nach oben

2014 | Buch

Kapitel lesen Erstes Kapitel lesen

Advances in Research Methods for Information Systems Research

Data Mining, Data Envelopment Analysis, Value Focused Thinking

herausgegeben von: Kweku-Muata Osei-Bryson, Ojelanki Ngwenyama

Verlag: Springer US

Buchreihe : Integrated Series in Information Systems

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

Advances in social science research methodologies and data analytic methods are changing the way research in information systems is conducted. New developments in statistical software technologies for data mining (DM) such as regression splines or decision tree induction can be used to assist researchers in systematic post-positivist theory testing and development. Established management science techniques like data envelopment analysis (DEA), and value focused thinking (VFT) can be used in combination with traditional statistical analysis and data mining techniques to more effectively explore behavioral questions in information systems research. As adoption and use of these research methods expand, there is growing need for a resource book to assist doctoral students and advanced researchers in understanding their potential to contribute to a broad range of research problems.

Advances in Research Methods for Information Systems Research: Data Mining, Data Envelopment Analysis, Value Focused Thinking focuses on bridging and unifying these three different methodologies in order to bring them together in a unified volume for the information systems community. This book serves as a resource that provides overviews on each method, as well as applications on how they can be employed to address IS research problems. Its goal is to help researchers in their continuous efforts to set the pace for having an appropriate interplay between behavioral research and design science.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

The decades from the 1990s to 2000s have seen long and vigorous debates over the perceived deepening alienation of the academic discipline of information systems from practice of and technical content of information systems.

Kweku-Muata Osei-Bryson, Ojelanki Ngwenyama

Chapter 2. Logical Foundations of Social Science Research

Abstract

In this chapter, I want to review the four inferential logics (1) induction, (2) deduction, (3) abduction, and (4) retroduction which we use to develop the conjectures or hypotheses when doing theory development.

Ojelanki Ngwenyama

Chapter 3. Overview on Decision Tree Induction

Abstract

The chapter provides an overview of decision tree (DT) induction. Its main purpose is to introduce the reader to the major concepts underlying this data mining technique, particularly those that are relevant to the chapters that involve the use of this technique.

Kweku-Muata Osei-Bryson

Chapter 4. An Approach for Using Data Mining to Support Theory Development

Abstract

The rapid and constant change in information technologies (IT), organizational forms, and social structures is challenging our existing theories of the impact IT on organizations and society. A basic problem for researchers is how to generate testable hypotheses about the given area of research. However, new IT offer opportunities for information processing and problem solving that could extend the capacity of researchers to generate hypotheses and systematically explore the limitations of any theory. The idea of using IT to support IS research is not new. In this chapter, we explore and illustrate how data mining techniques could be applied to assist researchers in systematic theory testing and development.

Kweku-Muata Osei-Bryson, Ojelanki Ngwenyama

Chapter 5. Application of a Hybrid Induction-Based Approach for Exploring Cumulative Abnormal Returns

Abstract

There is often an interest in business disciplines in investigating whether the public announcement of a business-related event has a statistically significant impact on the market value of the firm. The Capital Market reaction is typically assessed based on cumulative abnormal return (CAR), which is the sum of abnormal returns over the event window. The event study methodology is a popular approach for exploring the occurrence of CAR. Most previous event studies have used confirmatory approaches, which require the prior explicit specification of all hypotheses. However, in many situations, it could be difficult for the researcher to identify every relevant hypothesis that might be testable, particularly the local hypotheses. In this chapter, we present an exploratory data analysis methodology approach that involves the use of decision tree generation together with statistical hypothesis testing. We use two previous studies to demonstrate this methodology.

Francis Kofi Andoh-Baidoo, Kwasi Amoako-Gyampah, Kweku-Muata Osei-Bryson

Chapter 6. Ethnographic Decision Tree Modelling: An Exploration of Telecentre Usage in the Human Development Context

Abstract

This chapter presents an investigation of the decision-making process of community members who decide on using telecentres for entrepreneurial endeavours. A qualitative approach through interviews with telecentre staff and users is used to assess the barriers and enablers to economic activity through use of telecentres. An ethnographic decision tree model (EDTM) is developed to illustrate the process through which a community member makes a decision to use the telecentre to support economic livelihood. A predictive model for entrepreneurial behaviour is proposed based on the factors which influence the usage of telecentres for entrepreneurship—social ties, opportunity recognition and support from the telecentres.

Arlene Bailey, Ojelanki Ngwenyama

Chapter 7. Using Association Rules Mining to Facilitate Qualitative Data Analysis in Theory Building

Abstract

The richness captured in qualitative data is a key strength of the qualitative approach to theory building. However, given the nature of qualitative data, it is typically not apparent to qualitative researchers as to how quantitative techniques could be used to facilitate the identification of strong relationships between concepts that are embedded in the data. This typically leads to the formulation of theoretical propositions that are often rich in detail, yet lacking in simplicity. In addition, the researcher faces the daunting task of developing persuasive arguments to justify the findings. This chapter proposes a systematic procedure toward qualitative data analysis to facilitate developing propositions in theory building. Specifically, we demonstrate how researchers can take advantage of quantitative data analysis techniques such as association rules (AR) mining to identify strong concept relationships from qualitative data. The proposed procedure is illustrated using a case study in the public health domain.

