Iterative Improvement of a Power Transformation to Stabilise Variance

Joe N. Perry

Journal of the Royal Statistical Society Series C, 1987, vol. 36, issue 1, 15-21

Abstract: The usual method to estimate the exponent of a variance‐mean power‐law relationship involves the regression of the logarithm of sample variance on the logarithm of sample mean; this estimate may then be used in a power transformation to stabilise the variance of the transformed variable. A method is suggested by which this transformation may be improved, iteratively, until there is no dependence, to first order, of the variance of the transformed value on its mean; this method provides an alternative estimate of the exponent. Use of this iterative method is justified using simulated data; three examples are given.

Date: 1987
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.2307/2347841

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:bla:jorssc:v:36:y:1987:i:1:p:15-21

Ordering information: This journal article can be ordered from
http://ordering.onli ... 1111/(ISSN)1467-9876

Access Statistics for this article

Journal of the Royal Statistical Society Series C is currently edited by R. Chandler and P. W. F. Smith

More articles in Journal of the Royal Statistical Society Series C from Royal Statistical Society Contact information at EDIRC.
Bibliographic data for series maintained by Wiley Content Delivery ().