Following data collection, responses were downloaded from LimeSurvey™ into a comma-separated file, which was opened in a spreadsheet program. Responses were divided into separate sheets according to the research questions. Because qualitative items were included among the quantitative items, a separate sheet was created for the qualitative data. Any personally identifying information was removed from the data and stored in a separate file and all study participants were assigned a code. Identifying information was only used to contact the winner of the draw.
Likert-scale items were converted from their original format to numerical responses. “Strongly Disagree” was given a score of “1” and “Strongly Agree” was given a score of “5” in accordance with the scoring scheme provided by Biggs et al. (2001). “Yes” and “No” responses were converted to “1” and “2” respectively.
The first section of the survey (the Biggs et al. R-SPQ-2F) was the only section completed by both the participants in the study buddy activity (n=25) and the non-participants (n=6). Non-participants were removed from the remaining sections of the survey data so that their blank answers would not be factored into statistical calculations.
Data were anonymized and loaded into PASW Statistics ™ (Student Version) for analysis. A limitation of the Student Version is that it is limited to 50 variables. This study contained 54 quantitative variables, so each section of the quantitative data was loaded individually. PASW Statistics ™ was used to calculate the t-test, basic descriptive statistics, and frequencies. Due to the exploratory nature of this investigation, the small sample size and the very small size of the non-participant group (n=6), further in-depth statistical analyses would have been unjustified.
The analysis of the qualitative data followed the hermeneutic phenomenology procedures outlined by Creswell (2007).
- Bracketing involves the researcher explaining his or her own experiences related to the phenomenon in question. This step is intended to allow the researcher to look at the phenomenon without bias or preconceived notions about the meaning of the phenomenon.
- Developing a list of significant statements through the process of horizontalization involves the researcher reading through the data several times to get a feeling for the data and then identifying statements that are particularly significant in light of the research questions. These statements are treated as having equal worth and any repeated or overlapping statements are removed from the data.
- Grouping the significant statements into themes involves the researcher identifying groups of significant statements that fall into larger categories, or themes.
- Describing what happened in the “textural description”, which outlines what happened from the perspective of the participants in the study and includes direct quotations from the participants.
- Describing how the phenomenon occurred in the “structural description”, which is a description of the context of the study.
- Combining the textural and structural description into the “composite description,” which captures the essence of the phenomenon.
Each of these steps is described more fully in Chapter V.
Validity in qualitative research refers to the idea that the findings of a qualitative study are an accurate representation of what the participants in the study actually experienced. Creswell (2007) recommends eight strategies that can be used to ensure validity in qualitative investigations. He recommends that researchers use at least two of the eight strategies. The strategies employed in this investigation were:
- Triangulation: this investigation gathered data from multiple sources (participants, non-participants, and the instructor), gathered two types of data (quantitative and qualitative), and relied on multiple theoretical foundations (interaction, cooperative learning, and student approach to learning).
- Member checking: during the qualitative analysis, the researcher consistently checked the coding process and results against what the participants reported in the quantitative data. The results of this process are made explicit in Chapter VI.