Can anyone help me, in multilevel model variant of triangulation design, does it really matter whether qualitative or quantitative comes first such as the ones in explanatory (start with quantitative) and exploratory (start with qualitative) ? Thanks.
Dear Nurhanis Syazni Roslan,
In Mixed Method Triangulation Design, the multilevel model is used to investigate the different level of analysis. The findings from each level are merged together into one overall interpretation. As both quantitative and qualitative levels have the same weight in the design. Therefore, I suggest that quantitative and quantitative should go together.
The following papers may help, specifically: “In explanatory designs, researchers first collect and analyze quantitative data, then build on those findings in a qualitative follow up, which seeks to provide a better understanding of the quantitative results……In embedded designs, researchers collect both quantitative and qualitative data either sequentially or concurrently with one form of data playing a supporting role, or both forms of data playing a supporting role in a larger design….In concurrent designs, researchers collect both qualitative and quantitative data simultaneously, analyze both data strands separately, and then mix the databases by merging the data…. (Harrison and Reilly, 2011, pp. 16-18); and the mixed method process/map (Johnstone, 2004, p. 266)
- Harrison, R. L. and Reilly, T. M. (2011) Mixed methods designs in marketing research, Qualitative Market Research, 14, 1, pp. 7-26.
- Johnstone, P. L. (2004) Mixed Methods, Mixed Methodology Health Services Research in Practice, Qualitative Health Research, 14, 2, pp. 259-271.
- Onwuegbuzie, A. J., Johnson, R. B. and Turner, L. A. (2007) Toward a Definition of Mixed Methods Research, Journal of Mixed Methods Research, 1, 2, pp. 112-133.
Nurhanis - you can do either. That is commence with qualitative or quantitative. It depends what you want to achieve. The attached chapter may assist - and table 14.2 highlights the different combinations that can be used for varying outcomes.
Thank you Prof Whitehead for the excellent summary in Table 14.2, Dr Lui-Ming Ngie and Dr Panezai for the great references.
First, the term "multi-level" design is used almost exclusively in quantitative research, where it refers to the nesting of observations within different levels of analysis (e.g., students in schools, and schools in districts, etc.).
Second, the hallmark of of triangulation is the comparison of qualitative and quantitative studies are done independently, so that neither influences the other. the goal is to determine whether the two types of methods produce similar results. As long as the data collection procedures are completely separate, it doesn't matter whether they are done in either order or at the same time.
Exploratory-sequential (qual --> QUANT) and explanatory-sequential (QUANT --> qual) designs quite different from triangulation, as described in the chapter that Dean Whitehead sent you.
It does not matter whether you do qualitative or quantitative first. But you must be clear as to which method is the prominent method based on which you arrive at your major findings. And as David has stated, the methodology has to be distinct .
Thank you Prof Morgan and Shobha for the nice explanation. I planned to perform quantitative followed by qualitative approach to address several system in the study, where both will be equally important and merged to form the overal interpretation. But as many text highlighted example of QUAL-QUAN, I kinda needed confirmation that both can do. Thank you for all the enlightening information. I really appreciate it :-)
If your goal is to use the qualitative portion of your project to help interpret the results from the earlier quantitative portion, then that is known as an Explanatory Sequential design, which is summarized as QUANT --> qual.
There are multiple ways of combining multiple methods as can be seen in the article on Flexible Systems Methodology. But for triangulation the qualitative and quantitative may go independently and then compared by results
Article Flexible systems methodology
- Badges
- Science topic
- Similar topics
- Psychology
- Social Psychology