Listed below are some example data sets that can imported into EvalC3 and analysed there. These and others (along with their source documents) can be found on the Compasss website, a repository for QCA studies.
The challenge:
- Can you replicate the results reported in the papers below?
- Can you improve on those results, in terms of the accuracy of the prediction model, the breadth of cases it covers, or its simplicity? Or on any other criteria that could be argued to be appropriate?
The datasets
These are arranged roughly by size of data set.
The Krook data set is the data set describing 26 African countries is built into EvalC3 as an example data set to play with.
- Welle et al (2015) Testing the Waters: A Qualitative Comparative Analysis of the Factors Affecting Success in Rendering Water Services Sustainable Based on ICT Reporting, June 2015. Itad. Water Aid, IRC.
- EvalC3-example-data-set-6-water-aid
- Outcome 1: 8 projects x 9 attributes and 1 outcome. Binary data
- Outcome 2: 8 projects x 7 attributes and 1 outcome. Binary data
- Outcome 3: 8 projects x 6 attributes and 1 outcome. Binary data
- EvalC3-example-data-set-6-water-aid
- Balthasar, A. (2006) “The Effects of Institutional Design on the Utilization of Evaluation.” Evaluation 12 (3):353-71.
- EC3 Example data set 8 Balthasar
- 10 institutions x 8 attributes and 1 outcome
- EC3 Example data set 8 Balthasar
- Ansorg, N. 2014. “Wars without Borders: Conditions for the Development of Regional Conflict Systems in Sub-Saharan Africa.” International Area Studies Review 17 (3):295-312.
- EC3 Example data set 7 Ansorg
- 12 regions x 7 attributes and 1 outcome. Binary data
- EC3 Example data set 7 Ansorg
- Krook, M.L., 2010. Women’s representation in parliament: A qualitative comparative analysis. Political Studies 58, 886–908.
- EvalC3-example-data-set-5
- 22 developed countries x 5 attributes of those countries and 1 outcome measure (% of women in parliament). Binary data.
- 26 African countries x 5 attributes of those countries and 1 outcome measure (% of women in parliament). Binary data.
- EvalC3-example-data-set-5
- Basedau, Matthias, and Thomas Richter. 2014. “Why do some Oil Exporters Experience Civil War but others do not? Investigating the Conditional Effects of Oil.” European Political Science Review 6 (4):549-74.
- EC3 Example data set 16 39 x 4 Basedau
- 39 cases x 4 attributes and 1 outcome
- EC3 Example data set 16 39 x 4 Basedau
- Blackman, Tim, Jonathan Wistow, and David Byrne. 2011. “A Qualitative Comparative Analysis of Factors Associated with Trends in Narrowing Health Inequalities in England.” Social Science & Medicine 72 (12):1965-74.
- EC3 Example data set 17 Blackman
- 27 cases x 10 attributes and 1 outcome
- 27 cases x 6 attributes and 1 outcome
- EC3 Example data set 17 Blackman
- A random data set
- EvalC3 example data set 9 Random
- 100 cases x 10 attributes and 1 outcome
- This data set can be useful as a comparator for processing speeds using different types of search.
- An exhaustive search for configurations took me 6 minutes on HP Pavillion 550 153a desktop
- An evolutionary search for configurations took me less than one minute on the same machine
- EvalC3 example data set 9 Random
- Bara, C (2014). “Incentives and Opportunities A Complexity-Oriented Explanation of Violent Ethnic Conflict.” Journal of Peace Research 51, no. 6 (November 1, 2014): 696–710.
-
- EvalC3-example-data-set-15-Bara
- 500 cases x 11 attributes and 1 outcome. Binary data
- I have found that EvalC3 struggles with this data set, especially when using exhaustive search. but this may depend a lot on the age and size of your computer
- EvalC3-example-data-set-15-Bara
- Itad&DFID (2015) Empowerment and Accountability macro-evaluation. See here for details of the evaluation and here for details of the data set
- EvalC3 -example-data-set-16-DFIDE&A
- 523 cases x 117 attributes
- EvalC3 -example-data-set-16-DFIDE&A