Question

Nonparametric tests are more likely to be appropriate than parametric tests when: a. The response variable is severely skewed b. The response variable is measured on at least an interval scale c. The sample size is large d. Values in the population are normally distributed

Answer 1

Nonparametric tests called as distribution-free tests because they do not assume that the data follow a specific distribution. When your data do not meet the assumptions of the parametric test you should use nonparametric tests . e.g Normality assumption.

So option d is incorrect. also for large sample size we can assume distribution of data as normal by central limit therem, so option c is also incorrect. Option b is incorrect because by measuring on an interval scale c we just shift the whole distribution by c.

Now let us come to option a. This is correct because non-parametric test usualy give better result with small sample size and skewed data.