On 1α$\frac{1}{\alpha }$-characteristic functions and applications to asymptotic statistical inference

Alessandro Selvitella

Communications in Statistics - Theory and Methods, 2017, vol. 46, issue 4, 1941-1958

Abstract: In this paper, we give emphasis to a method to do statistical inference and to study properties of random variables, whose probability density functions (pdfs) do not possess good regularity, decay, and integrability properties. The main tool will be what we will call 1α$\frac{1}{\alpha }$-characteristic function, a generalization of the classical characteristic function that is basically a measurable transform of pdfs. In this perspective and using this terminology, we will restate and prove theorems, such as the law of large numbers and the central limit theorem that now, after this measurable transform, apply to basically every distribution, upon the correct choice of a free parameter α. We apply this theory to hypothesis testing and to the construction of confidence intervals for location parameters. We connect the classical parameters of a distribution to their related 1/α-counterparts, that we will call 1α$\frac{1}{\alpha }$-momenta. We treat in detail the case of the multivariate Cauchy distribution for which we compute explicitly all the 1α$\frac{1}{\alpha }$-expected values and 1α$\frac{1}{\alpha }$-variances in dimension n = 1 and for which we construct an approximate confidence interval for the location parameter μ, by means of asymptotic theorems in the 1α$\frac{1}{\alpha }$-context. Among the other things and to illustrate the usefulness of this point of view, we prove some new characterizations of the Poisson distribution, the uniform discrete, and the uniform continuous distribution.

Date: 2017
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2015.1030427 (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:lstaxx:v:46:y:2017:i:4:p:1941-1958

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2015.1030427

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().