STREAM-SMR simulation study: sequential Bayesian gamma–Poisson DGLM monitoring of standardized mortality ratios — simulation code and frozen protocol
Year: 2026
Type: software
Abstract: Simulation code and frozen protocol for the preprint "STREAM-SMR: Sequential Bayesian state-space monitoring of standardized mortality ratios — a simulation comparison with risk-adjusted CUSUM and EWMA" (medRxiv, 2026). STREAM-SMR is a conjugate gamma–Poisson dynamic generalized linear model (discount factor δ) for sequential SMR monitoring; the alarm statistic is the posterior exceedance probability P(SMR > 1), with filtered SMR estimates and 95% credible intervals returned at every time step. Contents: data generation and method implementations (STREAM-SMR, risk-adjusted CUSUM, risk-adjusted EWMA), Monte Carlo calibration (1,000 replications; common 5% false-alarm probability over 60 months), evaluation across 3 strata × 6 scenarios, full results CSV and figure-generation code. All random seeds fixed in-source (SEED = 20260807); runs reproduce every number in the manuscript exactly. The related deposit "Navigator Synthetic Demo" (10.5281/zenodo.21819216) is an earlier, distinct log-scale Kalman implementation; this deposit contains the conjugate DGLM formulation described in the manuscript.
Author: Ohno, Kunihisa
Language: English
Subfield: Epidemiology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7203661997
