Estimating Sensitivity of Process Capability Modeled by a Transfer Function

Summary: [This abstract is based on the authors' abstract.] The output variable Y of a process with a number of inputs represented as random variables is assumed to be subject to specification limits. A one-pass Monte Carlo simulation permits the estimation of the sensitivity of the process capability to each parameter of the input variables. The proposed method is more efficient than completing methods and can call attention to parameter changes producing the greatest improvement in capability. The algorithm is outlined and demonstrated on three problems.