On the construction of an aggregated measure of the development of interval data

Andrzej Młodak ()

Computational Statistics, 2014, vol. 29, issue 5, 895-929

Abstract: We analyse some possibilities for constructing an aggregated measure of the development of socio-economical objects in terms of their composite phenomenon (i.e., phenomenon described by many statistical features) if the relevant data are expressed as intervals. Such a measure, based on the deviation of the data structure for a given object from the benchmark of development is a useful tool for ordering, comparing and clustering objects. We present the construction of a composite phenomenon when it is described by interval data and discuss various aspects of stimulation and normalization of the diagnostic features as well as a definition of a benchmark of development (based usually on optimum or expected levels of these features). Our investigation includes the following options for the realization of this purpose: transformation of the interval model into a single–valued version without any significant loss of its statistical properties, standardization of pure intervals as well as definition of the interval “ideal” object. For the determination of a distance between intervals, the Hausdorff formula is applied. The simulation study conducted and the empirical analysis showed that the first two variants are especially useful in practice. Copyright Springer-Verlag Berlin Heidelberg 2014

Keywords: Multi–feature objects; Aggregated measure of development; Interval data; Hausdorff distance (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1007/s00180-013-0469-7 (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:spr:compst:v:29:y:2014:i:5:p:895-929

Ordering information: This journal article can be ordered from
http://www.springer.com/statistics/journal/180/PS2

DOI: 10.1007/s00180-013-0469-7

Access Statistics for this article

Computational Statistics is currently edited by Wataru Sakamoto, Ricardo Cao and Jürgen Symanzik

More articles in Computational Statistics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().