Bimodality is observed in empirical distributions of variables related to materials (glass resistance), companies (productivity) and natural phenomena (geyser eruption). Our proposal for modeling bimodality exploits the change of variables theorem requiring the choice of a generating density function which represents the main features of the phenomena under analysis, and the choice of the transforming function ϕ(x) that describes the observed departure from the expected behaviour. The novelty of this work consists in putting attention to the choice of ϕ(x) in two different cases: when bimodality arises from a slight departure from unimodality and when it is a proper structural feature of the variable under study. As an example we use the R ”geyser” dataset.

Change of Variables theorem to fit Bimodal Distributions / Ferretti, Camilla; Ganugi, Piero; Zammori, Francesco. - (2017), pp. 417-422. (Intervento presentato al convegno Conference of the Italian Statistical Society tenutosi a Florence nel 28-30 June 2017).

Change of Variables theorem to fit Bimodal Distributions

Ganugi Piero;Zammori Francesco
2017-01-01

Abstract

Bimodality is observed in empirical distributions of variables related to materials (glass resistance), companies (productivity) and natural phenomena (geyser eruption). Our proposal for modeling bimodality exploits the change of variables theorem requiring the choice of a generating density function which represents the main features of the phenomena under analysis, and the choice of the transforming function ϕ(x) that describes the observed departure from the expected behaviour. The novelty of this work consists in putting attention to the choice of ϕ(x) in two different cases: when bimodality arises from a slight departure from unimodality and when it is a proper structural feature of the variable under study. As an example we use the R ”geyser” dataset.
2017
978-88-6453-521-0
Change of Variables theorem to fit Bimodal Distributions / Ferretti, Camilla; Ganugi, Piero; Zammori, Francesco. - (2017), pp. 417-422. (Intervento presentato al convegno Conference of the Italian Statistical Society tenutosi a Florence nel 28-30 June 2017).
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11381/2848586
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact