The Cathie Marsh Centre for Census and Survey Research

Fuzzy Set Analysis

Dates:

4th June 2010,

7th June 2011

Duration: 1 day (10am-4:30pm)

Level: Introductory

Course Fee: £175 (£125 for those from educational institutions)

CCSR offer 5 free places to research staff and students within the Faculty of Humanities at the University of Manchester.

Course Leader: Wendy Olsen

Course Requirements: None, although a strong knowledge of Windows software is highly recommended. If in doubt, the European Computer Driving License is an accepted standard.

Fuzzy sets can deliver three sets of results: 1) data reduction, where from 3 to 6 variables are reduced to one; 2) causal analysis, both within the set of cases and aiming at inference to a population; and 3) a separation of necessary cause from sufficient cause, taking into account mixtures of causes rather than having a linear separation of each cause. Fuzzy sets are a way of introducing orderings into any table of data. Each case is ranked (or calibrated) on its membership in sets (e.g. the set of chronically poor households.) We then study causality using fsQCA software or STATA “fuzzy” command. Tests of sufficient causality and of necessary causality are conducted separately. The method is suited to research with a medium-N scale, i.e. from 8 to 200 cases, and for comparative research. The workshop teaches how to create fuzzy sets, and analyse them causally. The result is a simplified summary of the multiple causal pathways present in the data.

Course Summary

This course aims to:

- Introduce concepts of fuzzy and crisp sets

- Study causality using truth tables

- Calibrate ranked data

- Reduce truth tables using Boolean algebra

- Study causality using fuzzy set data

Learning Outcomes

Students will learn to:

- Contrast fuzzy sets with other methods

- Explain the epistemology of causal analysis with fuzzy sets

- Use Boolean algebra with ordinal data

- Critically compare the expert knowledge of a statistician and a fuzzy set analyst

- Explain how a given level of one or more fuzzy sets can be a sufficient condition for a fuzzy outcome

Course Content

- Lecture on fuzzy sets in comparative research

- Practical on creating and calibrating fuzzy sets (uses SPSS and FS-QCA software)

- Lecture on Boolean algebra and reducing truth tables

- Practical on qualitative comparative analysis, using FS-QCA and Tosmana software

- Practical on analysing fuzzy set data using nested sorts (uses STATA software, Excel and STAT-Transfer)

Jointly useful course – The course on Qualitative Comparative Analysis can be studied independently of this course, but they are complementary. QCA studies the data matrix using binary variables only, i.e crisp sets. Fuzzy set analysis adds a ranked element into the recording of the qualitative membership in each set.

Source of background information: http:\\www.compasss.org for QCA and fuzzy set software.

Preliminary Reading

Ragin, C. (2000) Fuzzy Set Social Science, Chicago: University of Chicago Press.

Rihoux, B., and Grimm, H. (Eds.) (2006), Innovative Comparative Methods For Policy Analysis: Beyond the Quantitative-Qualitative Divide, Kluwer Academic Publishers.

Kvist, J. (2007) “Fuzzy Set Ideal Type Analysis”, Journal Of Business Research, 60 (5): 474-481.

Smithson, M., and Verkuilen, J. (2006), Fuzzy Set Theory: Applications in the Social Science,sSage Publications, Quantitative Applications in the Social Sciences Series.

C. Q. Schneider and C. Wagemann (2007) Qualitative Comparative Analysis (QCA) Und Fuzzy-Sets: ein Lehrbuch Für Anwender, , 287p., Verlag Barbara Budrich.


Home Staff Research Publications Masters' Study PhD Study Consultancy Short Courses Contact Search	Fuzzy Set Analysis Dates: 4th June 2010, 7th June 2011 Duration: 1 day (10am-4:30pm) Level: Introductory Course Fee: £175 (£125 for those from educational institutions) CCSR offer 5 free places to research staff and students within the Faculty of Humanities at the University of Manchester. Course Leader: Wendy Olsen Course Requirements: None, although a strong knowledge of Windows software is highly recommended. If in doubt, the European Computer Driving License is an accepted standard. Fuzzy sets can deliver three sets of results: 1) data reduction, where from 3 to 6 variables are reduced to one; 2) causal analysis, both within the set of cases and aiming at inference to a population; and 3) a separation of necessary cause from sufficient cause, taking into account mixtures of causes rather than having a linear separation of each cause. Fuzzy sets are a way of introducing orderings into any table of data. Each case is ranked (or calibrated) on its membership in sets (e.g. the set of chronically poor households.) We then study causality using fsQCA software or STATA “fuzzy” command. Tests of sufficient causality and of necessary causality are conducted separately. The method is suited to research with a medium-N scale, i.e. from 8 to 200 cases, and for comparative research. The workshop teaches how to create fuzzy sets, and analyse them causally. The result is a simplified summary of the multiple causal pathways present in the data. Course Summary This course aims to: - Introduce concepts of fuzzy and crisp sets - Study causality using truth tables - Calibrate ranked data - Reduce truth tables using Boolean algebra - Study causality using fuzzy set data Learning Outcomes Students will learn to: - Contrast fuzzy sets with other methods - Explain the epistemology of causal analysis with fuzzy sets - Use Boolean algebra with ordinal data - Critically compare the expert knowledge of a statistician and a fuzzy set analyst - Explain how a given level of one or more fuzzy sets can be a sufficient condition for a fuzzy outcome Course Content - Lecture on fuzzy sets in comparative research - Practical on creating and calibrating fuzzy sets (uses SPSS and FS-QCA software) - Lecture on Boolean algebra and reducing truth tables - Practical on qualitative comparative analysis, using FS-QCA and Tosmana software - Practical on analysing fuzzy set data using nested sorts (uses STATA software, Excel and STAT-Transfer) Jointly useful course – The course on Qualitative Comparative Analysis can be studied independently of this course, but they are complementary. QCA studies the data matrix using binary variables only, i.e crisp sets. Fuzzy set analysis adds a ranked element into the recording of the qualitative membership in each set. Source of background information: http:\\www.compasss.org for QCA and fuzzy set software. Preliminary Reading Ragin, C. (2000) Fuzzy Set Social Science, Chicago: University of Chicago Press. Rihoux, B., and Grimm, H. (Eds.) (2006), Innovative Comparative Methods For Policy Analysis: Beyond the Quantitative-Qualitative Divide, Kluwer Academic Publishers. Kvist, J. (2007) “Fuzzy Set Ideal Type Analysis”, Journal Of Business Research, 60 (5): 474-481. Smithson, M., and Verkuilen, J. (2006), Fuzzy Set Theory: Applications in the Social Science,sSage Publications, Quantitative Applications in the Social Sciences Series. C. Q. Schneider and C. Wagemann (2007) Qualitative Comparative Analysis (QCA) Und Fuzzy-Sets: ein Lehrbuch Für Anwender, , 287p., Verlag Barbara Budrich.