- First, report the lowest magnitude correlation in the intercorrelation matrix, including degrees of freedom, correlation coefficient, p value, and effect size. Interpret the effect size. Specify whether or not to reject the null hypothesis for this correlation.
- Second, report the highest magnitude correlation in the intercorrelation matrix, including degrees of freedom, correlation coefficient, p value, and effect size. Interpret the effect size. Specify whether or not to reject the null hypothesis for this correlation.
- Third, report the correlation between GPA and final, including degrees of freedom, correlation coefficient, p value, and effect size. Interpret the effect size. Analyze the correlation in terms of the null hypothesis.
Running head: DATA ANALYSIS AND APPLICATION TEMPLATE 1 PAGE 2 Data Analysis and Application Capella University Data Analysis Plan For assessment 2 all the variables used are continuous which are Quiz 1, GPA, Total, and Final. Quiz 1 is defined as the number of correct answers, GPA is defined as the previous grade point average, Total is defined as the total number of points earned, and final is defined as the number of correct answers on the final exam. The research question is: Is there a relationship between GPA and Quiz 1? The null hypothesis states there is not a relationship between GPA and Quiz 1, and the alternative hypothesis states there is a relationship between the GPA and Quiz 1. Testing Assumptions The table shows that the normality assumption is not met by the data. Quiz 1 has a positive skew of -0.851, GPA has a positive skew of -0.220, total has a positive skew -0.757. Quiz 1 displays leptokurtic data, 0.162 while GPA displays platykurtic data, -0.688. Results and Interpretation Correlations quiz1 gpa total final quiz1 Pearson Correlation 1 .152 .797** .499** Sig. (2-tailed) .121 .000 .000 N 105 105 105 105 gpa Pearson Correlation .152 1 .318** .379** Sig. (2-tailed) .121 .001 .000 N 105 105 105 105 total Pearson Correlation .797** .318** 1 .875** Sig. (2-tailed) .000 .001 .000 N 105 105 105 105 final Pearson Correlation .499** .379** .875** 1 Sig. (2-tailed) .000 .000 .000 N 105 105 105 105 **. Correlation is significant at the 0.01 level (2-tailed). The correlation between GPA and Quiz 1 was not significant r (103) =0.152, p = 0.121. The null hypothesis is not rejected. The lowest magnitude correlation is between GPA and quiz1 which is 0.152. The corresponding degrees of freedom is (105-2) = 103. The correlation coefficient is 0.152 and the corresponding p-value is 0.121. The effect size is below: This interprets that there is very small association between GPA and Quiz 1. Since the p-value is not less than 0.01 level of significance, the null hypothesis is not rejected and it cannot be concluded that there is significant correlation between GPA and Quiz 1. Statistical Conclusions From the analysis performed on the data we see there is no relationship between GPA and Quiz 1. One of the limitations with correlations analysis is that it cannot look at the effect of other variables only the two being used. Also, a correlation analysis cannot accurately describe curvilinear relationship, nor can a correlation test explain cause and effect (Janse et al., 2021). The alternate explanation for the analysis is that there is not a big enough effect for quiz 1 and the GPA to be correlated. For future exploration a correlation analysis can be performed on the other variables. Perhaps GPA and the final, that would be helpful in knowing how the final effects the GPA. Application In residential treatment, correlations would allow researchers to look closer into age and satisfaction with the residential treatment program. When I first started the population was older adults in their 30’s, more recently our population has shifted to consumers in their 20’s. However, that age group does not seem complete the program and discharge early. I have wondered if it is the structure of the program and if it is time for a new design since it was created in the late 90’s. Running a correlation test might show if the younger generation is less satisfied with the program, then the older adult population. References Field, A. (2018). Discovering Statistics Using Ibm Spss Statistics: North American edition. SAGE. Janse, R. J., Hoekstra, T., Jager, K. J., Zoccali, C., Tripepi, G., Dekker, F. W., & van Diepen, M. (2021). Conducting Correlation Analysis: Important limitations and Pitfalls. Clinical Kidney Journal, 14(11), 2332–2337. https://doi.org/10.1093/ckj/sfab085