Research in human sciences traditionally consists in two separate (if not opposed) research traditions and methods: qualitative versus quantitative research. The two methods rely on fundamentally different worldviews (they usually differ on their ontological, epistemological, axiological and methodological assumptions; see Johnson & Onwuegbuzie, 2004; Rossman & Wilson, 1985; Smith, 1983). Despite of – and even building upon – these differences, a third approach, consisting of merging the two approaches, has gained much popularity in the last 30 years, and henceforth stands out as a mean to bridge the gap between these two research traditions (Creswell & Plano Clark, 2011; Tashakkori & Teddlie, 2010).
As suggested by its name, quantitative (QUAN) methods rely on numbers, quantitative data, or defined categories. QUAN research follows a top-down (deductive) approach where theory/hypothesis testing is the driving force of research, and shapes data collection. Studies are conducted to predict variables of interest in order to understand specific relationships and quantify their strength or reliability. Researchers’ subjectivity should not impact research results, and is considered as noise in the data that should imperatively be neutralized. As such QUAN approaches aim to reduce the quantity of information to produce precise, parsimonious and generalizable models.
On the opposite, qualitative (QUAL) methods rely on non-numeric contents (texts, audio recordings, videos, pictures, etc.). QUAL research follows a bottom-up (inductive) approach where data guide the research process. Previous theories generally do not drive data collection and hypotheses generation, but instead serve as a reference point to which emerging results are compared. QUAL studies aim to conduct a detailed and in-depth analysis of the process of a given phenomenon and how individuals experience or attribute meaning to this phenomenon. QUAL approaches aim to shed light on the complexity of the phenomenon of interest in a given group of individuals, in a specific context. Contrary to QUAN approaches, researchers’ subjectivity plays an important and acknowledged role in QUAL research. As such, QUAL researchers consider that there is no single objective reality to study and unveil, but rather multiple co-constructed subjective realities that may coexist.
Because it relies on empirical studies and theory-driven hypothesis testing, the QUAN approach is known to be systematic and more structured than QUAL research. However, QUAN research is sometimes too rigid, and can neglect relevant research topics or ideas that would not arise from theoretical predictions. On the opposite, given that researchers put the emphasis on reaching detailed description of the phenomenon of interest instead of testing theoretically-derived hypotheses, the QUAL approach is significantly more flexible. The latter is nevertheless criticized for its lack of systematicity and generalizability, and its sensitivity to researchers’ subjectivity. Despite their differences, both approaches nevertheless share some common characteristics and many distinguished scholars argued against a stubborn and systematic opposition between QUAL and QUAN research paradigms. As stated by the eminent statistician John Tukey, «Neither exploratory nor confirmatory is sufficient alone. To try replace either by the other is madness. We need them both.» (Tukey, 1980, p.23). Indeed, both QUAL and QUAN approaches rely on empirical observations, describe their data, derive explanatory arguments and try to identify mechanisms underlying their results (Sechrest & Sidani, 1995). In addition, they both involve strategies to acknowledge and reduce biases in the research process. Building on these common grounds, mixed-methods aim at pragmatically intertwining the two approaches by combining their strengths and overcoming their respective shortcomings to reach a rigorous understanding and analysis of the phenomenon of interest (Jick, 1979).
Creswell and Plano Clark (2011) specify six central characteristics of mixed methods:
- Rigorously collecting and analyzing both QUAL and QUAN data;
- Mixing, integrating or linking the two types of data, combining them simultaneously, sequentially or embedding one of them into the other;
- Giving priority to one form of data over the other, depending on the research question;
- Using these procedures in a single study or in sequential phases of a more complex study program;
- Contextualizing the research within both philosophical and theoretical frameworks;
- Combining these procedures into a specific research design guiding the development of the study.
Accordingly, researchers often use mixed methods when one single type of data does not suffice to give a comprehensive answer to the research question. This is for instance the case when researchers (a) want to know if results obtained from two difference perspectives and methods converge (see for example Bowling & Gabriel, 2004); (b) use QUAN methods as the first part of their study, then follow up with QUAL methods to explain or refine the QUAN results (e.g., Carpentieri et al., 2017); or (c) use QUAL methods as the first part of their study to explore a new topic of interest, then follow up with QUAN methods and hypotheses generated from the first QUAL results (e.g., De Vriendt et al., 2012, 2013; Jopp et al., 2015). More broadly, mixed-methods are particularly suitable for the following research objectives (see Greene et al., 1989):
- Complementarity and completeness: Multiple sources and types of data may provide a better answer to the research question than QUAN or QUAL separately
- Explanation: Explaining initial results
- Generalizability: Generalizing exploratory results
- Triangulation: Elucidating whether different methods yield similar results
- Initiation: Highlighting unexpected or contradictory results between the two methods, and adopting new perspectives or theoretical frameworks to make sense of the results pattern
- Expansion: Reaching a research goal through multiple research/study phases involving various methodologies
- Focus on structure vs. processes: the QUAN approach investigates the structure of the phenomenon of interest, while the QUAL approach investigates its underlying processes.
