Impact of COVID-19 Pandemic Years on Pediatric Mycoplasma Pneumoniae Pneumonia Symptoms: A Population-based Cohort Study Using a Difference-in-Differences Design and Mediation Analysis of IgM

This repository contains the complete replication package for the study examining the impact of COVID-19 pandemic years on pediatric Mycoplasma pneumoniae pneumonia symptoms, with a focus on the mediating role of IgM. The analysis implements three main econometric methods: 1. Propensity Score Matching (PSM) using logistic regression with 1:1 nearest-neighbor matching to balance covariates between treatment and control groups. 2. Baseline Difference-in-Differences (DID) estimation to identify the causal effect of the pandemic on symptom outcomes. 3. Mediation DID analysis to decompose the total effect into direct and indirect pathways through IgM. The replication package includes: - A Jupyter Notebook (code.ipynb) with all analysis code - Anonymized patient-level data (data/病例.xlsx) All results presented in the associated paper can be fully reproduced using this package. The code is written in Python 3.8+ and requires standard data science libraries including pandas, numpy, scikit-learn, statsmodels, and matplotlib. Please cite this work as: Ding, Keyi (2026). Impact of COVID-19 Pandemic Years on Pediatric Mycoplasma Pneumoniae Pneumonia Symptoms: A Population-based Cohort Study Using a Difference-in-Differences Design and Mediation Analysis of IgM. Zenodo.