Monotonic Change Point Estimation in the Parameters of Polynomial Profile Model

Abstract

In this paper, a maximum likelihood estimator is developed to estimate isotonic change point in the parameters of a polynomial profile in phase II. In addition, performance of the proposed estimator is compared to the performance of the step change point estimator, under increasing change types using simulation study. Accuracy and the precision of the estimators are considered as the performance measures in this paper. Simulation results show that the proposed estimator has an acceptable performance in terms of the accuracy and precision of the estimations. The proposed estimator also does not require any awareness about the change type, and its only assumption is that changes occur in an increasing manner. This is the advantage of the proposed estimator over the step change point estimator.