13.Qualitative03.Mixed methods design - sporedata/researchdesigneR Wiki

1. Use cases: in which situations should I use this method?


1.1 The qualitative portion of mixed methods are used in situations where the research team intends to have an in-depth understanding of the research problem from the perspective of research participants (patients and other stakeholders) by the analysis of qualitative material (transcripts from interviews or focus groups, ethnographic observations, etc). The end product of the qualitative portion are emerging themes.


1.2 The quantitative portion of mixed methods are material such as surveys, cohort studies, randomized trials, etc. In the end, we will establish the association between results from these materials and the emerging themes from the qualitative portion.

2. Input: what kind of data does the method require?


2.1 Text obtained from participants' interviews, focus groups, or ethnographic observations. Of importance, ethnographic observations could be an addition to the interviews.


2.2 Results from surveys

3. Algorithm: how does the method work?

Model mechanics


  • Mixed methods research will often make discoveries in the form of emerging themes obtained through qualitative methods (focus groups, interviews, ethnographic observations), and those themes are then tested using hypothesis-driven, quantitative studies such as surveys, association or causal studies.
  • The focus of the qualitative component is to uncover new facts but without establishing how generalizable they are.
  • A qualitative analysis will involve the identification of emerging themes through a Grounded Theory framework [1], displayed using a circular plot demonstrating the connections among emerging themes. Grounded theory describes how participants perceive, reflect, and attribute value to experiences they have undergone, specifically allowing participants to express their opinions in face of each question.


  • The quantitative component will usually evaluate how generalizable new facts are.
  • Latent Dirichlet Allocation (LDA) and sentiment analysis are more advanced machine learning methods that can assist in the identification and characterization of emerging themes with very large, qualitative corpora. - see Using Latent Dirichlet Allocation to analyse qualitative survey data

Reporting guidelines

Data science packages

Suggested companion methods

  • Whenever possible, qualitative methods should be used prior to quantitative methods, because they allow us to learn things beyond what we currently know. Whereas quantitative methods are usually used to test hypothesis.

Learning materials

  1. Books
  2. Articles

4. Output: how do I interpret this method's results?

Mock conclusions or most frequent format for conclusions reached at the end of a typical analysis.

Tables, plots, and their interpretation

5. SporeData-specific


Data science functions


[1] Charmaz K. Constructing Grounded Theory. 2014

⚠️ **GitHub.com Fallback** ⚠️