Abstract
In previous chapters, we discussed alternative tests of hypotheses. These tests were generally concerned with statistical measures such as the mean, variance, or proportion of a population. A mean, variance, or proportion is referred to as a parameter in statistics. To test these parameters, we generally assume that the sample observations were drawn from a normally distributed population. The assumption of normality is especially critical when the sample size is small. Tests such as the Z, t, and F tests discussed in Chap. 11 depend on assumptions about the parameters of the population, so all these tests are parametric tests or classical tests. A parametric test is generally a test based on a parametric model.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The first test is concerned with how well a set of data fits a hypothesized probability distribution. The second seeks to determine whether a relationship exists between two variables. These two tests are generally large-sample tests.
- 2.
Technically, this is not a null hypothesis, because it is stated in sample—not population—terms.
- 3.
See Kruskal W.H., Wallis W.A.: Use of ranks in one-criterion variance analysis. J. Am. Stat. Assoc. 47(152), 583–621 (1952)
- 4.
This example is adapted from results given by Jaggi, B.: Further evidence on the accuracy of management forecasts vis-à-vis analysts’ forecasts. Account. Rev. 55, 96–101 (1980)
- 5.
Other methods of comparing the predicted and observed values will be discussed in the next chapter.
- 6.
Finn, D.W., Wang, C.K., Lamb, C.W.: An examination of the effects of sample composition bias in a mail survey. J. Mark. Res. 25(Oct), 331–338 (1983).
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
Lee, CF., Lee, J.C., Lee, A.C. (2013). Nonparametric Statistics. In: Statistics for Business and Financial Economics. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-5897-5_17
Download citation
DOI: https://doi.org/10.1007/978-1-4614-5897-5_17
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-5896-8
Online ISBN: 978-1-4614-5897-5
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)