Open AccessStochastic Programming for Optimal Decision Making through Scaling Measures
Author(s) -
Tirupathi Rao Padi,
Kiran Kumar Paidipati,
C. Umashankar
Publication year - 2013
Publication title -
international journal of management and information technology
Language(s) - English
Resource type - Journals
ISSN - 2278-5612
DOI - 10.24297/ijmit.v6i1.748
Subject(s) - stochastic programming , bivariate analysis , computer science , mathematical optimization , goal programming , sensitivity (control systems) , scaling , stochastic optimization , optimal decision , likert scale , software , mathematics , decision tree , machine learning , statistics , engineering , programming language , geometry , electronic engineering
In this paper, a stochastic programming problem for scaling measures similar to Likert's format is developed. The objective function is formulated with a view of maximizing the expected decision making score. The constraints are designed with minimum expected decision score and with minimum targeted precision. The very objective of this problem is to find the decision variables of finding the optimal handled number of assignments by a manager in different categories. While developing the programming problem, the statistical measures such as mean and variances of decision scores are derived from the developed stochastic models based on bivariate stochastic processes as a result of spread sheet experimentation. Sensitivity analysis is carried out with the numerical outputs after solving the derived NLPP using a mathematical software LINGO.