Self-Study: Comparison of Means, Comparison of Means, Part II: ANOVA and Kruskal Wallis
Throughout the course, there will be a self-study Discussion pertaining to an important concept or topic covered within the assigned week. These Discussions are designed to give you the opportunity to collaborate with your peers and faculty, test your knowledge, ask questions, practice research analysis, and assist your peers.
You are not required to post to this forum; however, you are encouraged to post, review the posts of others, as well as answer questions and/or provide clarity and collaboration with your peers. Discussions will be graded as either Complete or Incomplete.
Resources
Be sure to review the Learning Resources before completing this activity.
Click the weekly resources link to access the resources.
WEEKLY RESOURCES
Required Resources
· Laerd Statistics: Sign up for a one-month plan using this link
to an external site.
·
One Way ANOVA in SPSSLinks to an external site.
·
Kruskal-Wallis Test in SPSSLinks to an external site.
· Salkind, N., & Frey, B. (2019).
Statistics for people who (think they) hate statistics (7th ed.). SAGE Publications.
· Chapter 14, “Analysis of Variance: Two Groups Too Many?” (pp. 269–273, 279)
·
Document:
Statistical Output: Kruskal-Wallis (Word document)
Download Statistical Output: Kruskal-Wallis (Word document)
·
Document:
Statistical Output: ANOVA (Word document)
Download Statistical Output: ANOVA (Word document)
Required Media
Niedz, B. (2024).
Comparison of means, part II: ANOVA and Krustkal Wallis [Video]. Walden University Canvas.
PowerPoint Presentation
Document:
Comparison of Means, ANOVA and Kruskal Wallis (PowerPoint presentation)
Required Resources for Topic: ANOVA
· Turgut, M., & Yıldız, H. (2023).
Investigation of grief and posttraumatic growth related to patient loss in pediatric intensive care nurses: A cross-sectional studyLinks to an external site..
BMC Palliative Care, 22(1), 195.
To prepare:
· Read and view the Learning Resources in Doherty and Skalsky, and Dang et al. (2021) in Required Readings.
· View the video on comparison of means.
Use this Discussion to collaborate with your peers and faculty as an open office hours/ Q&A forum.
Post answers to the following:
· Summarize the ANOVA or the Kruskal-Wallis output after completing the self-learning module and completing the Required Readings.
· Turgut and Yıldız (2023) used both a
t test and an ANOVA and presented these findings in Table 2 on page 5.
· Compare and contrast the comparisons for the impact of
duration of work on the unit, on the Texas Revised Inventory of Grief (ANOVA), and the
education on terminal period and grief (
t test).
· Were these the correct tests to be used in these analyses? Explain why.
For this Self-Study Discussion, you may post throughout Week 5. You are not required to post to this forum; however, you are encouraged to post, review the posts of others, as well as answer questions and/or provide clarity and collaboration with your peers. Discussions will be graded as either Complete or Incomplete.
Use this Discussion to collaborate with your peers and faculty as an open office hours/ Q&A forum.
Post answers to any or all of the following:
· Summarize the ANOVA or the Kruskal-Wallis output after completing the self-learning module and completing the Required Readings.
· Turgut and Yıldız (2023) used both a
t-test and an ANOVA and presented these findings in Table 2 on page 5.
· Compare and contrast the comparisons for the impact of
duration of work on the unit, on the Texas Revised Inventory of Grief (ANOVA), and the
education on terminal period and grief (
t-test).
· Were these the correct tests to be used in these analyses? Explain why.
Our interactive discussion addresses the following learning objectives:
· Differentiate between ANOVA and Kruskal-Wallis tests of significance
· Summarize statistical findings for ANOVA and for Kruskal-Wallis
RESPOND TO THIS DISCUSSION POST
Reply from Tania
After reviewing the learning resources by Doherty and Skalsky (2021), Dang et al. (2022), and Turgut and Yıldız (2023), I have analyzed the appropriate application of ANOVA and t-tests in healthcare research, specifically in the context of evaluating grief among healthcare professionals.
