Skip to Main Content

Scholarship of Teaching and Learning guide

Data collection and analysis

"It is unethical to fail to explore one’s data to learn the lessons they can reveal." 

Melvin Mark, Kristen Eyssell & Bernadette Campbell (2004) 

Choosing your methods

Each of the research approaches (whether it’s qualitative, quantitative, or mixed) involves using one or more data collection methods. Choosing your data collection and analysis methods is closely linked to methodology and it is not possible to discuss one without the other. SoTL research is often informed by a social research approach, and this requires a rationale that clearly links methodology and methods. For example, if you were interested in researching how a particular cohort understands and enacts knowledge in a specific circumstance, you might choose ethnography as your methodology. As you are seeking to collect data that focuses on the cohort’s views, you might choose unstructured interviews as a data collection method.  

Common qualitative methods 

Data collection

These are some of the most common qualitative methods for data collection:  

  • Observations: recording what you have seen, heard, or encountered in detailed field notes. For example, a researcher visits various classrooms to observe teaching methods and student engagement levels. 
  • Interviews: personally asking people questions in one-on-one conversations. For example, a researcher interviews teaching academics who have recently incorporated generative AI learning into their courses. 
  • Focus groups: asking questions and generating discussion among a group of people. For example, the university wants to understand students' experiences with a newly introduced online learning management system. A group of students from diverse disciplines are invited to a focus group discussion where they share their likes, dislikes, and suggestions for the platform. 
  • Surveys: distributing questionnaires with open-ended questions. For example, An educator distributes a survey at the end of a semester with open-ended questions asking students to reflect on the most impactful learning activities and suggest areas for improvement in the course design. 
  • Secondary research: collecting existing data in the form of texts, images, audio or video recordings, etc. For example, a researcher is interested in studying the evolution of teaching methodologies over the past few decades. They gather and analyse existing lecture recordings, textbooks, syllabi, and course materials from past years to trace patterns and shifts in pedagogical strategies. 

Data analysis

These are some of the most common qualitative methods for data analysis: 

  • Content analysis: systematically decodes textual data into themes or patterns. For example, an educator analyzes feedback from several semesters of course evaluations to categorize recurring topics. 
  • Narrative analysis: interprets personal stories to understand individual experiences. For example, a researcher collects personal narratives from first-generation college students about their experiences in transitioning to higher education. 
  • Discourse analysis: examines language use in social contexts, highlighting power dynamics. For example, study examines the classroom dialogues in a humanities course to understand the power dynamics between the instructor and students. 
  • Thematic analysis: identifies and interprets patterns or themes in qualitative data. For example, interviews are conducted with faculty members about their perceptions of online teaching and the qualitative data is then analysed for themes (like technical challenges or peer collaboration). 

Common quantitative methods 

Data collection

These are some of the most common quantitative methods for data collection:  

  • Surveys: Structured questionnaires given to a sample group to gather numerical data or categorical responses. For example, educator distributes a survey to students asking them to rate, on a scale of 1 to 5, the usefulness of a new online learning module. 
  • Experiments: Manipulating one or more variables to determine their effect on a specific outcome, while controlling other potential influences. For example, a teacher divides a class into two groups: one group is taught using traditional lectures, and the other using interactive simulations. 
  • Observations: Systematic recording of observable behaviours in situ. For example, a researcher observes a classroom implementing a new active learning strategy and counts the number of times students engage in discussions during each session. 
  • Structured interviews: A series of pre-determined questions are asked to participants. For example, an educator conducts structured interviews with a sample of students, asking them to rank their confidence in mastering course content on a scale from 1 to 10. 
  • Secondary data analysis: Examination of existing data (previously collected and published) such as datasets or archives. For example, a researcher reviews institutional data on student retention rates over the past decade and correlates it with the implementation of a new mentoring program. 

Data analysis

These are some of the most common quantitative methods for data analysis:  

  • Descriptive statistics: Summarizes and organizes data features like mean, median, mode, and standard deviation to provide a basic understanding. For example, summaries of student performance or responses, such as class averages, standard deviations, and distribution patterns.  
  • Inferential statistics: Inferential statistics allow researchers to draw conclusions about a population based on data from a sample of that population. For example, analysing test scores from a sample of students. 
  • Regression analysis: Determines how changes in one variable (independent) can predict changes in another variable (dependent). For example, an educator finds that for every additional hour students engage in group study sessions, their final exam scores increase by an average of two points. 
  • Text mining and analysis: Text mining and analysis involve extracting meaningful information and patterns from large volumes of textual data. For example, by text mining student feedback forms, a researcher can identify common themes and sentiments. 
  • Correlation analysis: Investigates the strength and direction of a relationship between two variables. For example, researching the correlation between student behaviour (class attendance) and assessment grades. 



Mixed-methods research combines both quantitative and qualitative approaches, leveraging the strengths of each to provide a more comprehensive understanding of a research problem.  

In terms of data collection, a mixed-methods study might employ surveys to gather numerical data on participants' behaviours or preferences, and then conduct focus group discussions or interviews to delve deeper into reasons or motivations behind those responses.  

For data analysis, quantitative data might be statistically analyzed to identify patterns or significant differences, while qualitative data would be coded and thematically analyzed to uncover underlying themes or narratives. By synthesising results from both methods, researchers can achieve a richer and more nuanced insight into their research questions, benefiting from the specificity of quantitative data and the depth of qualitative perspectives.