The paper describes a time series model that permits the estimation of the statistical properties of pounds of SO2 per million Btu in stack emissions. It uses measured values for this quantity provided by coal sampling and analysis (CSA), by a continuous emissions monitor (CEM), or by a continuous bubbler (EPA Reference Method 6B). The model fits exceptionally well, which is especially surprising because it is so simple and has been applied to so many different sources. It accounts only for autocorrelation between measurements, leaving out any dependence on weather; season of year; temperature, specifications, and efficiency of the boiler; load; blending practices; spot coal versus contract coal supplies; etc. As such, it provides a first generation, universally applicable model.