Summary of ANOVA and Kruskal-Wallis Output
ANOVA (Analysis of Variance) compares the means of three or more independent groups to determine whether they have statistically significant differences. It assumes normal distribution and homogeneity of variances. When these assumptions are violated, the non-parametric alternative’s Kruskal-Wallis test is appropriate because it does not require normality and
can be used with ordinal data (Ghasemi & Zahediasl, 2021). Doherty and Skalsky (2021) highlight that selecting the correct test depends on the measurement and data distribution level, emphasizing that ANOVA is effective for parametric data. Kruskal-Wallis’s test is more robust when assumptions are unmet.
Comparison of ANOVA and t-Test in Turgut and Yıldız (2023)
Turgut and Yıldız (2023) used both an independent t-test and ANOVA to assess different variables affecting grief among healthcare workers:
Impact of Work Duration on the Texas Revised Inventory of Grief (ANOVA):
The study applied a one-way ANOVA to analyze differences in grief scores based on the duration of work on the unit. Since the work duration was categorized into multiple groups (e.g., short-term, mid-term, and long-term experience), ANOVA was the correct choice for comparing mean grief scores among three or more independent groups (Kim, 2017).
Impact of Education on Terminal Period and Grief (t-Test):
An independent t-test was employed to compare grief scores between two groups: those who received education on terminal care and grief and those who did not. Since this analysis involved only two independent groups, the t-test was the appropriate statistical method to determine whether education significantly influenced grief scores (McDonald, 2019).
Appropriateness of the Statistical Tests
The statistical tests used in Turgut and Yıldız’s (2023) study were appropriate. ANOVA was correctly used to compare means among multiple independent
groups, while the t-test effectively assessed differences between two distinct groups. Doherty and Skalsky (2021) emphasize the importance of ensuring statistical assumptions are met before applying parametric tests. If assumptions such as normality and homogeneity of variances were violated, the Kruskal-Wallis test could have been an alternative to ANOVA, and the Mann-Whitney U test could have replaced the t-test (Ghasemi & Zahediasl, 2021).
Insights from Dang et al. (2022)
Dang et al. (2022) highlight the role of evidence-based practice in healthcare research, stressing the need for rigorous statistical analysis. Their framework aligns with the approach used in Turgut and Yıldız (2023), where statistical tests were chosen based on data structure and research questions, ensuring reliable findings that inform nursing and healthcare practices.
Conclusion
Turgut and Yıldız (2023) appropriately applied ANOVA and t-tests to analyze the impact of work duration and education on grief among healthcare workers. The discussion from Doherty and Skalsky (2021) and Dang et al. (2022) reinforces the importance of selecting the correct statistical tests based on data characteristics. Ensuring that statistical assumptions are met is essential for the validity of findings, and when necessary, non-parametric alternatives such as the Kruskal-Wallis test should be considered.
References
Dang, D., Dearholt, S. L., Bissett, K., Ascenzi, J., & Whalen, M. (2022
). Johns Hopkins Evidence-Based Practice for Nurses and Healthcare Professionals: Model and Guidelines (4th ed.). Sigma Theta Tau International Honor Society of Nursing.
Doherty, C., & Skalsky, K. (2021).
Statistics and Research Design for the DNP Project. DEStech Publications.
Ghasemi, A., & Zahediasl, S. (2021). Normality tests for statistical analysis: A guide for non-statisticians.
International Journal of Endocrinology and Metabolism, 19(2), e110979.
Kim, H. Y. (2017). Statistical notes for clinical researchers: Understanding one-way ANOVA.
Korean Journal of Anesthesiology, 70(1), 22-26.
Kim, H. Y. (2017). Statistical notes for clinical researchers: Understanding one-way ANOVA.
Korean Journal of Anesthesiology, 70(1), 22-26.
McDonald, J. H. (2019). Handbook of biological statistics (4th ed.). Sparky House Publishing.
Turgut, M., & Yıldız, H. (2023). Investigation of grief and posttraumatic growth related to patient loss in pediatric intensive care nurses: A cross-sectional study.
BMC Palliative Care, 22(1), 195.
