Answers are grounded in this paper and cite their sources.
This is a locked pre-registration protocol for a study of whether ordinal event detectors based on windowed Kendall τb and the mean absolute change DE, applied to uncorrected PurpleAir PM2.5 series, recover pollution episodes defined solely by a collocated regulatory FRM or FEM monitor at least as well as magnitude detectors applied to the same uncorrected series (H1) and to the same series after the published United States-wide EPA PurpleAir correction (H2). The analysis uses the public 24-hour collocated dataset of Barkjohn, Gantt and Clements (2021). Design parameters, including the window, thresholds, episode rule, primary metric and non-inferiority margin, are specified a priori. No episode-level or detector-performance results were computed before registration.
No takes yet. Share an insight, caveat, or question.
Johel Padilla (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: