tailieunhanh - Use of orthogonal arrays and design of experiment via Taguchi L9 method in probability of default

The main aim is to determine which parameters affect mostly on PD of a firm. The experiment is based on the orthogonal array L9 in which the four parameters are varied at three levels. | Use of orthogonal arrays and design of experiment via Taguchi L9 method in probability of default Accounting 4 2018 113 122 Contents lists available at GrowingScience Accounting homepage ac Use of orthogonal arrays and design of experiment via Taguchi L9 method in probability of default Amir Ahmad Dara and N. Anuradhab Department of Mathematics and Actuarial Science B s Abdur Rahman University Chennai india-48 a bDepartmentof Management Studies B S Abdur Rahman university Chennai india-48 CHRONICLE ABSTRACT Article history The Taguchi s orthogonal array is based on a mathematical model of factorial designs. This Received August 17 2017 paper investigates the effects of four parameters in Probability of Default PD using Black- Received in revised format Scholes model BSM for call option at one period by considering asset value firm s debt September 11 2017 Accepted November 1 2017 expected growth and the volatility . The main aim is to determine which parameters Available online affect mostly on PD of a firm. The experiment is based on the orthogonal array L9 in which November 1 2017 the four parameters are varied at three levels. Finally the ANOM is used to describe the best Keywords combination and ANOVA is implemented to measure the contribution of the given independent PD variables. BSM Taguchi method Regression line ANOM 2017 by the authors licensee Growing Science Canada ANOVA 1. Introduction Design of experiment DOE is a statistical tool developed by Fisher England 1920 s in order to study the effect of multiple variables simultaneously. In his early experiment he wanted to estimate how much sun-light fertilizers water etc. are required to produce the good crop. There are two main approaches to DOE Full Factorial design FFD and the Taguchi s method. The FFD is a set of an experiment whose design consists of more than one factor each with discrete possible level and whose experiment units takes all possible combinations of