Non-Parametric Tests Flashcards
What are parametric tests?
Parametric tests make many assumptions about the nature of the population from which the observations or data were drawn (remember all SLR & ANOVA assumptions)
Based on these assumptions, the sampling distribution of test statistics was derived and we made inferences about unknown parameters
Parametric tests are more powerful when all the assumptions required by a particular statistical test are met and when we know the appropriate model to use
What are non-parametric tests?
Non-parametric tests make very few and very weak assumptions about the underlying distribution of the data and does not refer to any specific parameter of a populations distribution
Independence of observations and random samples are still required
Majority of non-parametric tests do not focus on the numerical values of the scores but rather on the rank of the scores
Ranking is useful when the required distribution of the data is unknown or other assumptions required by a parametric test are not met. Non-parametric tests can be used when parametric methods are inapplicable or the validity of their assumptions is uncertain
Non-parametric tests are useful when samples are small and uses medium rather than mean as a measure of location
Non-parametric tests are always valid, not not always powerful
What does the power of a statistical test refer to?
Power refers to how likely a test is to reject a false null hypothesis (probability of not committing a Type 2 error)
What are the types of qualitative (categorical) data?
Normal: Can be placed into categories, but these categories do not have a natural order
Ordinal: Can be placed into categories and can be ranked with respect to some characteristic. However, we cannot interpret the difference between ranked values as numbers used are arbitrary
What are the types of quantitative (numerical) data?
Interval: Has all the characteristics of ordinal data & the differences between two values have meaning. However, there is no “absolute” zero point on the scale and thus ratios between values are not meaningful
Ratio-Scaled: Has all the characteristics of interval-scale data & has a true zero point as its origin. Hence, ratios between values are meaningful
