What Do Heteroskedasticity Tests Detect?

A test can be said to ‘detect’ an alternative hypothesis only if its power against this alternative exceeds its size. We use this principle to define the implicit null and alternative for a test. We analyze the performance of several tests for location and scale parameters. We show that there are many situations in which heteroskedasticity is impossible to detect: any test has zero power against many heteroskedastic alternatives.

MoreLess

Year of publication:	1989-04
Authors:	Dutta, Jayasri ; Zaman, Asad

More details

Type of publication:	Book / Working Paper
Language:	English
Notes:	Dutta, Jayasri and Zaman, Asad (1989): What Do Heteroskedasticity Tests Detect?
Classification:	C12 - Hypothesis Testing ; c18
Source:	BASE

Persistent link: https://www.econbiz.de/10015268013