A closed testing procedure for comparison between successive variances

Navdeep Singh and Parminder Singh

Journal of Applied Statistics, 2020, vol. 47, issue 3, 541-553

Abstract: For a sequence of $k $k independent normally distributed random samples from $k $k populations with different means and variances, it is common to know which successive populations differ significantly with respect to a parameter. In this article, a stepwise test procedure is proposed for simultaneously testing the difference between successive normal populations with respect to the variance. The proposed procedure controls the family-wise error rate strongly. Critical constants, obtained numerically, are tabulated for the use of the proposed procedure. An extension of the proposed procedure for detecting the difference between scale parameters of successive two-parameter exponential populations is given. A Monte Carlo simulation study of the power comparison of the proposed procedure with a single-step procedure revealed that the proposed stepwise procedure performs better than the single-step procedure. Finally, a numerical example is also given to illustrate the advantage of the proposed procedure in comparison to the single-step procedure.

Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/02664763.2019.1645819 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:japsta:v:47:y:2020:i:3:p:541-553

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/02664763.2019.1645819

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().