Necessary Condition Analysis: Theory and Practice Summer School
The goals of this hands-on course (2 consecutive days) are the following:
- To gain a deep understanding of the logic of necessary conditions, and why these are important for social science and practice;
- To be able to identify necessary conditions in (own) data sets;
- To be able to combine NCA with other research methods (e.g., regression, QCA);
- To be able to report the results in an academic work (papers, articles, PhD thesis) in a convincing and attractive way.
What is a necessary condition?
A necessary condition is a critical determinant of an outcome: if the condition is not in place the outcome will not occur. A student will not be admitted to a PhD program when the GMAT score is too low, creativity will not exist without intelligence, and organizational change will not occur without management commitment. Such single conditions can be a bottleneck for the outcome. If the necessary condition is not in place there is guaranteed failure, and this cannot be compensated by other determinants. But when the condition is in place there is no guaranteed success. The condition is necessary but not sufficient. To prevent failure, each single necessary condition must be in place. Necessary Condition Analysis (NCA) provides the logic and a methodological tool for identifying necessary conditions in different datasets.
Why is NCA important?
Necessary (but not sufficient) conditions are widespread in real life and therefore relevant to various research areas, such as management, business research, sociology, and psychology. But until recently no technique was available to identify necessary conditions in datasets. Traditional (regression based) data analysis techniques fail to do so, even though they are frequently applied for exactly that matter. Necessary Condition Analysis (NCA) is a new technique that can do the job (Dul 2016).
Whom is NCA for?
NCA is applicable to any discipline, and can provide strong results even when other analyses such as regression analysis show no or weak effects. By adding a different logic and data analysis approach, NCA adds both rigor and relevance to theory, data analysis, and publications. NCA is a straightforward and user-friendly method that requires no advanced statistical or methodological knowledge beforehand. It can be used in both quantitative research as well as in qualitative research.
Recently, NCA papers have appeared in fields such as (industrial) psychology, operations management, information sciences, finance, strategy, entrepreneurship, organizational behavior, and human resourse management. Examples include a paper by Karwowski et al. (2016) showing that intelligence is necessary for creativity, and paper by Van der Valk et al. showing that trust and contracts are necessary for successful collaboration between companies for innovation. In other papers NCA is used to complement regression analysis (e.g. De Vries et al. 2017) or to complement QCA (Lesrado et al., 2016).
Applying NCA has three main advantages:
- It provides new substantive insights in social science phenomena (expressed as necessity rather than average trend); using NCA provides an alternative perspective, may enhance existing research, or falsify theories;
- It has great practical meaning because identified necessary condition must always be put and kept in place
- Journal editors and reviewers appreciate that authors use a new solid methodology that provides new insights and contributes to academic rigor and practical relevance.
What editors said about NCA?
- “From my perspective, it is the most interesting paper I have handled at this journal, insofar as it really represents a new way to think about data analyses"
- “I just added the paper to the required reading list for my doctoral-level seminar on research methods”
- “This is a fine paper, employing a novel methodology”
- “I believe the paper holds the potential to be widely cited and to change how organizational researchers approach testing for cause and effect relationships”
What participants of this course said about NCA?
- “Simple technique that requires no ‘preparation’, data transformation/manipulation/ correction. A perfect plug-and-play method that can give output in under 10 minutes”
- “It’s a new way of thinking and therefore it may lead to many interesting insights, just reanalyzing old dataset”
- “Analysis provides insights that cannot be obtained with another method”
- “Insights are very relevant for practice”
- “I do believe that is has great exploratory value that is congruent with recent emphasis on big data”
Who can attend the course?
The course is primarily open to PhD candidates and junior faculty, but also other researchers (including master students and senior faculty) who are interested in this novel approach are welcome. It is expected that each participant has at least some experience with traditional regression analysis to understand the differences between NCA and regression, and to appreciate how NCA complements regression. Also researchers with a background in Qualitative Comparative Analysis (QCA) can benefit from the course to appreciate how NCA complements QCA. No special methodological or substantive knowledge is required for this course. Examples will be drawn from many different (business) fields. Each participant is expected to bring a laptop computer with a Windows (Microsoft) or IOS (Apple) operating system. The exercises with the NCA software (in R) can be done without prior programming knowledge or experience.
What is the content of the course?
The course consists of four parts:
1. Individual preparations to be done before the course (approximately 16 hours)
- Participant reads literature about necessary conditions (reader)
- Participant installs the NCA software on own laptop (detailed instructions will be provided)
- Participant makes an individual assignment (linked to own research area and own data set)
2. Class 1 (day 1) (approximately 8 hours)
- The logic of necessary conditions
- Format: lecture with class discussions
- Content: differences between necessity and sufficiency
- Data analysis for identifying necessity conditions
- Format: lecture with class discussions
- Content: principles of NCA, comparison NCA with regression analysis, comparison NCA with QCA (Qualitative Comparative Analysis)
3. Class 2 (day2) (approximately 8 hours)
- Applying NCA to an example dataset
- Format: Participants works on own laptop with assistance by lecturer, and class discussions
- Content: calculate ceiling line, effect size, accuracy, inefficiency, bottleneck table, interpretation of results, handling of problematic or unusual cases, practical issues to pay attention to
- Necessary conditions in own research area and in own data set (or personally selected dataset)
4. Final Assignment (approximately 24 hours)
- Write a short paper about testing a necessary condition hypothesis with NCA using own dataset (or a personally selected existing dataset): Introduction, Methods, Results, Discussion.
Reader “Introduction to NCA”, NCA software (will be provided)
Dul, J. (2016). Necessary Condition Analysis (NCA): Logic and Methodology of “Necessary But Not Sufficient” Causality. Organizational Research Methods, 19(1), 10-52. (free access)
Karwowski, M., Dul, J., Gralewski, J., Jauk, E., Jankowska, D.M., Gajda, A., Chruszczewski, M.H., Benedek, M. (2016). Is creativity without intelligence possible? A Necessary Condition Analysis, Intelligence 57, 105-117.
Van der Valk, Sumo, R., Dul, J. & Schroeder, R. (2016). When are contracts and trust necessary for innovation in buyer-supplier relationships? A Necessary Condition Analysis. Journal of Purchasing and Supply Management, 22(4), 266-277.
For the timetable of this course, please click here.
To register, ERIM participants can take the following steps:
1. Go to SIN Online and log in with your ERNA credentials if required.
2. Click in the checkbox next to the course title and click Save Changes.
3. Your registration is complete. You will receive an automatic confirmation e-mail.
External (non-ERIM) participants are welcome to this course. To register, please fill in the registration form and e-mail it to email@example.com by 4 weeks prior to the start of the course. Please note that the number of places for this course is limited.
This course is free of charge for ERIM members (faculty members, PhD candidates and Research Master students). For external participants, the course fee is 250 euro per ECTS credit.