The presence of clusters in a data set is sometimes due to the existence of certain relations among the measured variables which vary depending on some hidden factors. In these cases, observations could be grouped in a natural way around linear and nonlinear structures and, thus, the problem of doing robust clustering around linear affine subspaces has recently been tackled through the minimiza...

1 Dario Nardi, University of California Los Angeles, Program in Computing, Math Sciences 6363, Los Angeles, CA 90095 [email protected] Abstract—Systems concepts like non-linearity and feedback are relevant in many fields, but interactive software to demonstrate these concepts are uncommon. Three mini-applications are discussed. These applications are relatively simple in programming and desi...

New Zealand has a poor rate of immunisation in comparison to other OECD countries. Immunisation is a major public health issue as it is one of the most cost-effective health interventions. However, high immunisation rates are required to realise the full benefit of immunisation programmes. In this paper we use Systems Thinking to identify principal dynamics that underlie immunisation system and...

A successful knowledge management strategy identifies a firm’s key leverage points essential to achieve business results. These often reside in core business processes that may be re-engineered to capitalize on and expand organizational knowledge resources and capabilities. This case describes a 4-year initiative undertaken by IBM to re-engineer its customer relationship management process and ...

Integrated supply chains are one of the most powerful competitive tools in today's globalizing business economy. For agricultural products, successful supply chain development projects reduce not only the transaction costs but also the institutional barriers that decouple individual links in traditional distribution channels. They allow participants to achieve higher levels of service and to ca...

the latest known source of multicollinearity, a nonorthogonality of two or more explanatory variables in multiple regression models, is high leverage points. Interpreting a fitted regression model may become impossible by the influential impacts of multicollinearity. In this paper, we attempt to investigate the impact of different sample sizes as one of the main causing factors of high leverage...

Robust selection of variables in a linear regression model is investigated. Many variable selection methods are available, but very few methods are designed to avoid sensitivity to vertical outliers aswell as to leverage points. The nonnegative garrotemethod is a powerful variable selection method, developed originally for linear regression but recently successfully extended to more complex reg...

In recent years there has been considerable activity, by business analysts and academics, in developing new approaches to understanding contemporary innovation processes. This has resulted in the emergence of a large number of conceptual alternatives, with many overlapping features. It is the aim of this paper to outline and compare the most popular of these frameworks, and develop a model inco...

This paper investigates the diffusion of system dynamics as research paradigm. It deals with the question whether the diffusion of system dynamics is influenced by network externalities. Assuming the existence of such network externalities the so called penguin and bandwagon effect must be considered regarding the diffusion. Based on a system dynamics model considering network externalities lev...

This paper outlines some research questions in relation to software process improvement. Software process improvement should be a continuous activity where you go through with a set of activities to achieve a higher level of maturity. These activities can be seen as a four step process; information collection and investigation, decision making and planning, implementation, and evaluation. This ...