Parametric Vs. Pon-Parametric and Assumptions

The nature of information available on population-based issues is the major factor in distinguishing between parametric and non-parametric tests. While the two statistical concerns have been significant in offering a deeper study into research subjects to improve decision-making and policy formulation, parametric tests such as the z-test, t-test, and f-test are used when population data is available. The distribution of student scores in a classroom is an excellent example of a parametric test. The decision is influenced by the fact that student grades follow a pattern that has been observed and confirmed over time. Every set of results conforms to a normal distribution curve, where the number of outliers in both extremes is minuscule, while the majority of students are in average zones of grades B, C, and D.

In the event of the absence of documented knowledge of parameters, non-parametric tests such as the Mann-Whitney are employed to explore the population-linked hypothesis. Besides the existence of observed trend on population-based aspects, parametric tests focus on distribution and utilize ratio and interval levels of measurement (Ghasemi & Zahediasl, 2012). The most applicable descriptive exploration is the mean, while the Pearson is the most reasonable inferential statistic. In the case of non-parametric, the tests are based on arbitrary and make use of ordinal and nominal variables, with the focus being the median. One key distinguishing feature of the non-parametric test is that they are not based on non-normal distribution (Gibbons & Chakraborti, 2011). While the tests are equally robust as parametric ones in answering research questions, they are weak in documenting frequencies.

Data Analysis Plan

With the study being hugely qualitative, non-parametric tests will be the most applicable approach. The utility is based on the nature of the survey subject, which is distribution free. While the research focus is exploring factors underlying in the perenniality of overcrowding in the ED, the study cannot be able to quantify the attributive effect of every dependent variable. Nevertheless, the categories variables will be ranked based on the frequency reported, and media calculated.

References

Ghasemi, A., & Zahediasl, S. (2012). Normality tests for statistical analysis: a guide for non-statisticians. International journal of endocrinology and metabolism, 10(2), 486-489.

Gibbons, J. D., & Chakraborti, S. (2011). Nonparametric statistical inference (pp. 977-979). Springer Berlin Heidelberg.