Skip to main content
Sign In
 

Published Work

Professor Marlene A. Smith


​​

Marlene Smith's Top Ten Research Publications

M.A. Smith (1999), "Data Analysis," in The Handbook of Technology Management, CRC Press and IEEE Press, Boca Raton, FL, 5-31 to 5-35.

The Handbook of Technology Management is a reference manual for engineers, scientists, and technology managers. This invited chapter describes the basics of data analytic tools appropriate to management of high technology firms.

Peter Bryant and M.A. Smith, Practical Data Analysis: Case Studies in Business Statistics, Volumes I, II, and III, Richard D. Irwin Publishing Company, 1995, 1999.

Practical Data Analysis is a collection of 75 case studies, available in three volumes, for use in graduate and undergraduate business statistics courses.

M.A. Smith and Jan Zahrly (1993), "Resource Allocation in High Technology Firms: Managerial Strategies and Empirical Results, "Journal of High Technology Management Research, 4, 47-61.

Two competing theoretical models of strategic allocation decisions are posited and tested. The long-run model hypothesizes that capital expenditures and R&D activities are important determinants of profit in high technology organizations. Alternatively, the short-run model uses marketing expenditures and dividend payments to investors as predictors of profit. A cross-section of 106 high technology firms is used to compare these long-term and short-term strategies. The findings indicate that R&D and investment in capital improvements are important components of profitability in high technology firms.

Christina M.L. Kelton and M.A. Smith (1991), "Statistical Inference in Nonstationary Markov Models with Embedded Explanatory Variables," Journal of Statistical Computation and Simulation,38, 25-44.

In this paper, we develop an operational nonstationary Markov process model for use with macro aggregate frequency data. Independent, time-variant factors assumed to affect the process of interest are embedded in the model. Transition probabilities are estimated indirectly from the coefficients on the embedded variables. Here, we propose a test for parameter stationarity. By means of designed simulation experiments for the two-state model, we find that our test has acceptable Type I error probabilities, and that power rises with the degree of departure from the null hypothesis. Both validity and power performance can be improved by longer time records of data and a greater number of entities observed.

M.A. Smith and David J. Smyth (1991), "Multiple and Pairwise Non-nested Tests of the Influence of Taxes on Money Demand, "Journal of Applied Econometrics, 6, 17-30.

The minimal computational requirements of the linear embedding techniques initiated by Davidson and MacKinnon (1981) accommodate multiple and binary tests of autoregressive, non-nested regression models with different dependent variables. The small sample adjustments of Fisher and McAleer (1981) effectively reduce the size of the P-tests for our models. Our application to transactions demand for money models supports the Holmes and Smyth (1972) hypothesis that pre-tax variables are preferred to GNP in M1 money equations.

M.A. Smith and David J. Smyth (1990), "Choosing Among Multiple Nonlinear Non-nested Regression Models with Different Dependent Variables: An Application to Money Demand," Economics Letters, 34, 147-150.

The linearly-embedded regression model approach of Davidson and MacKinnon (1981) is used to construct joint tests of seven non-nested, autoregressive money demand equations with different regressands. The results support the Holmes-Smyth (1972) hypothesis that taxes affect money demand.

M.A. Smith (1988), "Income or Wealth in Money Demand: Comment, "Southern Economic Journal, 54, 1033-1038.

This paper suggests a method for dealing with non-nested tests of regression models characterized by first-order autoregressive error structures.

Christina M.L. Kelton and M.A. Smith (1987), "Estimation Efficiency for Markov Chain Models," Journal of Statistical Computation and Simulation, 28, 145-165.

In this paper, we evaluate and compare four algorithms for estimating stationary Markov chain models with embedded parameters from aggregate frequency data. By means of a factorially designed Monte Carlo simulation experiment, we are able to determine the effects of model characteristics on algorithm accuracy and efficiency. We then present an application, using the best-performing algorithm, for U.S. population migration.

Christina M.L. Kelton and M.A. Smith (1986), "Nonlinear Programming Solutions to the Nonstationary Markov Model," Communications in Statistics: Computation and Simulation, 15, 1169-1190.

A nonstationary Markov process model with embedded explanatory variables offers a means to account for underlying causal factors while retaining unrestrictive assumptions and the predictive ability of a stochastic framework. We find that a direct search algorithm requiring minimal user preparation is a feasible computational procedure for estimating such a model. We compare this method with several others using factorially designed Monte Carlo simulations and find evidence that a small state space and a long time series lead to better algorithmic performance.

M.A. Smith and G.S. Maddala (1983), "Multiple Model Testing for Nonnested Heteroskedastic Censored Regression Models, "Journal of Econometrics, 21, 71-81.

The Davidson and MacKinnon (1981) J-test is a computationally efficient method for choosing between non-nested regression models. The paper illustrates the use of this test for separate, nonlinear, heteroskedastic Tobit models with an important application to the problem of measuring income and wealth effects in the demand for money. The multiple model J-test rejects all five models under consideration; the paper proposes an interpretation of the results when joint rejection of all models is suggested by the non-nested tests.
 

The instructional materials and contents of this website are the property of Professor Marlene A. Smith. They are intended for use by students enrolled in QUAN 2010 (Business Statistics) and BUSN 6530 (Data Analysis for Managers) at the University of Colorado at Denver. Other use of this website, instructional materials, or content is prohibited without the expressed written consent of Marlene Smith.

  Copyright © 2000-2001 by Marlene A. Smith. All rights reserved.

© The Regents of the University of Colorado, a body corporate. All rights reserved.

Accredited by the Higher Learning Commission. All trademarks are registered property of the University. Used by permission only.