Data Analysis And Findings

In this chapter, statistical tests of significance are performed and correlations are made. 79 students ‒ 47 female and 32 male ‒ of similar age participated in the research and all their responses were viable for examination during data analysis. Raw data collected and recorded in Excel worksheets were populated into SPSS (version 23) for statistical analyses. First, descriptive analysis with the means and standard deviations for gender were determined gender only since all students were of similar age. Next, a factorial multivariate analysis of variance (MANOVA) was performed using gender as the independent variable (IV) and the four attitude variables namely, cognitive (C), affect enjoyment (AE), affect feeling (AF) and affect teacher (AT) as the dependent variables. For those needing support in this area, seeking data analysis dissertation help can provide additional insights. A stepwise discriminant function analysis (DFA) test was identified as suitable on significant MANOVA results to identify the dependent variables responsible for observed differences. The results are presented below:

A general overview of Table 1 suggests that on average, the students “agree” to fitness testing since the mean scores for all attitude variables can be rounded off to “4”. In fact, the overall mean score for all students on a 5-point Likert scale was 3.9475 with a standard deviation of 0.1526 suggesting a low spread of the data thereby reinforcing the inference that most students agreed. The cognitive factor had the highest mean score for both genders (M = 4.1518, SD = 0.5798). On the other hand, affective feeling attitude variable had the lowest mean score (M = 3.8182, SD = 0. 9332). From a gender perspective, the overall female score (M = 3.9536, SD = 0.1383) suggested that girls had more positive attitudes towards fitness testing than males (M = 3.9385, SD = 0.1797). The lowest mean attitude score for males was observed in the affective feeling factor (M = 3.7503, SD = 1.07364). The magnitude of the standard deviation suggests that opinions varied widely within the factor. On the other hand, the lowest attitude scores for females were observed within the affective enjoyment factor (M = 3.8319, SD = 0.7899).

There was lack of a statistically significant difference between gender and students’ attitudes towards fitness testing (Wilk's Λ = 0.99, F(4, 74) = 0.182, p > 0.05, partial η2 = 0.01). As a result, the stepwise DFA test was not conducted since the MANOVA test did not identify significant correlations between gender and the dependent variables. As such, it was not possible to determine the magnitude to which the dependent variables were responsible for observed differences.

c. R Squared = .004 (Adjusted R Squared = -.009) d. R Squared = .000 (Adjusted R Squared = -.013) e. Computed using alpha = .05

Tests of between subjects determine how the independent variable differs from the dependent variables. From Table 3 above, gender did not a significant effect on the variation of the dependent variables.

The partial eta squared statistic indicates the practical significance of each variable, based upon the ratio of the variation, which is the sum of squares accounted for by the variable, to the sum of the variation accounted for by the term and the variation left to error. From the table above, cognitive and affective feeling had relatively higher scores than other dependent variables. It would suggests a greater amount of variation accounted for by the variables to a maximum of 1.

Bibliography

• Bryman, A., 2012. Social research methods. London: Oxford University Press.
• Hatcher, L., 2013. Advanced statistics in research: Reading, understanding, and writing up data analysis results. Saginaw MI: Shadow Finch Media.
• P.Chapman, Clinton, J. & Kerber, R., 2006. CRISP-DM 1.0; Step-by-step data mining guide. New York: CRISP-DM consortium.

Looking for further insights on Comparative Analysis of Smoking Cessation Treatments? Click here.