Parametric vs. Non-Parametric Tests
Traditionally, two types of tests used for proving the null hypothesis either right or wrong are distinguished. The use of parametric tests requires the availability of the information about the target population. For instance, the ANOVA tool, as well as the z-test, falls under the category of parametric tests since they require that the data such as the number or percentage of the target population should be provided to run the calculations. Specifically, the following requirements are typically listed for parametric tests:
- Population variance must be calculated;
- The measurement must be carried out on at least an interval level;
- The data must come from random samples.
Non-parametric tests, in their turn, are typically defined as the statistical tools for testing that can be carried out in the scenarios when there is no information about the variables available (Gravetter & Wallnau, 2013).
Examples
Parametric tests such as ANOVA can be viewed as perfect tools in addressing the needs of a very specific population with a unique problem. For instance, when determining the efficacy of a particular management strategy in two teams consisting of twenty people each the use of the parametric test should be viewed as the means of conducting the research. A rank-sum test, in its turn, is often viewed as a clear-cut example of a non-parametric test.
Measures of Central Tendency
The study that I am currently working on requires the adoption of a parametric test since there is a specific number of patients with a unique problem that needs to be addressed. In other words, the population-related information is quite clear and, thus, allows for the adoption of a parametric test.
It is expected that the data analysis should be carried out by comparing the data retrieved from the assessments that were carried out prior to the provision of the corresponding treatment to the participants, and the ones that were received after the intervention.
As far as the levels of measurement are concerned, it will be reasonable to analyze the data at the interval level. The reasons for choosing the identified framework concern primarily the fact that, to provide a careful evaluation of the progress made by the participants, one will have to take the concept known as distance into account. In other words, the extent, which the variances in the identified groups reach, will have to be identified and assessed together with the location of the factors that either inhibit the learning process or promote it among learners with disabilities (LD).
At present, the use of the t-test can be considered as the primary means of data analysis. Seeing that there is a strong need to locate the difference between the two sets of data, i.e., the level of competence among the participants prior to the intervention and their knowledge after the treatment is over, the application of ANOVA does not seem required; instead, the t-test should be considered as the most reasonable and basic option.
Random samples will be taken in order to test the null hypothesis. It is expected that the t-test will help prove that there is a significant difference in the progress of the PLD that have been communicating in the crossed networks settings and those that undergo the traditional therapy (Wray, Aspland, Taghzouit, & Pace, 2012). The outcomes of the research are bound to serve as the prerequisites for improving the quality of care in the contemporary nursing setting (Smith, Ooms, & Marks-Maran, 2016).
Reference List
Gravetter, F. J., & Wallnau, L. B. (2013). Essentials of statistics for the behavioral sciences. Boston, MA: Cengage Learning.
Smith, P., Ooms, A., & Marks-Maran, D. (2016). Active involvement of learning disabilities service users in the development and delivery of a teaching session to pre-registration nurses: Students’ perspectives. Nurse Education in Practice, 16(1), 111-118.
Wray, J., Aspland, J., Taghzouit, J., & Pace, K. (2012). Making the nursing curriculum more inclusive for students with specific learning difficulties (SpLD): Embedding specialist study skills into a core module. Nurse Education Today, 33(6), 602–607.