NUR 705 Discussion 12.1 Alternate Statistical Tests
University:
St. Thomas University
NUR 705 Discussion 12.1 Alternate Statistical Tests
Paper Instructions
Discussion Guidelines
Initial Post
For this discussion, you will participate in a group discussion. Choose a group and identify alternate statistical tests to conduct with a non-normal distribution of data. Read the article Considerations when choosing a statistical method for data analysis (PDF) (Links to an external site.) by McKechnie & Fisher (2019). Propose a short research study plan, citing variables you would measure.
Discuss the variables you are studying and measuring. What type of parametric statistical test would you run if the measurements were normally distributed? In this example, measurement of your variables would not end up being normally distributed. What is the alternative statistical test you would propose and why?
Response Posts
Respond to at least two classmates’ posts.
Follow the RISE Model for Meaningful Feedback (PDF) (Links to an external site.) when writing your response posts.
Submission
Post your responses and review full grading criteria on the Discussion 12.1 Alternate Statistical Tests page.
We Work Hard So That You Don’t
We’ll write a 100% plagiarism-free paper in under 1 hour.
Sample Answer
There are a variety of alternate statistical tests that can be conducted when data is not normally distributed. Some of these tests include the Mann-Whitney U test, the Kruskal-Wallis H test, and the Spearman rank correlation coefficient. The Mann-Whitney U test is used to compare the median scores of two groups, while the Kruskal-Wallis H test is used to compare the ranks of several groups (Totaro et al., 2019). The Spearman rank correlation coefficient is used to measure the strength of a linear relationship between two variables.
Proposed Research
To determine the effects of obesity on high blood pressure among the elderly aged 60 years and above. The variables being studied in this case include Body Mass Index (BMI) and systolic blood pressure. Both BMI and systolic blood pressure will be measured and recorded as continuous data. The sample size will be 30. In other words, 30 elderly male and female participants will be involved in the study.
Null Hypothesis
Obesity has no significant impacts on blood pressure
Alternative Hypothesis
Obesity has significant impacts on blood pressure
If the measurements of the two variables are normally distributed. There are different parametric tests that can be used to prove hypothesis. These statistical tests include student t-test, Z-test, and ANOVA (Hussain & Mahmud, 2019). In addition, Pearson correlation can be used to determine the relationship between the two variables. However, if the two variables are not normally distributed Spearman’s correlation can be used to determine the relationship between the two variables.
On the other hand, Wilcoxon signed rank test, the Mann-Whitney U Test and the Kruskal-Wallis test can be used instead of student t-test, Z-test, and ANOVA.
References
- Hussain, M., & Mahmud, I. (2019). pyMannKendall a python package for non parametric Mann Kendall family of trend tests. Journal of Open Source Software, 4(39), 1556. https //joss.theoj.org/papers/10.21105/joss.01556
- Totaro, V., Gioia, A., & Iacobellis, V. (2019). Power of parametric and non-parametric tests for trend detection in annual maximum series. Hydrology and Earth System Sciences. https //hess.copernicus.org/preprints/hess-2019-363/hess-2019-363.pdf
We Work Hard So That You Don’t
We’ll write a 100% plagiarism-free paper in under 1 hour