Adi Raveh

Conceptual maps of the leading MBA programs in the United States: core courses, concentration areas, and the ranking of the school

This paper captures the structure of MBA programs in 25 leading U.S. business schools at the beginning of the revolution these programs are undergoing. It is a study of strategic groups in the MBA industry, and a baseline for examining adaptation and strategic change in educational institutions. We use the Co-plot method to map the schools according to the 1993 structure of their core courses and existing areas of concentration. The maps indicate similarities among business schools and shed light on their 1994 ranking. Each of the five top schools has been found to be in a different cluster of MBA program structures. The findings suggest that program structure content—the particular mix of core and concentration areas—in itself is not a source of superior performance. Copyright

The Greek banking system: Reanalysis of performance

Abstract Zopounidis et al. used an ordinal regression analysis to assess an additive utility model and to obtain final ranking of a representative sample of commercial Greek banks [C. Zopounidis, D.K. Despotis, E. Stavropoulou, Multiattribute evaluation of Greek banking performance, Applied Stochastic Models and Data Analysis 11 (1995) 97–107]. In this paper, we reanalyze their data by means of a new multivariate analysis method called Co-plot, a two-dimensional graphic display technique designed to analyze observations (e.g., 16 banks) and attributes (e.g., 7 attributes) simultaneously . The method produces three results: (1) similarity among the banks by the composite of all attributes involved (five clusters are obtained), (2) the structure of correlations among the attributes (three clusters are obtained), and (3) the mutual relationships between the banks and the attributes. The banks are mapped into a partial order according to their (increased) performance to obtain their rating. The final ranking obtained by the Co-plot method differed from that obtained by Zopounidis et al.

On Measures of Monotone Association

Abstract A family of coefficients for measuring monotone association is presented. These include measures of association of ordinal or interval variables such as gamma of Goodman and Kruskal, Somerss dyx , Kendalls tau, or Spearmans rho as special cases. The article shows how a large number of measures of association can be put into a single general form. These coefficients are used as a basis for defining a variety of data analysis techniques.

Co-plot: A graphic display method for geometrical representations of MCDM

Abstract A relatively new multivariate analysis method called Co-plot is shown to be highly efficient for the geometrical representation of multicriteria decision problems. Co-plot, a two-dimensional graphic display technique is designed for multicriteria analysis. Its main feature is the simultaneous analysis of actions (e.g., observations) and criteria (e.g., variables) in a simple way. The method produces three results: (1) similarity among actions by the composite of all criteria involved; (2) the structure of correlations among the criteria, and (3) the mutual relationships between the actions and the criteria. The method is demonstrated on two numerical applications previously analyzed by Mareschal and Brans [B. Mareschal, J.P. Brans, European Journal of Operational Research 34 (1988) 69–77] using the Promethee methods and Principal Component Analysis.

Information Filtering: A New Two-Phase Model Using StereotypicUser Profiling

Computer users often experience the “lost in informationspace” syndrome. Information filtering suggests a solution based onrestricting the amount of information made available to users. Thisstudy suggests an advanced model for information filtering which isbased on a two-phase filtering process. The user profiling in themodel is constructed on the basis of the users areas of interestand on sociological parameters about him that are known to thesystem. The system maintains a database of known stereotypes thatincludes rules on their information retrieval needs and habits.During the filtering process, the system relates the user to one ormore stereotypes and operates the appropriate stereotypic rules.

On the use of the Inverse of the Correlation Matrix in Multivariate Data Analysis

Abstract It is well known that the correlation matrix has a central role in the analysis of multivariate data. The inverse of the correlation matrix, however, also has important interpretations. An exposition of some of the properties connected with the inverse of the correlation matrix is provided and its use in the analysis of multivariate data is described.

Comparing Logs and Models of Parallel Workloads Using the Co-plot Method

We present a multivariate analysis technique called Co-plot that is especially suitable for samples with many variables and relatively few observations, as the data about workloads often is. Observations and variables are analyzed simultaneously. We find three stable clusters of highly correlated variables, but that the workloads themselves, on the other hand, are rather different from one another. Synthetic models for workload generation are also analyzed, and found to be reasonable; however, each model usually covers well one machine type. This leads us to conclude that a parameterized model of parallel workloads should be built, and we describe guidelines for such a model. Another feature that the models lack is self-similarity: We demonstrate that production logs exhibit this phenomenon in several attributes of the workload, and in contrast that the none of the synthetic models do.

Stress factors, social support, and violence in Israeli society: a quantitative analysis

In the present study violence in Israel for a period of 32 years (1950-1981) was analyzed, within a stress model according to which the probability of violence and agression as a reaction to stress will increase when social support systems fail or malfunction. Following this model, three types of variables were identified: 1. Measures of stress and social change: to the regular social stressors (i.e., inflation and unemployment), we added two measures of affluence (income per capita and rates of cars) as well as population density. 2. Measures of social support: rates of birth to unmarried mothers and marriage and divorce rates served as measures of the strength of the family. Another measure in this category was rates of psychiatric hospitalization. 3. Measures of violence: in addition to rates of homicide, robbery, and all offenses, inward directed aggression (suicide) was included in this category. At the first stage of the data analysis, Guttmans Smallest Space Analysis (SSA-1) was applied, providing a two-dimensional space diagram of the correlations between the variables. At the second stage, a multiple regression analysis was introduced. The findings indicate that the theoretical model received substantial support mainly from four stress measures (inflation, income per capita, cars, and population density) and one measure of social support (divorce). Unemployment contributed significantly (in the expected direction) only to homicide. Some theoretical implications of the findings, as well as their relevance to some developments in Israeli society are discussed, and suggestions are made for future research.

Integration in large, related M&As: linkages between contextual factors, integration approaches and process dimensions

The purpose of our study is to examine differences in contextual factors and process dimensions across three integration approaches used in large, related M&As – absorption, symbiotic and transformation. Absorption and symbiosis are commonly documented in M&A process literature and transformation, while emphasised less in existing M&A studies, appears to be widely utilised in large, related M&As. Using a unique co-plotting technique, we find that the existence of several contextual factors which influence the potential for resource combinations and use of multiple process dimensions which facilitate actual resource combinations during the implementation stage differ significantly depending upon the integration approach used by the combined firm. Moreover, our study adds to growing literature on the M&A process by providing systematic evidence of the important linkages between integration approaches, pre-existing contextual factors and process activities.

A Nonmetric Approach to Linear Discriminant Analysis

Abstract A new nonmetric linear discriminant analysis approach is proposed that is based on the maximization of an index of separation differing from that used by the classical method. The possibility of choosing between Fishers classical discriminant function and the one proposed here enables us to reduce the number of misclassifications for given data. The method is exemplified on empirical data and various simulations and is compared with the classical linear discriminant analysis.