Albers, Casper J. and Schaafsma, Willem
Goodness of fit testing using a specific density estimate.
Statistics & Decisions, 26(1) pp. 3–23.
Full text available as:
Due to copyright restrictions, this file is not available for public download
To test the hypothesis H0: f=? that an unknown density f is equal to a specified one, ?, an estimate f^ of f is compared with ?. The total variation distance || f^-?||1 is used as test statistic. The density estimate f^ considered is a peculiar one. A table of critical values is provided, this table is applicable for arbitrary ?. Relations with other methods, Neyman´s smooth tests in particular, are discussed and power comparisons are performed. In certain situations, our test is recommendable. An example from practice is provided.
||2008 Oldenbourg Wissenschaftsverlag, München
||goodness of fit; Neyman smooth tests; power analysis
||Mathematics, Computing and Technology
||18 Aug 2010 11:34
||06 Dec 2010 17:10
Actions (login may be required)