Yan Li, Manoj Thomas, Kweku-Muata Osei-Bryson

Chapter 8. Overview on Multivariate Adaptive Regression Splines

Abstract

This chapter provides an overview of multivariate adaptive regression splines (MARS). Its main purpose is to introduce the reader to the major concepts underlying this data mining technique, particularly those that are relevant to the chapter that involves the use of this technique. This chapter includes an illustrative example and also provides guidance for interpreting a MARS model.

Kweku-Muata Osei-Bryson

Chapter 9. Reexamining the Impact of Information Technology Investments on Productivity Using Regression Tree- and MARS-Based Analyses

Abstract

Several studies have investigated the impact of investments in IT on productivity. In this chapter, we revisit this issue and reexamine the impact of investments in IT on hospital productivity using two data mining techniques, which allowed us to explore interactions between the input variables as well as conditional impacts. The results of our study indicated that the relationship between IT investment and productivity is very complex. We found that the impact of IT investment is not uniform and the rate of IT impact varies contingent on the amounts invested in the IT Stock, Non-IT Labor, Non-IT Capital, and possibly time.

Myung Ko, Kweku-Muata Osei-Bryson

Chapter 10. Overview on Cluster Analysis

Abstract

This chapter provides an overview of cluster analysis. Its main purpose is to introduce the reader to the major concepts underlying this data mining (DM) technique, particularly those that are relevant to the chapter that involves the use of this technique. It also provides an illustrative example of cluster analysis.

Kweku-Muata Osei-Bryson, Sergey Samoilenko

Chapter 11. Overview on Data Envelopment Analysis

Abstract

The chapter provides a general introductory overview of data envelopment analysis. Its main purpose is to introduce the reader to the major concepts underlying this nonparametric technique. After familiarizing the reader with the general process used in calculating the scores of relative efficiency, the chapter presents an overview of various orientations and types of DEA models. In conclusion, the chapter gives an overview of using DEA for the purposes of constructing Malmquist index, a popular tool for measuring changes in efficiency over time; a brief example is used to illustrate major points.

Sergey Samoilenko

Chapter 12. ICT Infrastructure Expansion in Sub-Saharan Africa: An Analysis of Six West African Countries from 1995 to 2002

Abstract

The World Bank, International Monetary Fund, the UN and International Telecommunications Union (ITU) argue that ICT infrastructure and informatization are prerequisites to adequate development in the present era. The ITU has proposed a framework for measuring ICT efficiency and its impact on social development. However, it offered no advice on how to develop, model and implement this proposal. In this chapter, we use data envelopment analysis to address one aspect of the ITU proposal, the measurement of the efficiency of investments in ICT infrastructure development. The study makes two important contributions: (1) It provides a methodology for assessing the efficiency of investments in ICT; (2) it provides insights into the structuring development policies to benefit from effective allocation of scarce resources in developing countries.

Felix Bollou

Chapter 13. A Hybrid DEA-/DM-Based DSS for Productivity-Driven Environments

Abstract

This chapter begins with the overview of the challenges facing organizations competing in dynamic business environments and the associated demands placed on organizational DSS. The overview of the design of DSS starts with an outline of the capabilities that combination of such various methods as data envelopment analysis (DEA), cluster analysis (CA), decision tree (DT), neural networks (NN), and multivariate regression (MR) offer to a decision maker.

Sergey Samoilenko, Kweku-Muata Osei-Bryson

Chapter 14. Overview of the Value-Focused Thinking Methodology

Abstract

The chapter provides an overview of the value-focused thinking (VFT) methodology. Its main purpose is to introduce the reader to the major concepts of this methodology, particularly those that are relevant to the chapter that involves the use of VFT. It also discusses previous applications of the VFT methodology in information systems research.

Corlane Barclay

Chapter 15. A Hybrid VFT-GQM Method for Developing Performance Criteria and Measures

Abstract

This chapter utilizes the principles of the Value Focused Thinking (VFT) and Goal Question Metric (GQM) to present a tool for managing the foundation processes of projects, programs and portfolios. The Project Performance Development Framework (PPDF) promotes the use of formal steps for identifying project criteria and measures that are used as the basis to evaluate the performance of the project. It addresses critical problems in project management where objectives typically are not clearly defined and stakeholders have multiple views and objectives on what is important to them in the project, which in turn impacts how the project performance is perceived. The PPDF has several iterative steps including stakeholder identification, objectives identification and structuring, definition of project measurement and prioritization to aid in stakeholder management and project objectives identification, prioritization and management. The PPDF artifact presented is demonstrated and evaluated for utility through a single Process Quality Management Development Project. The findings support the goals of PPDF and show that the formal approach provides added advantages in identifying important values of the stakeholders thereby improving the likelihood of managing stakeholders’ needs and achieving identified goals.

Corlane Barclay, Kweku-Muata Osei-Bryson

Backmatter

Titel: Advances in Research Methods for Information Systems Research
herausgegeben von: Kweku-Muata Osei-Bryson
Ojelanki Ngwenyama
Verlag: Springer US
Electronic ISBN: 978-1-4614-9463-8
Print ISBN: 978-1-4614-9462-1
DOI: https://doi.org/10.1007/978-1-4614-9463-8