The reliability of an environmental epidemiology meta-analysis, a case study

TL;DR

This paper critically examines the reliability of a meta-analysis on air quality and heart attacks, revealing significant issues like p-hacking and uncorrected multiple testing that undermine its validity.

Contribution

It introduces a method to evaluate the statistical reliability of base studies in meta-analyses, highlighting potential biases and heterogeneity.

Findings

Base studies exhibit massive multiple testing without adjustments.

Evidence of p-hacking and study heterogeneity.

Meta-analysis and base studies are unreliable due to these issues.

Abstract

Summary Background Claims made in science papers are coming under increased scrutiny with many claims failing to replicate. Meta-analysis studies that use unreliable observational studies should be in question. We examine the reliability of the base studies used in an air quality/heart attack meta-analysis and the resulting meta-analysis. Methods A meta-analysis study that includes 14 observational air quality/heart attack studies is examined for its statistical reliability. We use simple counting to evaluate the reliability of the base papers and a p-value plot of the p-values from the base studies to examine study heterogeneity. Findings We find that the based papers have massive multiple testing and multiple modeling with no statistical adjustments. Statistics coming from the base papers are not guaranteed to be unbiased, a requirement for a valid meta-analysis. There is study heterogeneity for the base papers with strong evidence for so called p-hacking. Interpretation We make two observations: there are many claims at issue in each of the 14 base studies so uncorrected multiple testing is a serious issue. We find the base papers and the resulting meta-analysis are unreliable.