Graphical models are pivotal in studying the conditional independence structure of a set of random variables. Circular variables, arising in several contexts and fields, are characterized by periodicity. Models for studying the dependence/independence structure of circular variables are under-explored but of increasing interest. This paper delves into two multivariate circular distributions, the Wrapped Normal and the Inverse Stereographic Normal distribution as undirected graphical models. For each of these distributions, we study their key properties with respect to conditional independence and introduce specific classes of graphical models. The usefulness of the proposal is shown by modelling the conditional independence among dihedral angles that play a critical role in defining the three-dimensional structure and functionality of proteins. This can provide valuable insights, for instance, into the multiform protein folding understanding.

Gaussian-related undirected graphical models for circular variables / Anna Gottard; Agnese Panzera. - In: STATISTICS. - ISSN 0233-1888. - ELETTRONICO. - 58:(2024), pp. 1224-1247. [10.1080/02331888.2024.2400179]

Gaussian-related undirected graphical models for circular variables

Anna Gottard
;
Agnese Panzera
2024

Abstract

Graphical models are pivotal in studying the conditional independence structure of a set of random variables. Circular variables, arising in several contexts and fields, are characterized by periodicity. Models for studying the dependence/independence structure of circular variables are under-explored but of increasing interest. This paper delves into two multivariate circular distributions, the Wrapped Normal and the Inverse Stereographic Normal distribution as undirected graphical models. For each of these distributions, we study their key properties with respect to conditional independence and introduce specific classes of graphical models. The usefulness of the proposal is shown by modelling the conditional independence among dihedral angles that play a critical role in defining the three-dimensional structure and functionality of proteins. This can provide valuable insights, for instance, into the multiform protein folding understanding.
2024
58
1224
1247
Anna Gottard; Agnese Panzera
File in questo prodotto:
File Dimensione Formato  
Gaussian-related undirected graphical models for circular variables.pdf

accesso aperto

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 3.7 MB
Formato Adobe PDF
3.7 MB Adobe PDF

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

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1383912
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact