Multiple Regression with Dependent Dummy Variable (MRDDV) Model as an Ad-hoc Risk Management System (ARMS)

N.-J. Park. N. Park, and K.M. George (USA)

Keywords

ARMS, MRDDV, stepwise, Bernoulli, OLS, 2 R .

Abstract

An ad hoc risk management system (ARMS) is a frame work composed of statistical model and surveyed field data for forecasting. The primary concern in ARMS is dynamically forecasting or predicting a risky state. An 'Ad-hoc risk Management System (ARMS) using Multiple Regression with Scaled Dummy Variable (MRSDV) model' has been recently proposed for this purpose. MRSDV model focuses on the forecast and management of critical situation (e.g. critical network security breach, a terror event and the invest timing in stock market), but it is insufficient in estimating parameter and lacks fitness test of model and criterion of risk and non-risk states, even though it grasps the spike pattern from actual data. In this paper, we propose a dependent dummy variable technique, Ordinary Least Square (OLS) method, and fitness test scheme for the proposed model. We also propose a new 'risk plane' for practical use, which is used as threshold criterion of risk.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image