Statistical Practice: Mann-Whitney And Wilcoxon Signed Rank (Nonparametric) Tests
The nonparametric tests that are being performed in this unit (Mann-Whitney U, the nonparametric equivalent of the independent t-test and the Wilcoxon Test, the nonparametric equivalent of the dependent t-test) are most often used if the interval or ratio data is not normally distributed or if the data being analyzed is at the ordinal (ranked) measurement level.
Tobest prepare for the upcoming assignments, you must understand how to perform and interpret paired t-tests.
Instructions
For this discussion, we will use the data scenario we described in Unit 8 (the various group comparisons for well-being), but we will pretend that the normal distribution assumption that we tested was violated (this is, test results suggest that the data is not normally distributed). You will perform a nonparametric Mann-Whitney test and a Wilcoxon signed-rank on the appropriate data.
Complete the following:
1. Describe, in your own words, an example of the type of research project scenarios where you should use these nonparametric statistical tests.
2. Report, using the Emotional Well-Being data set you created previously, the results of the two nonparametric tests that you perform. Be sure to include all relevant statistical outcomes.
3. Provide a one- or two-sentence practical interpretation of the results.
Remember to refer to the guidelines in the FEM as you prepare your post.
· How do the challenges and resolutions of your peers compare to yours?
· How do your practical interpretations compare to those of your peers?
Resources
· Emotional Well-Being (SF-36) Study Data Set [XLSX].
· Laerd Statistics. (n.d.). Mann-Whitney u test using SPSS statistics. Retrieved from https://statistics.laerd.com/spss-tutorials/mann-whitney-u-test-using-spss-statistics.php
· Laerd Statistics. (n.d.). Wilcoxon signed-rank test using SPSS statistics. Retrieved from https://statistics.laerd.com/spss-tutorials/wilcoxon-signed-rank-test-using-spss-statistics.php
PART TWO
[u07d2] Unit 7 Discussion 2
Analyzing a Health Care Data Set
Overview
Public health researchers are often involved in collaborating in the design, development, and analysis of community initiatives of varying complexity. While this course alone will not provide sufficient training for you to act as a statistical consultant, it does offer a broad and practice-based analytic foundation that can position you to better understand and more fully contribute to real-world project teams. Building on the basic statistical concepts and analytical techniques of the previous units, this assignment is an opportunity touse your cumulative quantitative-analysis skills to address a broad set of real-world research questions.
Demonstration of Proficiency
By successfully completing this assessment you will address the following Scoring Guide Criteria, which align to the indicated course competencies.
· Competency 2:Apply appropriate statistical methods using common software tools in the collection and evaluation of health care data.
. Perform the most appropriate parametric or nonparametric test to answer each question.
· Competency 3:Interpret the results and practical significance of statistical health care data analyses.
. Assess the assumption of normal distribution prior to analysis.
. Appropriately interpret the statistical output (such as estimate, p-value, confidence interval, and effect size) resulting from each statistical test.
. Summarize the clinical implications, significance, and potential limitations of the study data and outcomes.
· Competency 4: Assess the quality of quantitative research methods reported in peer-reviewed health care literature.
. Describe the practical significance of the results of statistical tests.
· Competency 5: Address assignment purpose in a well-organized text, incorporating appropriate evidence and tone in grammatically sound sentences.
. Articulate meaning relevant to the main topic, scope, and purpose of the prompt.
. Apply APA formatting to in-text citations and references.
Instructions
Complete the following for this two-part assignment:
Part 1: Yoga and Stress Study Statistical Tests
1. Using the data set linked in Resources, determine the measurement level of data of the dependent or outcome variable (Psychological Stress Score) you are analyzing.
. Is the data categorical, ordinal, or interval or ratio?
· Before performing any statistical tests, you must determine which tests would be most appropriate for your data type.
. First, perform a pre-evaluation of the data for outliers (all variables) and normal distribution (only dependent variables) as you have done previously.
. Then, useHow to Choose a Statistical Test (linked in Resources) as general guidance in helping you to decide which test to use.
. Use the readings, media, resources, and textbook as guides to perform an analysis of the selected variables.
· Perform and interpret an appropriate series of statistical tests (including pre-analytical testing for outliers and normal distribution of data) that answer the following research questions:
. How would you quantitatively describe the study population?
. Summarize the primary demographic data using descriptive statistics.
· Is there any association between gender and race in this military study?
. Perform an appropriate chi-square analysis.
· Perform preliminary assessment of the data, then compare pretest to post-test scores.
· In the total population being studied, what was the effect of the yoga intervention on stress?
· Provide the SPSS ".sav"output file that shows your programming and results for this assignment.
Part 2: Interpretive Report
1. Summarize the clinical implications related to the statistical outcomes for each of the questions above.
2. Describe potential limitations of the study (Part 1, number 3).
Additional Requirements
· Length:Your paper will be 3-4 typed, double-spaced pages of content, plustitle and reference pages.
· Font:Times New Roman, 12 points.
Resources
· Yoga Stress (PSS) Study Data Set [XLSX].
PLEASE USE AT LEAST 2 OF THESE!!!
· Health Knowledge. (n.d.). Parametric and non-parametric tests for comparing two or more groups. Retrieved from https://www.healthknowledge.org.uk/public-health-textbook/research-methods/1b-statistical-methods/parametric-nonparametric-tests
· Hoskin, T. (n.d.). Parametric and nonparametric: Demistifying the terms [PDF]. Available from https://www.mayo.edu/documents/berd-5-6/doc-20274735
· Nahm, F. S. (2016). Nonparametric statistical tests for the continuous data: The basic concept and the practical use. Retrieved from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4754273/
· Pryjmachuk, S., & Richards, D. A. (2007). Look before you leap and don't put all your eggs in one basket. Journal of Research in Nursing, 12(1), 43-54.