in weight as institutional trust increases. DATA COLLECTION: Survey conducted by Micro Insurance Academy (MIA), New Delhi, 2008-2009. Stratified random sampling, four districts in rural Nepal. Response rate: 94.2%. All data collected was under applicable ethics rules at the time of collection. MIA closed in 2017; data is historical. REPLICATION: Complete replication possible using provided code and data. Bootstrap random seeds specified for exact reproducibility. Estimated computation time: 2-3 hours for full replication on a standard desktop computer. LICENSE: All materials released under Creative Commons Attribution 4.0 International (CC BY 4.0). Users are free to share and adapt with appropriate attribution. CITATION: Dror, D. M. (2025). Beyond Financial Protection: Empirical Decomposition of Willingness-to-Pay in Health Microinsurance - Nepal 2008-2009 Dataset and Replication Package [Dataset]. Zenodo. https://doi.org/[DOI_WILL_BE_ASSIGNED]