Working Papers 1998 – Abstracts

13/98
Lead Time Demand for Simple Exponential Smoothing
Ralph Snyder, Anne B. Koehler, J.Keith Ord

A new simple formula is found to correct the underestimation of the standard deviation for total lead time demand when using simple exponential smoothing. The traditional formula for the standard deviation of lead time demand is to multiply the standard deviation for the one- period-ahead forecast error (estimated by using the residuals) by the square root of the number of periods in the lead time. It has been shown by others that the traditional formula significantly underestimates variation in the lead time demand when the mean of the process is somewhat changing and simple exponential smoothing is appropriate. This new formula allows one to see readily the significant size of the underestimation of the traditional formula and can easily be implemented in practice. The formula is derived by using a state space model for simple exponential smoothing.

14/98
Testing Convergence in Economic Growth for OECD Countries
Syfun Nahar and Brett Inder

In this paper we propose a new test procedure with more general steady state information to test the convergence hypothesis for a specific economy. We consider a model where demeaned per capital output of an economy is a function of time trend and then set the convergence hypothesis as negative average slope of that model. Applying the new procedure to 22 OECD countries we find strong evidence of convergence for 20 countries towards their average level. We also consider the per capital output of USA as a common steady state level for OECD countries. Then using the per capital output gap from USA we test the convergence hypothesis for an individual economy. This approach also shows strong evidence in favour of convergence towards the USA for most economies. France and Iceland do not converge towards the average level of OECD countries although they are converging towards USA. Australia and New Zealand are showing the opposite pattern as they are converging towards the average level but moving away from USA. This study also points out why using standard unit root tests with Bernard and Durlauf's (1995) definition of convergence is inappropriate.

15/98
Model Selection When a Key Parameter is Constrained to be an Interval
Md. Zakir Hossain and Maxwell L. King

This paper considers the construction of model selection procedures based on choosing the model with the largest maximised log-likelihood minus a penalty, when key parameters are restricted to be in a closed interval. The approach adopted is based on King et al.'s (1995) representative models method with the use of the parametric bootstrap to handle nuisance parameters. The method is illustrated by application to two model selection problems in the context of Box-Cox transformations and the linear regression model. Simulation for both problems indicate that the new procedure clearly dominated existing procedures in terms of having higher probabilities of correctly selecting the true model.

Next Abstract