NONLINEAR CONTROL CHARTS FOR JUMP DETECTION

This paper presents a new class of nonlinear control charts which resp ond quickly to small shifts and jump patterns in tme series. The under lying disturbance models for the control charts are nonlinear extensio ns of the IMA(1,1) model. The Kalman filtering algorithm generates Bay esian estimates of the process level for the control chart plotting. T he single-parameter chart is identical to the EWMA, while the two- and three-parameter designs are much more effective in detecting small sh ifts mixed with local trends. The nonlinear control charting scheme is also capable of detecting a mean shift in independent observation.