Marietta J. Tretter

Strategy and Structure of U.S. Multinationals: An Exploratory Study

Large U.S. multinational companies are classified by the structure through which their foreign operations report to headquarters. Structural groups then are compared by the use of such variables as...

Defining and Evaluating a Measure of Open Source Project Survivability

In this paper, we define and validate a new multidimensional measure of Open Source Software (OSS) project survivability, called Project Viability. Project viability has three dimensions: vigor, resilience, and organization. We define each of these dimensions and formulate an index called the Viability Index (VI) to combine all three dimensions. Archival data of projects hosted at SourceForge.net are used for the empirical validation of the measure. An Analysis Sample (n=136) is used to assign weights to each dimension of project viability and to determine a suitable cut-off point for VI. Cross-validation of the measure is performed on a hold-out Validation Sample (n=96). We demonstrate that project viability is a robust and valid measure of OSS project survivability that can be used to predict the failure or survival of an OSS project accurately. It is a tangible measure that can be used by organizations to compare various OSS projects and to make informed decisions regarding investment in the OSS domain.

An interval arithmetic approach to sensitivity analysis in geometric programming

Geometric programming has been an important optimization approach in several engineering design areas. In this paper, we present an approach to sensitivity analysis in geometric programming using interval arithmetic. The study of the effect of changes in the problem parameters is important for theoretical as well as for practical reasons. To date, most of the numerical approaches to sensitivity analysis have characterized the solution in terms of differential changes in the parameters. We use interval arithmetic to generate an interval of solution values associated with an interval of parameter values. These results indicate a new approach to characterizing solutions to geometric programs in terms of changes in the problem parameters.

Antecedents of open source software defects: A data mining approach to model formulation, validation and testing

This paper develops tests and validates a model for the antecedents of open source software (OSS) defects, using Data and Text Mining. The public archives of OSS projects are used to access historical data on over 5,000 active and mature OSS projects. Using domain knowledge and exploratory analysis, a wide range of variables is identified from the process, product, resource, and end-user characteristics of a project to ensure that the model is robust and considers all aspects of the system. Multiple Data Mining techniques are used to refine the model and data is enriched by the use of Text Mining for knowledge discovery from qualitative information. The study demonstrates the suitability of Data Mining and Text Mining for model building. Results indicate that project type, end-user activity, process quality, team size and project popularity have a significant impact on the defect density of operational OSS projects. Since many organizations, both for profit and not for profit, are beginning to use Open Source Software as an economic alternative to commercial software, these results can be used in the process of deciding what software can be reasonably maintained by an organization.

The evolution of and expert DSS for electric utility load research

Abstract Load research conducted by electric utility companies is an activity embracing the measurement and study of electrical load to understand the trends and behavior of electric utility consumption. The results of load research are major determinants in rate design and capacity planning for the electric utility company. Accurate load research is imperative for a well managed electric utility. The information base used in load research consists of customer billing data and sample data collected under strict guidelines set by the Public Utilities Regulatory Policies Act. Selection of appropriate sampling procedures is a central function of load research. This paper describes the evolution of an integrated expert decision support system (XDSS) for load research sample design. It is an exploratory system that has a potentially large impact on the profitability of electric utility companies. It was the result of a consulting project begun 4 years ago with a medium sized utility company. Much of the underlying statistical sampling methodology in the XDSS had to be newly derived to meet the specific needs of sampling in load research.

Classification of software patches: a text mining approach

Installation of maintenance patches in operational software systems is a source of significant expenditure and resource consumption. Managers often have to find a balance between publicly announced vulnerabilities and/or possible destabilization of existing applications, while making decisions regarding patch roll out to all systems. We propose a classification scheme for maintenance patches and examine the effects of patch category on the internal characteristics of a software system. Text mining the patch releases of 77 successive versions of the Linux operating system, we extend previous categorization schemes to maintenance patches. This granularity level offers a view of the aggregate nature of the tasks performed in each version. An unsupervised learning technique, cluster analysis associated with Text mining, reveals that there are three identifiable categories in Linux patch files. Based on the maintenance keywords in each category, we label them as: corrective, perfective and adaptive patches. Further analysis of the effects of patch category on the structural complexity and the time to next release indicates that perfective patches are associated with a reduction in the complexity and frequency of patch release. Categorization at the patch level is useful for managers, since changes made to operational software systems are through patches. Determining the nature of a patch can assist managers in planning version roll out and testing criterion. Copyright

An interactive decision support system for designing appropriate and adaptive sampling procedures in electric utility load research

Abstract Confidence interval estimation of customer demand for electricity plays a vital role in the capacity and financial planning of electric utility companies. Inaccurate or inadequate estimation could severely affect the economic efficiency of these companies. Selecting the appropriate sampling procedure is, in turn, critical to ensuring success in the accurate estimation of electrical demand. Because of the nature and diversity of demand for electricity, however, classical sampling procedures have to be extensively modified. This paper describes a decision support system (DSS) that aids electric utility companies in selecting and designing appropriate sampling plans. The DSS adapts sophisticated statistical techniques to address all aspects of the sampling procedure.

Interval Newton methods and perturbed problems

This paper describes a straightforward implementation of a modified Newton algorithm which generates the best interval bounding the solution generated using interval Newton methods. This implementation addresses the issues described by Hansen and Greenberg for analyzing problems with data perturbations using interval analysis. It also indicates a new approach of potentially attractive methods for using interval Newton methods. While our focus is on perturbed problems (sensitivity analysis), the results are more generally applicable. The major difference in the point of view of perturbed problems versus the general use of interval methods is that in perturbed problems we are focused on the behavior of the function around an optimal solution. The more general approach seeks to identify all optimal solutions of the function.

Predicting OSS Development Success: A Data Mining Approach

Open Source Software OSS has reached new levels of sophistication and acceptance by users and commercial software vendors. This research creates tests and validates a model for predicting successful development of OSS projects. Widely available archival data was used for OSS projects from Sourceforge.net. The data is analyzed with multiple Data Mining techniques. Initially three competing models are created using Logistic Regression, Decision Trees and Neural Networks. These models are compared for precision and are refined in several phases. Text Mining is used to create new variables that improve the predictive power of the models. The final model is chosen based on best fit to separate training and validation data sets and the ability to explain the relationship among variables. Model robustness is determined by testing it on a new dataset extracted from the SF repository. The results indicate that end-user involvement, project age, functionality, usage, project management techniques, project type and team communication methods have a significant impact on the development of OSS projects.

A simulation procedure for sample size determination in electric utility load research

Estimating the customer demand for electricity plays a crucial role in the equitable determination of customer electric utility rates. To estimate the customer demand accurately, it is necessary to determine the appropriate sample size. Due to the unique requirements imposed by the Public Utilities Regulatory Policies Act of 1978, existing procedures to determine sample size fail to provide the optimal sample size that will satisfy the re quirements at the minimum cost. The objective of this study is to develop and describe a simulation based procedure that is capable of achieving both criteria. The effectiveness of the pro cedure is tested for selected distributions of electrical demand. The study also identifies other instances where similar sample size determination problems occur and how the newly developed procedure can be used in these situations as well.