image

WP Series » WP Series 2007

Vink, Maarten and Olaf van Vliet. 2007. "Not Quite Crisp, Not Yet Fuzzy?... Assessing the Potentials and Pitfalls of Multi-Value QCA". COMPASSS WP Series 2007-52. Published online 27 November 2007.
Available from: http:\\www.compasss.org\wpseries\VinkVanVliet2007.pdf.
NB: Published in Field Methods, see bibliography

Abstract: This paper assesses the strengths and shortcomings of multi-value Qualitative Comparative Analysis (mvQCA) a comparative technique for small to medium size datasets that has been integrated in the TOSMANA software developed by Lasse Cronqvist. Its main difference with Charles Ragin's 'crisp-set' QCA (csQCA) which only allows for conditions with 0 or B values, is that the dataset can also contain causal conditions with three or more categories. MvQCA thus avoids relatively crude dichotomization and arguably better captures the richness of information of the raw data. Unlike 'fuzzy-set' QCA (fsQCA), developed by Ragin to go beyond the classic dichotomous approach, mvQCA is still based on dichotomous outcomes and applies Boolean minimization principles in a similar way to csQCA. Its major advantage, according to its proponents, is that it deals better with the classic QCA problem of contradictory configurations where cases with the same explanatory characteristics display different outcomes and in principle cannot be taken into account for logical minimization. We discuss the logical status of mvQCA, its impact on limited diversity, and present a re-analysis of a recent paper to show how mvQCA uses threshold-setting to solve contradictions.

Wagemann, Claudius and Carsten Schneider. 2007. "Standards of Good Practice in Qualitative Comparative Analysis and Fuzzy-Sets". COMPASSS WP Series 2007-51. Published online 4 November 2007.
Available from: http:\\www.compasss.org\wpseries\WagemannSchneider2007.pdf.

Abstract: Over the last couple of years, we witness an increasing curiosity for a methodological family, generally identified with its acronym, 'QCA'. This stands for 'Qualitative Comparative Analysis', which was introduced for the first time to a wider public by the American social scientist Charles Ragin in 1987 (1987). Since then, QCA has been modified, extended and improved several times (Ragin 2000; Ragin 2003b; Ragin 2006a Ragin 2006b; and Ragin and Sonnett 2004). These developments have contributed to a better applicability of QCA to empirical social scientific research questions and to its prominence within the discipline. In this article, we will, first, present the 'state of the art' of QCA and will introduce both its basic principles and the different variants of this group of 'Configurational Comparative Methods' (a term coined by Rihoux and Ragin 2007a, which might probably substitute 'Qualitative Comparative Analysis' in the long run). After this, we will propose a list of criteria for a 'good' QCA analysis. We hope that our contribution can be a guideline for QCA users as to which aspects have to be considered when carrying out QCA analyses in order to render them not only technically correct, but also to make the best out of the analytically relevant information one can generate with QCA. Furthermore, the standard of good practice which we propose can also be a helpful instrument for readers and commentators when they have to evaluate empirical analyses based on QCA techniques.

Dusa, Adrian. 2007. "QCA Graphical User Interface Manual". COMPASSS WP Series 2007-50. Published online 7 October 2007.
Available from: http:\\www.compasss.org\wpseries\Dusa2007c.pdf.
NB: Published in Journal of Business Research, see bibliography; update of WP 2006-41.

Abstract: This manual is intended for scholars wishing to use QCA in an R environment. It includes visualisation and factorisation functions, along with all other basic QCA functions. QCAGUI is a graphical user interface (GUI) for the QCA package, derived from R Commander. Because QCA has little to do with statistics, the menus from Rcmdr were stripped down to the very basics. In crisp sets QCA, data is binary therefore it is fairly decent to treat it as categorical (1 - presence; 0 - absence). In order to ease the primary analysis (e.g. tables of frequencies) and the creation of basic graphs, this package activates some menus that are not available in Rcmdr but for factors. Users should be aware, however, that QCAGUI is not a package for statistics; Rcmdr is better for this purpose. Updates of the QCA packages can be followed on the R webpage.

