Do parametric and non-parametric test share any of the same characteristics?
             Yes, parametric and non-parametric tests require assumptions about the data used in the tests. Both types of statistics generally assume random sampling and also assume a specific level of measurement. In both cases the assumptions for the test must be met for the test results to be valid. Second, both types of tests are hypothesis tests and require the same statement of the null hypothesis and the research hypothesis. Third, both kinds of tests have specific formulas to calculate a test statistic. These test statistics must be accurately calculated in order for the test results to be valid. Finally, both use the same type of decision process based on the likelihood of the test statistic value occurring by chance. In both cases the researcher defines a critical region often p equals .01 or p equals .05. If the test statistic (either parametric or non-parametric) falls within the critical region, the null hypothesis can be rejected.
             Discuss the major advantages and disadvantages of using parametric and non-parametric tests.
             The major advantage of non-parametric tests, often called distribution pre-tests, is that they require no particular assumption about the population distribution. More often than not, in the research setting, the shape of the population distribution is, in fact, unknown. The main advantage of parametric statistics is that they offer the researcher more statistical power to detect an effect if an effect exist. In other words, non-parametric statistics are particularly conservative tests and are less likely to detect an existing difference.
             Under what circumstances would you choose to use non-parametric over parametric tests?
             Non-parametric tests are used when (1) the sample size is small and (2) the shape of the population distribution is unknown. The reason that sample size makes a d
             ...