5.4 Philosophical Underpinnings to Mixed Methods Research

As discussed in Chapter 1, a research methodology needs a philosophical and epistemological underpinning, i.e. what is the nature of the knowledge you are trying to uncover? From a philosophical standpoint, quantitative research (scientific method) is conducted from a deductive point of view, and is based on a probabilistic interpretation of reality, positivism or post-positivism. A (post)positivist tenet is the belief that there is an objective world in which research and discovery are possible.¹⁴ This method aims to minimize the researchers’ influence on the data source and reduces subjectivity from skewing the conclusions.¹⁵ On the other hand, qualitative research allows investigation from an inductive perspective and is based on constructivist or interpretivist principles.¹⁶ This paradigm recognizes the possibility of multiple perspectives on reality, knowledge is not value-free, and that subjectivity is a necessary element of investigation.¹⁶ Mixed-methods researchers combine paradigms that allow investigation from inductive and deductive perspectives to combine theory-building and hypothesis testing in a single study.¹⁷ This approach is centred on the cyclical interplay of beliefs and actions.¹⁸ There are two major philosophical positions in which mixed methods research might be grounded – Pragmatism and Realism. These positions are often referred to as dialectal stances that bridge postpositivist and social constructivist worldviews, pragmatic and transformative perspectives.¹¹ A pragmatic perspective draws on employing “what works,” using diverse approaches, prioritising the importance of the research problem and question, and valuing objective and subjective knowledge.^15,19 Realist approaches developed mainly in response to a perceived need for research that was useful to policymakers, asking questions about what goes on beneath the surface in these socially complex situations. ^20,21  Nonetheless, calls have been made to embrace pragmatism as the best philosophical foundation for mixed methods research.²²

Sample size estimation and sampling technique

Sample size estimation and sampling techniques for quantitative and qualitative research have already been discussed in previous chapters and the same principles apply in mixed methods studies where quantitative and qualitative components are combined. For details on sample size estimation and sampling techniques used in quantitative and qualitative research, please refer to Chapter 3 and Chapter 4, respectively. A summary is provided below to remind you of what we discussed earlier on these topics.

Sample size is an important consideration in mixed methods research, as it pertains to the number of participants or cases included in the study. As discussed in Chapter 3, sample size for quantitative research is determined by the statistical power of the study, which is the probability of detecting an effect of a given size if one exists. ²³ Larger sample sizes generally increase the power of a study and reduce the likelihood of Type II errors (failing to reject a null hypothesis that is false). However, sample size also depends on the variability of the outcome, the effect size, and the desired level of confidence. Note that larger sample size improves precision but also increases cost, time, and complexity. As stated in Chapter 4, sample size for qualitative studies is determined by the principle of saturation, which is the point at which new data no longer provide new insights into the research question.²⁴ For qualitative data, a small sample size is usually sufficient, as the goal is to gain a detailed and in-depth understanding of the research problem. However, sample size also depends on the complexity of the research question and the research setting. On the whole, It is important to note that the sample size is a trade-off between study accuracy and feasibility. Therefore, it should be determined in a way that is appropriate for the research question and and feasible in terms of resources and time.

Sampling technique refers to the process of selecting participants for a mixed methods study. There are different ways to combine sampling techniques in mixed methods research. For example, a researcher may use a purposive sampling strategy for the qualitative component (see Chapter 4 for details) of the study and a probability sampling strategy  for the quantitative component (see Chapter 3 for details). It is important to note that the sampling strategy used should be consistent with the overall research design and the specific research question. Sampling techniques should be feasible in terms of resources and time, ethically sound and appropriate for the research question.

Data collection and analytical methods

Data collection refers to the process of collecting both quantitative and qualitative data as part of a mixed methods study. The data collection methods used will depend on the specific research question and the overall research design. Quantitative data is collected using methods such as surveys, experiments, or observational. These methods often involve structured instruments such as questionnaires or standardized tests. The data is usually numerical and can be analyzed using statistical methods. Quantitative data are usually analyzed using statistical techniques such as descriptive statistics, inferential statistics and multivariate analysis. These methods are used to identify patterns and relationships in the data and draw inferences about the population from which the sample was drawn. Please refer to Chapter 3 for more information on quantitative data collection and analytical methods.

Qualitative data is collected using methods such as interviews, focus groups, or ethnographic observations. These methods often involve unstructured or semi-structured instruments such as open-ended questions or interview guides. The data is usually in the form of words and can be analysed using methods such as content analysis or thematic analysis. Qualitative data are typically analyzed using methods such as content analysis, thematic analysis and discourse analysis. These methods are used to identify patterns and themes in the data and interpret the meaning of the data. For further details on qualitative data collection and analytical methods, please revisit the content covered in Chapter 4.