Search

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ejor.2004.09.041 Byline: Eugene D. Hahn Keywords: Analytic hierarchy process; Bayesian inference; Multivariate statistics; Simulation Abstract: A stochastic formulation of the Analytic Hierarchy Process (AHP) using an approach based on Bayesian categorical data models has been developed. However, in categorical data models it is known that the selection of the link function may have an impact on the model estimates. In particular, the selection of the probit link implies an assumption that model error terms are normally distributed and this normality assumption is regularly utilized in other related methods such as the multiplicative AHP. We examine model performance with respect to the choice of two model link functions. With regard to point estimates, it is found that the logit formulation is better able to replicate the estimates obtained by the eigenvector decomposition associated with the original formulation of the AHP. By contrast, the probit link produces priorities which are consistently more moderate than those of the AHP. The results suggest that the logit formulation will be preferred by decision makers who wish to replicate the AHP priorities as closely as possible. The results also suggest that the unexamined use of the normality assumption in other stochastic AHP methods may have an impact on priority estimates and thus is worthy of further attention. Author Affiliation: Department of Information & Decision Sciences, Franklin P. Perdue School of Business, Salisbury University, 1101 Camden Avenue, Salisbury, MD 21801, USA Article History: Received 10 January 2003; Accepted 20 September 2004

In the literature, decision support systems (DSSs) have typically been evaluated on only a single criterion such as the outcome from decision making. However, it is clear that DSSs simultaneously have a critical impact on the process-oriented aspects of decision making, suggesting that a combination of both outcome and process criteria are highly relevant for DSS evaluation. Indeed, process characteristics are particularly crucial for web-based and real-time DSSs because of their ability to deliver timely, current information through features such as just-in-time information, real-time processing, on-line transaction processing, connectivity and globally up-to-date information. In this underexplored area, we propose a framework to evaluate DSSs that combines outcome- and process-oriented evaluation measures. The approach is demonstrated in the context of a real-time threat criticality detection DSS. Investigations are conducted using a multicriteria decision-making method called the Analytic Hierarchy Process (AHP) as well as a newly developed stochastic enhancement of AHP. We find that the real-time DSS offered a significant improvement in terms of process-related characteristics. However, it did not offer a statistically significant improvement in terms of outcome-related characteristics. The importance of simultaneously addressing both sets of considerations is discussed. Keywords: Decision support system; Evaluation; Analytic hierarchy process; Stochastic; Real-time, 1. Introduction In a study of 21 reported decision support systems (DSSs), Forgionne [1] found that most empirical studies of traditional DSSs focused on either process-oriented or outcome-oriented evaluation measures, [...]

Analytic Hierarchy Process (AHP) is a multicriterian decision-making method used in making challenging business decisions and troubleshoots in complexity and conflicting objectives. Different views, models for obtaining priorities and the alternatives were tested to reexamine quantitative judgments.

To determine cohort changes in gender-role attitudes, responses to the 15-item form of the Attitudes Toward Women Scale (AWS; Spence & Helmreich, 1972a, 1978) were compared for students at the same university tested in 1972, 1976, 1980, and 1992. In both males and females, members of the 1992 cohort were the most egalitarian, and members of the 1972 cohort were the least egalitarian. In all groups, women were significantly less traditional in their attitudes than men. As has been found in previous studies, detailed analyses of the data from the 1992 cohort revealed that the scale was unifactorial, but that the score distributions were skewed. There was also some indication of ceiling effects at the egalitarian end of the scale, particularly in women. The implications of these latter results for the usefulness of the AWS in current research were explored.

Hansen, Perry, and Reese (2004) recently argued for and demonstrated the utility of Bayesian methods for research associated with the resource-based view (RBV) of the firm. In this paper, we propose that Bayesian approaches are highly relevant not only for strategy problems based on the RBV, but also to its extensions in the areas of dynamic capabilities and co-evolution of industries and firms. Further, we argue that Bayesian methods are equally applicable for a wide range of strategy research questions at both the micro- and macro-level. Bayesian techniques are especially useful in addressing specific methodological challenges related to firm- and individual-level effects, firm-level predictive results, precision with small samples, asymmetric distributions, and the treatment of missing data. Moreover, Bayesian methods readily permit the engineering and updating of more realistic, complex models. We provide a specific illustration of the utility of Bayesian approaches in strategy research on entry order and pioneering advantage to show how they can help to inform research that integrates micro- and macro-phenomena within a dynamic and interactive environment. Copyright &cop; 2006 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Offshoring has emerged as an important economic and social phenomenon that has generated intense interest from practitioners, the popular media, and policy makers. In addition, there is a nascent but rich research literature on offshoring developing in management, international business (IB), and related fields. In this review, we survey and integrate offshoring literature from several disciplines and draw implications of this review for management and IB research. We conclude that offshoring may challenge some aspects of established management and IB theory or require revision and/ or modification of those theories. We adopt a multilevel coevolutionary perspective as one potential integrative approach to offshoring research and identify important future areas for further enrichment of this emerging area. [ABSTRACT FROM AUTHOR]

Empirical research on the growing wave of services offshoring has examined the impact of several key factors such as wages and personnel quality on firm choices of offshore locations. However, examinations of culture in services offshoring to date have largely been confined to the relatively coarse concept of aggregate cultural differences between the home and host countries. We propose that specific cultural attributes are more closely aligned with successful service provision. We empirically examine our theoretical development of service cultural alignment and investigate the impact of cultural dimensions on the location of service offshoring projects. In addition, we examine whether Western and Asian firms have different cultural preferences in terms of the location of services offshoring projects. We find that host countries with lower levels of Hofstede''s uncertainty avoidance as well as higher levels of individualism and power distance are able to attract greater numbers of service offshoring projects, even after controlling for macroeconomic, linguistic, and risk-related factors. We did not find that Western and Asian firms have different cultural preferences in this regard. We discuss implications of the findings with respect to theory, managerial practice, and governmental policy. [Copyright &y& Elsevier]

Spatial and geographic constructs have been incorporated into strategy research since its inception. Yet, strategy researchers have been slow to take advantage of methods designed specifically for these variables. This is despite the fact that spatial methods can be used to identify and remediate spatial autocorrelation—eliminating a potentially important source of bias in empirical results—and more broadly, to test hypotheses about spatial phenomena in novel ways. This article reviews the use of spatial constructs and variables in strategy research, summarizes spatial methods relevant to the strategy field, and shows how these approaches can enhance strategy research. The authors demonstrate the utility of these methods for a wide range of empirical inquiries into the role of geographic space in firm location, competition, and other phenomena, and offer three specific illustrations of their usefulness in the context of international strategy research. [ABSTRACT FROM AUTHOR]

Presents an abstract of an article on cohort analysis in gender-role attitudes of college students. Details of the data and scaling method used; Indication of ceiling effects at the egalitarian end of the scale; Differences between the attitudes of men and women respondents.