ESTIMATING THE NUMBER OF ERRORS IN A SYSTEM USING A MARTINGALE APPROACH

A new, efficient procedure estimates the number of errors in a system. A known number of seeded errors are inserted into a system. The failu re intensities of the seeded and real errors are allowed to be differe nt and time dependent. When an error is detected during the test, it i s removed from the system. The testing process is observed for a fixed amount of time tau. Martingale theory is used to derive a class of es timators for the number of seeded errors in a continuous time setting. Some of the estimators and their associated standard deviations have explicit expressions. An optimal estimator among the class of estimato rs is obtained. A simulation study assesses the performance of the pro posed estimators.