Dusa, Adrian. 2007. "Enhancing Quine-McCluskey". COMPASSS WP Series 2007-49. Published online 5 October 2007.
Available from: http:\\www.compasss.org\wpseries\Dusa2007b.pdf.

Abstract: Currently, the only algorithm that yields an exact solution to the Boolean minimization problem is the well known Quine-McCluskey, but almost all software solutions employ different implementations because of its two fundamental weaknesses: it is memory hungry and slow for a large number of causal conditions. This paper proposes an alternative to the classical Quine-McCluskey algorithm, one that addresses both problems, and especially the one of memory consumption. The solutions of this new algorithm are also exact, but they are produced not by following the cumbersome classical algorithm but using a more direct and faster approach. Memory restrictions limit the number of input variables (causal conditions) at a ceiling of about 14 or 15 (because each new variable expands the memory usage in a geometric proportion), where this alternative uses only a very small fraction of memory and it can process about 20 input variables with acceptable speed.

Stokke, Olav. 2007. "Qualitative Comparative Analysis, Shaming, and International Regime Effectiveness". COMPASSS WP Series 2007-48. Published online 3 October 2007.
Available from: http:\\www.compasss.org\wpseries\Stokke2007.pdf.
NB: Published in Journal of Business Research, see bibliography; update of WP 2003-5.

Abstract: The article presents and applies a set-theoretic comparative technique, qualitative comparative analysis (QCA), to a string of case studies on shaming as a strategy for improving the effectiveness of international regimes for resource management. This technique is particularly attractive when the number of cases available is greater than the researcher can reliably handle by narrative comparison, yet too low to support statistical procedures. QCA can capture causal conjunctions, even in small-to-intermediate-N situations, primarily because it permits the introduction of simplifying assumptions in a way that maintains a clear connection to the underlying cases - thus allowing substantive evaluation of their plausibility. A more recent fuzzy-set version lifts two limitations of the crisp-set version of QCA examined here (i.e., that variables must be dichotomous, and that the analysis makes no allowance for measurement error and non-modeled causality).

Gjølberg, Maria. 2007. "The Origin of Corporate Social Responisbility: Global Forces or National Legacies?". COMPASSS WP Series 2007-47. Published online 2 August 2007.
Available from: http:\\www.compasss.org\wpseries\Gjolberg2007.pdf.
NB: Published in Socio-Economic Review, see bibliography

Abstract: This article explores the relative importance of global forces and national political-economic institutions for companies' inclination and ability to engage in initiatives promoting Corporate Social Responsibility (CSR). The globalist hypothesis postulates the CSR efforts of a given company as a function of necessities dictated by the global market place: strong anti-globalisation and anti-corporate sentiments create a need for a positive reputation in order to obtain a "social licence to operate". The institutionalist hypothesis postulates the CSR efforts of a given company as a function of institutional factors in the national, political-economic system: companies based in certain political economic systems have comparative institutional advantages for success in CSR. The hypotheses are examined quantitatively by testing an index of national CSR-performance against a wide variety of political-economic indicators. The final analysis, based on Qualitative Comparative Analysis (QCA), reveals causal heterogeneity and indicates two separate roads leading to CSR success.

Dusa, Adrian. 2007. "A Mathematical Approach to the Boolean Minimization Problem". COMPASSS WP Series 2007-46. Published online 8 March 2007.
Available from: http:\\www.compasss.org\wpseries\Dusa2007a.pdf.
NB: Published in Quality and Quantity, see bibliography

Abstract: Any minimization problem involves a computer algorithm. Many such algorithms have been developed for the Boolean minimizations, in diverse areas from computer science to social sciences (with the famous QCA algorithm). For a small number of entries (conditions in the QCA) any such algorithm will find a minimal solution, especially with the aid of the modern computers. However, for a large number of conditions a quick and complete solution is not easy to find using an algorithmic approach, due to the extremely large space of possible combinations to search in. In this article I will demonstrate a simple alternative solution, a mathematical method to obtain all possible minimized prime implicants. This method is not only easier to understand than other complex algorithms, but it could prove to be a faster method to obtain an exact and complete Boolean solution.

