R Code and Data for the Repeated Acute Exposure (RAE) Design

This repository contains the supplementary material required to reproduce the statistical analysis and methodological validation presented in the manuscript: 'Beyond Time-Series Counts: Reframing the short-term association between exposure to air pollution and mortality using the novel Repeated Acute Exposure (RAE) design'. This manuscript has been submitted to the International Journal of Environmental Health Research. The provided resources focus on the application of the Repeated Acute Exposure (RAE) design using a penalised Cox model with time-varying coefficients to estimate the short-term effects of air pollution on mortality. Contents: valencia.csv: A longitudinal dataset containing daily records of air pollution (PM10), mortality counts, and meteorological confounders (mean temperature and relative humidity) for Valencia, Spain. Rscript: The complete R script used for: Data preprocessing and long-format transformation. Fitting the final penalised Cox model with time-varying coefficients to account for the dynamic risk intensity of PM10 across the lag window. Testing the Proportional Hazards (PH) assumption via Schoenfeld residuals. Usage: Users are encouraged to run the script in R (version 4.0 or higher) using the survival package. Data Citation: The valencia.csv dataset is sourced from: Iñíguez, C., Ballester, F., & Tobías, A. (2022). Data supporting the short-term health effects of particles and mortality in 48 Spanish cities. Data in Brief, 42, 108144. DOI: 10.1016/j.dib.2022.108144