- CFA Exams
- CFA Level I Exam
- Topic 1. Quantitative Methods
- Learning Module 8. Hypothesis Testing
- Subject 12. Parametric vs. NonParametric Tests
CFA Practice Question
Which of the following would not be an example that would require a nonparametric test?
A. The variances between two sets of population need to be tested in order to determine if they are equal.
B. The data being analyzed is a set of rankings as opposed to actual values for a set of occurrences.
C. The population on which the tests are being conducted is known not to be normally distributed.
Explanation: Variance and arithmetic mean are the two most important parameters of a population. Hence, any test involving these two variables would be considered as a parametric test.
User Contributed Comments 4
User | Comment |
---|---|
Mikehuynh | Parametric test => parameters: variances, means Nonparametric => no parameters |
Patdotcom | And, Is C an example that would require nonparametric test? Can anyone explain? |
edrei7 | Parametric tests are tests that make assumptions about the parameters (e.g. mean, standard deviation, and variance) of the population distribution from which the sample is drawn. C is making an assumption of the population distribution itself, not its parameters. |
edrei7 | Correction. Another quality of parametric tests is the assumption of normality of the underlying distribution. I guess C being not normally distributed made it the wrong answer. |