Discussion Question Discuss the differences between non-parametric and parametric tests. Provide an example of each and discuss when it is appropriate to use the test. Next, discuss the assumptions that must be met by the investigator to run the test. Research is a way of proving or disproving hypothesis; however, many journals have noted over the years that there have been a plethora of errors found in the statistical procedures used. \"One of the most common statistical errors found in journals is the application of parametric statistical techniques to nonparametric data\" (Nahm, 2013, p. 8). The thought is that medical researchers have been more familiar with parametric analysis because statistical solutions most often use parametric analysis; therefore, there has been a lack of understanding between the difference in analysis types. There are two types of statistical analysis: (1) parametric and (2) non-parametric (Grove, Burns, & Gray, 2013). Medical researchers use parametric analysis more often because they are most familiar with this type analysis and software packages that offered statistical solutions strongly support this type testing (Nahm, 2016). According to Grove, Burns, and Gray (2013), \"the analysis is referred to as parametric statistical analysis because the findings are inferred to the parameters of a normally distributed population\" (p. 542). To be used, these analytical approaches must meet three assumptions. These assumptions are: (1) The sample must be selected from a population for which the can be a calculated variance and the distribution is normal or approximately normal; (2) The measurement level must reflect at least an approximately normal distribution when dealing with interval level data or ordinal data; and (3) \"the data can be treated as random samples\" (Grove, Burns, & Gray, 2013, p. 542). If these three assumptions are not met, the test can be misleading (Nahm, 2016). Interval or ration scales use this type analysis; however, \"because nonparametric statistics have lower statistical power, many researchers choose to submit ordinal data to parametric statistical procedures\" (Grove, Burns, & Gray, 2013, p. 542). This type analysis is usually used for interval or ratio scales (Grove, Burns, & Gray, 2013). Types of parametric tests for correlation is a Pearson test. For independent measures of two groups there is a t-test or for more than two groups the ANOVA measurement. Non-parametric statistical analysis is sometimes called distribution-free technique (Grove, Burns, & Gray, 2013) and is an excellent technique to use when the sample distribution is unknown because of a small sample number or is skewed in one direction (Nahm, 2016). For this reason, nominal or ordinal measurement scales commonly use non-parametric statistical analysis. Non-parametric statistical analysis is not a powerful as parametric statistical analysis and does not meet the first two out of the three previously listed assumptions that parametric statistical analysis meets. This analysis type is least likely to identify variances and carries an increased risk of Type II errors. Nonparametric tests are broken down into four types of median tests: (1) comparison of two independent samples; (2) comparison of two paired samples; (3) one sample; and (4) comparison of three or more samples (Nahm, 2016). The Wilcoxon's sign rank test and the sign test are examples of nonparametric analysis of one sample (Nahm, 2016). The Wilcoxon's rank sum test, the Kolmogrov-Smirnov test, and the Mann-Whitney test are examples of comparison of two independent samples (Nahm, 2016). Comparison of three or more independent variables is conducted by the Jonckhere test or Kruskal-Wallis test (Nahm, 2016). non-parametric tests for correlation is Spearman testing. For groups of two there is the Mann-Whitney test or the Kruskal-Wallis test for two or more groups (Changingminds.org, 2016 Conclude with a brief discussion of your data analysis plan. Discuss the test you will use to address the study hypothesis and which measures of central tendency you will report for demographic variables. The project that the team I am a member of will compare the percentage of decreased risk for type II diabetes obtained by an adolescent group who participates in a nurse practitioner led diabetes prevention program compared to a group of adolescents who attend a one-day educational opportunity. My project is whether or not breastfeeding peer counselors who support and encourage first time primapara mothers to breastfeed for at least six months. The research hypothesis is that breastfeeding peer counselors will improve the length of breastfeeding to six months or more. The data analysis plan for my project is Pearson for correlation and t-test since my proposal has a control and a treatment group as well. I am planning on using the mean as a central tendency of measurement for the demographics that are collected. References Grove, S. K., Burns, N., & Gray, J. R. (2013). The practice of nursing research: Appraisal, synthesis, and generation of evidence (7th ed.). St. Louis, MO: Elsevier Saunders. Nahm, F. S. (2016). Nonparametric statistical tests for the continuous data: The basic concept and the practical use. Korean Journal of Anesthesiology, 69(1), 8-14. http://doi.org/10.4097/kjae.2016.69.1.8