Yale Center for Teaching and Learning

Research Design

Education research usually begins with the formulation of a research question.  Researchers then design a study and select the appropriate methodology to investigate the question. Education research studies are usually classified into three research methods, each containing more specific research designs. 


Quantitative data is the process of using objective measurements and statistical, mathematical, or numerical analyses of data to explain a phenomenon. Questions are often focused on exploring relationships, making predictions, and examining group differences. Data can be collected from a sample and results are generalized to a larger population. The types of numerical quantitative data can be nominal (category based), ordinal (rank based), interval (numbers not based on absolute zero) and ratio (numbers with actual zero).[1] Quantitative research designs include:

  • Correlation Designs – Examine the relationship between two or more variables.
  • Causal Comparative Designs – Examine known differences between two or more groups and attempt to explain the cause of the differences.
  • Quasi-experimental Designs – Examine the impact of an intervention.  Unlike experimental designs, participants are not randomly sampled or selected into experimental conditions (i.e. treatment group vs control group).
  • Experimental Designs – Examine the impact of an intervention (i.e. learning activity, course, etc).


A qualitative research design centers on the analysis of non-numerically oriented data, which can include interviews, focus groups, case studies, video analysis, and the analysis of historical documents. Qualitative research is conducted: to understand the meaning, for participants in the study, of the events, situations, experiences and actions they are involved with or engage in; to understand the particular context within which the participants act, and the influence that this context has on their actions; to identify unanticipated phenomena and influences, and generating new, “grounded” theories; and to understand the processes by which events and actions take place. The data collection process is emergent and continues until saturation occurs. Data analysis is informed by one of several research traditions (Gall et al., 2007).

  • Narrative – Examines the meaning behind the lives, stories, and experiences of an individual
  • Case-study - The in-depth study of one or more instances of a phenomenon in its real-life context that reflects the perspective of the participants involved in the phenomenon
  • Phenomenology – Examines reality as it appears to individuals who experience a particular phenomenon
  • Symbolic Interactionism – Examines the influence of social interactions on social structures and individuals’ self-identity
  • Ethnography – Examines the characteristic features and patterns of a culture
  • Critical-theory – Examines power relationships within a culture
  • Grounded-theory – Develops an understanding of a phenomenon to inform the development of a theory
  • Action Research – Examines the self-reflective efforts of practitioners to improve the rationality and justice of their work


Mixed methods designs involve data collection using both quantitative and qualitative methodologies and can provide a more holistic view of the research questions, as both types of data can complement each other.


[1] https://www.nsf.gov/pubs/2002/nsf02057/nsf02057_4.pdf