Analysis of Two Economic Testing Policies in Discrete Time

Abstract

Two economic testing policies for industrial products are considered in discrete time. Based on the usual total time on test (TTT) method, we develop non-parametric statistical estimation algorithms to determine the optimal testing times, minimizing the expected cost function per unit time and maximizing the expected profit function per unit time, given that the complete sample data of lifetime are available. It is shown numerically in simulation experiments that the resulting estimators in discrete models possess statistical consistency even if the parametric form of lifetime distribution is unknown.

Key Words:

• Cost minimization
• discrete-time model
• non-parametric estimation
• optimal testing policies
• profit maximization
• total time on test statistics

Additional information

Notes on contributors

Tadashi Dohi

Tadashi Dohi received the B.Sc. (Engineering), M.Sc. (Engineering) and Ph.D. (Engineering) from Hiroshima University, Japan, in 1989, 1991 and 1995, respectively. In 1992, he joined the Department of Industrial and Systems Engineering, Hiroshima University, Japan, as an Assistant Professor. Now, he is working as a Full Professor in the Department of Information Engineering, Graduate School of Engineering, Hiroshima University, Japan, since 2002. In 1992 and 2000, he was a Visiting Research Scholar in University of British Columbia, Canada and Duke University, USA, respectively, on leave of absence from Hiroshima University. His research areas include software reliability engineering, dependable computing and performance evaluation. He is a Regular Member of ORSJ, JSIAM, IEICE and IEEE.

Naoya Shibata

Naoya Shibata received the B.Sc. (Engineering) from Hiroshima University, Japan, in 2007. He is now working at Glory Inc., Japan. His research interest in Hiroshima University was statistical quality control and burn-in testing.

Naoto Kaio

Naoto Kaio received the B.Sc. (Engineering), M.Sc. (Engineering) and Ph.D. (Engineering) from Hiroshima University, Japan, in 1976, 1978 and 1982, respectively. He is a Full Professor in the Department of Economic Informatics, Hiroshima Shudo University, Japan. From 1986 to 1987, he was a Visiting Research Scholar in the William E. Simon Graduate School of Business Administration, University of Rochester, USA. His research areas include systems science, operations research, and reliability theory. He is a Regular Member of ORSJ, IEICE, JIMA, IPSJ, JSQC, REAJ and IEEE. Also, Dr. Kaio is serving as Regional Editor for Asia in Journal of Quality in Maintenance Engineering.