Ragin, Charles and Sarah Strand. 2007. "Using QCA to Study Causal Order: Comment on Caren and Panofsky (2005)". COMPASSS WP Series 2007-45. Published online 25 January 2007.
Available from: http:\\www.compasss.org\wpseries\RaginStrand2007.pdf.
NB: Published in Sociological Methods & Research, see bibliography

Abstract: The goal of qualitative comparative analysis (QCA) is to identify the different combinations of causally relevant conditions linked to an outcome. The researcher typically focuses on a qualitative outcome and seeks to identify the different conjunctural conditions that generate it. In this way QCA allows for causal complexity--for the possibility that no single cause may be either necessary or INUS sufficient. Instead causes are viewed as conditions: insufficient but necessary components of unnecessary but sufficient combinations of conditions (Mackie 1965). Caren and Panofsky (2005) seek to advance QCA by demonstrating that it can be used to study causal conditions that occur in sequences and introduce a technique they call TQCA (temporal qualitative comparative analysis). In their sequence formulation the causal conjuncture is a of conditions or events. While we applaud their effort, in this comment we seek to clarify aspects of their analysis and to present a generalization of the approach that is more amenable to truth table analysis and use of existing software, fsQCA (Ragin 1987; 2000; Ragin, Drass, and Davies 2006). Our first task is to correct what appear to be errors of omission in their analysis. Specifically, they seem to have stopped the process of logical minimization short of completion. We show that it is possible to produce a logically simpler solution than the one they present, while still remaining true to the principles they advocate. Our second task is to demonstrate how to use fsQCA to implement a generalization of their procedure. This procedure takes advantage of an under-utilized feature of fsQCA software, namely, the facility in crisp-set analyses to code a causal condition not only as "present" versus "absent," but also as "irrelevant." The coding of "irrelevant" is especially important in analyses of event sequences, where event order is relevant only if the events actually occur. Thus, the question, "Which came first, event A or event B?" is relevant only if both A and B are coded "present."

Ragin, Charles. 2007. "Fuzzy Sets: Calibration Versus Measurement". COMPASSS WP Series 2007-44. Published online 25 January 2007.
Available from: http:\\www.compasss.org\wpseries\Ragin2007.pdf.

Abstract: This essay explores the connections between measurement and calibration in the social sciences and addresses its long-standing neglect. My starting point is the contrast between conventional approaches to measurement in quantitative and qualitative social research. After sketching common measurement practices in both types of research, I argue that a useful way for social scientists to incorporate measurement calibration into their research is through the use of fuzzy sets. In order to use fuzzy sets effectively, researchers must assess the degree of membership of cases in well defined sets (e.g., degree of membership in the set of "developed countries"). This requirement forces researchers to attend to the issue of calibration and provides additional motivation for them to explore the conceptual underpinnings of their measures. Fuzzy sets resonate with the measurement concerns of qualitative researchers, where the goal often is to distinguish between relevant and irrelevant variation--that is, to interpret it--and with the measurement concerns of quantitative researchers, where the goal is the precise placement of cases relative to each other. The second half of this essay sketches a technique for calibrating conventional interval- and ratio-scale variables according to external standards. In the examples provided, the external standard used is a qualitative assessment of the degree to which cases with given scores on a conventional interval-scale measure are members of a target set. A simple estimation technique rescales the interval-scale measure so that it conforms to these qualitative assessments. The end product of this procedure is the calibration of the degree of membership of cases in sets, which in turn is suitable for fuzzy-set and other types of analysis. The examples illustrate the responsiveness of this calibration technique to the researcher's qualitative assessments of cases. While calibration in the social sciences is unlikely ever to match the sophistication of calibration in the physical sciences, the technique of qualitative calibration presented here is an important first step.


compasss.org© - Page last modified 08.05.2012 19:24:53