This paper presents a broadly useful diagnostic methodology, which engineers and plant managers can use to detect system faults and find the in-situ operating characteristics of boilers when some metered data are either missing or obviously erroneous. The methodology is able to analyse conflicting measurements and utilize analytic redundancy (AR) to deduce the measurement or measurements that are substantially in error without shutting down the plant and recalibrating all instrumentation. The application of the AR technique in evaluating boiler performance is presented through a case study. Copyright (C) 2001 John Wiley & Sons, Ltd.