Thesis time?

So, it is that time in your academic career where you have to decide on the subject of your thesis. You may choose to explore something that intrigues you personally, or want to follow already established direction? Either way, you have to make an important choice. If you study Behavioral Sciences, Experimental Psychology or any other field closely associated with research, you will have to make a choice between the two possible types of inquires — quantitative or qualitative.

In my field of interest, the one of UX and Human Factors, both qualitative and quantitative methods of research take important place. Data from quantitative research — such as market size, demographics, and user preferences — provides important information for business decisions. Qualitative research provides information for use in the design of a product — including user needs, behavior patterns, and product application. Each of these approaches has strengths and weaknesses

For those not familiar with either research method, and introduction is in order. According to Babbie (2010) quantitative research methods emphasize objective measurements and the statistical, mathematical, or numerical analysis of data collected through variety of methods. Quantitative research focuses on gathering numerical data and generalizing it across groups of people to explain a phenomenon.

Your goal when conducting quantitative research is to determine a relationship between independent variable (the one you manipulate), and dependent variable (the one that supposedly changes as a result of the manipulation) and state with high confidence that the results are valid for the entire population of interest.

But if you are anything like me, and most of your thought begin with “I wonder why” or “How is it that…”, you may be a candidate for the qualitative type of research. The word qualitative suggests an emphasis on the characteristics of objects, and on processes and meanings that are not experimentally examined or measured in terms of quantity, amount, intensity, or frequency (Danzin & Lincoln, 2000). These methods are popular in health-related research, marketing, and social studies. They use different processes for data collection such as observations, structured interviews or surveys to identify trends or patterns. Since trends cannot be statistically analyzed and validated by the widely-accepted p — values or effect size measures, qualitative research must be extremely thorough, consistent, and easily replicable to achieve the same level of credibility.

Before you jump into qualitative research, there are several important aspects to consider. In recent years, many scientist have addressed the quality issue in qualitative research. When the standardized methods used in the quantitative research cannot be applied to the qualitative research, how can we assess the value of the inferences? Mays and Pope (2000) propose two criteria for decision: validity and relevance. They also identify two opposing perspectives regarding the evaluation of quality of the results.

The first groups support the idea that qualitative research is unique, and should not be judged by conventional measures for of validity, generalizability, and reliability. The second group is proposing a mix of both approaches. Combined, they can be extremely effective, if used appropriately. To limit the probability of mistakes in qualitative research Mays and Pope (2000) suggest possible solutions. Triangulation, is one of these solutions, and involves using multiple data sources. Qualitative researchers commonly use this technique to ensure that an account is rich, robust, comprehensive and well-developed. Another good technique to ensure accurate result representation is to obtain respondent validation. This method is a reverse form of interview, where the participants provide feedback on the correctness of the researcher’s interpretations.

It is critical to have a clear account of the collection and data analysis. In addition, reflexivity of the data collection, attention to negative cases, relevance, and fear dealing are important factors shaping the credibility of the findings.

Another important aspect to consider before attempting qualitative research is sampling. Kuzel (1999) points out that generalization of the finding in quantitative statistical methods depends how close the sample represents the population. In qualitative research, the goal is not to generalize or predict, but to create and test new interpretations. It is important to know what to sample, but it is critical to decide how to sample. He recommends specific sampling strategies, appropriate for qualitative research with respect of the study goal. Attached is a table with all suggested strategies and their purpose.

When getting ready to perform research it is important to recognize the different functions of qualitative and quantitative research methods. This understanding can help choose the appropriate research approach, understand why particular methodology may be more suitable, or combine features from both to achieve superior results.

Babbie, Earl. The Practice of Social Research. 12th ed. Belmont, CA: Wadsworth Cengage, 2010; Muijs, Daniel. Doing Quantitative Research in Education with SPSS. 2nd edition. London: SAGE Publications, 2010.

Denzin, Norman. K. & Lincoln. Yvonna S. Handbook of Qualitative Research. 2nd edition. Thousand Oaks, CA: Sage, 2000.

Kuzel, A. J. (1999). Sampling in qualitative inquiry. In B. F. Crabtree & M. B. Miles (Eds.), Doing qualitative research (2nd ed., pp. 33–45). Thousan Oaks, CA: Sage.

Mays, N., & Pope, C. (2000). Assessing quality in qualitative research. BMJ: British Medical Journal, 320(7226), 50.