Quantitative, Positivist Research Methods in Information Systems

Section 1. Welcome

Welcome to the section on Quantitative, Positivist Research (QPR) Methods in Information Systems (IS). This section attempts to address the needs of quantitative, positivist researchers in IS – both seasoned veterans, and those just beginning to learn to use these methods. The research tasks that are addressed include many stages in the scholarly process, including literature review and theory development stages, and the later stage of design. 

1.1 Acknowledgments: We wish to thank the CIS Dept. at Georgia State University for hosting this site. Suggestions on how best to improve on the site are very welcome. Please contact us directly if you wish to make suggestions on how to improve the site. No faults in content or design should be attributed to any persons other than ourselves since we made all relevant decisions on these matters. 

1.2 Objective of this Website
This section is dedicated to exploring issues in the use of quantitative, positivist research methods in Information Systems (IS). We intend to provide basic information about the methods and techniques associated with QPR and to offer the visitor links to other useful sites and to seminal works.

1.3 Explanation for Extent of Self-Citation
One of the main reasons the co-editors were interested in initiating this site is that we have already published a fair number of articles on the subject. We felt that we needed to cite our own works as readily as others to give the Web surfer as much information at his/her fingertips as possible. For this reason, we also include hyperlinks (Section 9, below) so users can download the last working paper version of the papers that we were eventually fortunate enough to have published.

Please note that a version of the material on this website has also been published as: Straub, Detmar W., David Gefen and Marie-Claude Boudreau, "Quantitative Research," In Research in Information Systems: A Handbook for Research Supervisors and Their Students, D. Avison and J. Pries-Heje (Ed.), Elsevier, Amsterdam, 2005, 221-238.

1.4 What is Quantitative, Positivist Research
QPR is a set of methods and techniques that allow IS researchers to answer research questions about the interaction of humans and computers. There are two cornerstones in this approach to research. The first cornerstone is the emphasis on quantitative data. The second cornerstone is the emphasis on positivist philosophy. Regarding the first cornerstone, these methods and techniques tend to specialize in quantities in the sense that numbers come to represent values and levels of theoretical constructs and concepts and the interpretation of the numbers is viewed as strong scientific evidence of how a phenomenon works. The presence of quantities is so predominant in QPR that statistical tools and packages are an essential element in the researcher's toolkit. Sources of data are of less concern in identifying an approach as being QPR than the fact that empirically derived numbers lie at the core of the scientific evidence assembled. A QPR researcher may use archival data or gather it through structured interviews. In both cases, the researcher is motivated by the numerical outputs and how to derive meaning from them. This emphasis on numerical analysis is also key to the second cornerstone, positivism, which defines a scientific theory as one that can be falsified. 

1.5 What it is Not and How it Differs from Analytical Modeling, Design Research and Qualitative Research
QPR is orthogonal to the analytical modeling (a.k.a. math modeling) that typically depends on mathematical derivations and assumptions. This difference stresses that empirical data gathering or data exploration is part and parcel of QPR, while the positivist philosophy deals with problem-solving and the testing of the theories derived to test these understandings. It is also not design research, in which IT artifacts are designed to improve processes. Models and prototypes are frequently the products of design research. First, in QPR, the models employed are most often causal models whereas design research places its stress on ontological models. Second, there is also the difference that QPR validates its findings through data whereas design research can find acceptable validation of a new design through a mathematical proof of concept. Nevertheless, it should be noted that design researchers are increasingly using QPR, specifically experimentation, to validate their models and prototypes so QPR is also becoming a key tool in the arsenal of design researchers.

To the qualitative researcher, a phenomenon can best be interpreted by studying speech acts, relationships between people and computers, archival documents, diagrams of the workplace, and the like. If a qualitative researcher believes that these sources of data and the techniques such as interviewing that are used to gather the data can be rendered into numbers, then this researcher would be classified as a qualitative, positivist researcher in Michael Myers' classification scheme for qualitative research.  

1.6 QPR Epistemology and Ontology
The underlying view of nature that leads a scholar to conclude that QPR can produce knowledge is that the world has an objective reality that can be captured and translated into testable hypotheses, usually in the form of statistical or other numerical analyses. The original inspiration for this came from the scientific epistemology of logical positivism that was developed by the Vienna Circle of Positivists, mostly Karl Popper, during the 1920s and 1930s. This "pure" positivist attempt at viewing scientific exploration as a search for the Truth has been replaced in recent years with the recognition that untimately all measurement is based on theory and hence capturing an "objective" truth is impossible. Even the measurement of a purely physical attribute, such as temperature, depends on the theory of how materials expand in heat. Hence interpreting the readings of a thermometer cannot be regarded as a pure observation but itself as an instance of theory.

In recent years, there have been efforts to even combine the techniques and viewpoints of positivists and non-positivists to triangulate on phenomena (Kaplan and Duchon, 1988). Lacity and Janson (1994) argue that both approaches can be viable, and both can be shown to be valid for their circumstances.

At the heart of the positivist mind frame is the concept of deduction. There are four steps in deduction:
  1. Testing internal consistency, i.e., verifying that there are no internal contradictions.
  2. Distinguishing between the logical basics of the theory and its empirical, testable, predictions.
  3. Comparison with existing theory, showing that the new theory advances knowledge. Specifically, it is necessary to show that the new theory has superior empirical substance and hence more predictive power.
  4. Empirical testing aimed at falsifying the theory with data. When the data do not contradict the hypothesized predictions of the theory, it is temporarily corroborate. The objective of this test is to falsify, not to verify, the predictions of the theory. Verifications can be found for almost any theory if one can pick and choose what to look at.
The qualitative researcher in contrast tends to see the world as a social construction that will demonstrate large variance depending on the observer and the interpreter of the phenomenon. Reality is usually seen as highly subjective by a qualitative researcher.

Saying that QPR tends to see the world as having an objective reality is not equivalent to saying that QPR assumes that constructs and measures of these constructs are moving toward perfection over the years. In fact, Cook and Campbell (1979) make the point repeatedly that QPR will always fall short of the mark of perfect representation. For this reason, they argue for a "critical-realist" perspective, positing that "causal relationships cannot be perceived with total accuracy by our imperfect sensory and intellective capacities" (p. 29).

There are many ontologies or typologies of QPR. We offer one ourselves in the next section, in fact. The important point to remember about these ontologies is that research methods are not naturally occurring artifacts. Distinctions between them will be socially constructed, on the one hand, or based on practice, on the other. Researchers need to know something about the capabilities of these methods so that they can match them to their research problems and evaluate them when they are asked to review. Otherwise, these are distinctions without a difference that matters. At any rate, it is imperative to recognize that any observation is itself inherently based on theory.

1.7 Caveats
This Website focuses on the most common QPR types of within the IS community. There are many other types of quantitative research that we can only gloss over here. This is not to suggest in any way that these methods and tools cannot be invaluable to an IS researcher. Only that they are not as common.

Please send suggestions for improvement to the Section Co-Editors at: dstraub@gsu.edu, gefend@dredxel.edu and mcboudre@terry.uga.edu.

Citation information: Electronic source: Straub, Detmar, David Gefen, and Marie-Claude Boudreau (2004). "The ISWorld Quantitative, Positivist Research Methods Website," (Ed) Dennis Galletta, http://www.dstraub.cis.gsu.edu:88/quant/. Last updated: January 7, 2005."