A comparative analysis of rankings of Polish provinces in terms of social cohesion for metric and interval-valued data

Marek Walesiak , Grażyna Dehnel

Abstract

The article describes a comparative analysis of rankings of Polish provinces in terms of social cohesion based on metric and interval-valued data between 1st and 3rd quartiles (50% of observations), 1st and 9th deciles (80% of observations) and the minimum and maximum (100% observations). The rankings were obtained using a hybrid approach combining the use of multidimensional scaling (MDS) with linear ordering. Interval-valued variables characterise the objects of interests more accurately than metric data. Metric data are of an atomic nature, i.e. an observation of each variable is expressed as a single real number. In contrast, an observation of each intervalvalued variable is expressed as an interval. Interval-valued data were derived by aggregating metric data on social cohesion at the level of districts to the province level. All observations were included in the aggregation and then outliers were omitted.
Author Marek Walesiak - Wroclaw University of Economics
Marek Walesiak,,
-
, Grażyna Dehnel (WIiGE / KS)
Grażyna Dehnel,,
- Department of Statistics
Pages250-258
Publication size in sheets0.5
Book Papież Monika, Śmiech Sławomir (eds.): The 13th Professor Aleksander Zelias International Conference on Modelling and Forecasting of Socio-Economic Phenomena. Conference Proceedings, Socio-Economic Modelling and Forecasting, 2019, Wydawnictwo C.H. Beck, ISBN 978-83-8158-734-1, 258 p.
Keywords in Polishspójność społeczna, dane symboliczne interwałowe, skalowanie wielowymiarowe, miary agregatowe, obserwacje odstające
Keywords in Englishsocial cohesion, interval-valued data, multidimensional scaling, composite indicators, outliers
URL http://pliki.konferencjazakopianska.pl/proceedings_2019/pdf/r29.pdf
Languageen angielski
Score (nominal)20
Score sourcepublisherList
ScoreMinisterial score = 20.0, 10-01-2020, ChapterFromConference
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?