Open Collections

Non-parametric two sample tests of statistical hypotheses

University of British Columbia

The testing of statistical hypotheses concerning two populations consists in determining the relationship between the cumulative distribution functions on the basis of random samples from each population. In the non-parametric case the only assumption made regarding the populations is that the two c.d.f's. are continuous. Thus the distribution of any statistic proposed to test the two samples must be independent of the functional form of the c.d.f.’s. One method of approach is based on the order relations of the sample values. A survey is made of such tests recently proposed and a new test is suggested based on sampling without replacement from a population of the positive integers 1, 2, 3, ... N .

Text

2012-03-09

For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.

http://hdl.handle.net/2429/41290

Mathematics

University of British Columbia

Graduate