Within the NCCR LIVES, Barbeiro and Spini (2015) proposed a calendar interview device (CID) as a mixed-methods device to study life course and turning points in the context of migration. This methodological approach enables the authors to study agency within structures in the lives of migrants. The CID consisted in the joint collection of life calendars containing standardized data and audio-recorded narratives for qualitative analysis. Interviews provide an opportunity to gain an in-depth understanding of the processes at stake in migrants’ trajectories and how they make sense of this experience, while quantitative calendar data provide a detailed resource for specific case analysis. Hence, the combination of both QUAL and QUAN data in the context of life calendars allows for identifying both objective and subjective dimensions of turning points in participants’ lives (also see Legewie & Tucci, 2020). And what is more, conjointly collecting both types of data improves the quality and accuracy of data as potential inconsistencies between data sources (e.g. dates provided in the calendar section sometimes did not match the duration of employment as explained during the interviews) were resolved by discussion between the interviewer and the interviewee.
Authors: Emilie Joly-Burra, Oana Ciobanu, Paolo Ghisletta
Barbeiro, A., & Spini, D. (2015). Calendar interviewing: A mixed methods device for a life course approach to migration. https://doi.org/10.12682/LIVES.2296-1658.2015.39
Bowling, A., & Gabriel, Z. (2004). An Integrational Model of Quality of Life in Older Age. Results from the ESRC/MRC HSRC Quality of Life Survey in Britain. Social Indicators Research, 69(1), 1–36. https://doi.org/10.1023/B:SOCI.0000032656.01524.07
Carpentieri, J. D., Elliott, J., Brett, C. E., & Deary, I. J. (2017). Adapting to Aging: Older People Talk About Their Use of Selection, Optimization, and Compensation to Maximize Well-being in the Context of Physical Decline. The Journals of Gerontology. Series B, Psychological Sciences and Social Sciences, 72(2), 351–361. https://doi.org/10.1093/geronb/gbw132
Creswell, J. W., & Plano Clark, V. L. (2011). Designing and Conducting Mixed Methods Research. SAGE.
De Vriendt, P., Gorus, E., Cornelis, E., Bautmans, I., Petrovic, M., & Mets, T. (2013). The advanced activities of daily living: A tool allowing the evaluation of subtle functional decline in mild cognitive impairment. The Journal of Nutrition, Health & Aging, 17(1), 64–71. https://doi.org/10.1007/s12603-012-0381-9
De Vriendt, P., Gorus, E., Cornelis, E., Velghe, A., Petrovic, M., & Mets, T. (2012). The process of decline in advanced activities of daily living: A qualitative explorative study in mild cognitive impairment. International Psychogeriatrics, 24(6), 974–986. https://doi.org/10.1017/S1041610211002766
Greene, J. C., Caracelli, V. J., & Graham, W. F. (1989). Toward a Conceptual Framework for Mixed-Method Evaluation Designs. Educational Evaluation and Policy Analysis, 11(3), 255–274. JSTOR. https://doi.org/10.2307/1163620
Jick, T. D. (1979). Mixing Qualitative and Quantitative Methods: Triangulation in Action. Administrative Science Quarterly, 24(4), 602–611. JSTOR. https://doi.org/10.2307/2392366
Johnson, R. B., & Onwuegbuzie, A. J. (2004). Mixed Methods Research: A Research Paradigm Whose Time Has Come. Educational Researcher, 33(7), 14–26. https://doi.org/10.3102/0013189X033007014
Jopp, D., Wozniak, D., Damarin, A. K., De Feo, M., Jung, S., & Jeswani, S. (2015). How could lay perspectives on successful aging complement scientific theory? Findings from a u.s. And a German life-span sample. The Gerontologist, 55(1), 91–106. https://doi.org/10.1093/geront/gnu059
Legewie, N., & Tucci, I. (2020). Studying turning points in labour market trajectories – benefits of a panel-based mixed methods design. Longitudinal and Life Course Studies, first online. https://doi.org/10.1332/175795920X15949756176915
Rossman, G. B., & Wilson, B. L. (1985). Numbers and Words: Combining Quantitative and Qualitative Methods in a Single Large-Scale Evaluation Study. Evaluation Review, 9(5), 627–643. https://doi.org/10.1177/0193841X8500900505
Sechrest, L., & Sidani, S. (1995). Quantitative and qualitative methods: Is there an alternative? Evaluation and Program Planning, 18(1), 77–87. https://doi.org/10.1016/0149-7189(94)00051-X
Smith, J. K. (1983). Quantitative Versus Qualitative Research: An Attempt to Clarify the Issue. Educational Researcher, 12(3), 6–13. https://doi.org/10.3102/0013189X012003006
Tashakkori, A., & Teddlie, C. (2010). SAGE Handbook of Mixed Methods in Social & Behavioral Research. SAGE.
Tukey, J. W. (1980). We Need Both Exploratory and Confirmatory. The American Statistician, 34(1), 23‑25. https://doi.org/10.1080/00031305.1980.10482706
Semantic network visualisation
Click to activate zoom- and drag-fonctionnality (scroll to zoom, drag nodes to move, click and hold nodes to open next level)