This question is about my applied research project, the analysis phase. Considering that I am engaged in a mixed-methods quasi-experimental study, I have been thinking a lot about the strategies I have employed thus far in the process of conducting applied research. Intervention studies that seek to establish a cause-and-effect link between variables can benefit from the use of a quasi-experimental study design. Also, in terms of the general character of the mixed-methods research, I opted for a progressive or sequential explanatory design, which places more emphasis on the quantitative phase, followed by the qualitative phase. The second [qualitative] phase is used to provide context for the findings from the first [quantitative] phase and also serves to explain any detected anomalies or improbable findings. I am in the midst of the data analysis phase of my research, and I am aware that, given the nature of my investigation, I need to condense my strategies. The instruments in my study include, two quantitative and one qualitative. The quantitative instruments are adaptive tests designed to assess student cognitive capacities based on Bloom's revised taxonomy. The first is mostly a multiple-choice test (let's call it Test A), while the second involves open-ended essay questions (Test B). The semi-structured [qualitative] interviews would use open-ended verbal questions adapted from either Test A or B, to test specific conceptual levels based on Bloom's metric. I have concluded two pre-tests (one for Test A, and one for Test B) and two post-tests (one for Test A, one for Test B). So, I need support and guidance on combining these results into the analysis phase to validate my findings? There is mention of measuring cognitive learning outcomes at both the pre- and post-test stages, using an n-gain analysis to help us pin down what it is that's causing students' test scores to rise. Assuming that the data is normally distributed, statistical analysis, specifically the pair t-test, will be utilized to ascertain whether or not there was a significant change in the mean score of student learning outcomes between the pre- and post-test. And as any difference over 5% would be considered unsatisfactory, the second step would be to perform an ANOVA on all post-test data. But these are just conclusions I have drawn from my research findings, although I need to be sure I am right. I need ideas on the best approach, something simple, straight forward and easy for a reader or instructor to follow, so that I do not get stuck somewhere. Let me know if you need anything else. Thank you!

Context:

https://journal-center.litpam.com/index.php/ijece/article/view/729

https://pdfs.semanticscholar.org/801f/23d7cbadb1bb1f1b798a48ac8e453b4df11a.pdf