The extension of exact conditional inference to include so-called approximate conditional methods has rapidly developed in the last two decades. However, these methods are still under-used in practice, the main problem being the lack of suitable software. Several attempts have been made to implement the methods, using either computer algebra systems or statistical packages, but none is fully satisfactory. The trade-off between algebraic calculation and numerical efficiency still represents a big impediment. The aim of the paper is to discuss the problems one encounters in the implementation of higher order asymptotics and how some of these might be overcome.

On the implementation of approximate conditional inference / R., Bellio; Brazzale, Alessandra Rosalba. - In: STATISTICA APPLICATA. - ISSN 1125-1964. - STAMPA. - 11:(1999), pp. 251-271.

On the implementation of approximate conditional inference

BRAZZALE, Alessandra Rosalba
1999

Abstract

The extension of exact conditional inference to include so-called approximate conditional methods has rapidly developed in the last two decades. However, these methods are still under-used in practice, the main problem being the lack of suitable software. Several attempts have been made to implement the methods, using either computer algebra systems or statistical packages, but none is fully satisfactory. The trade-off between algebraic calculation and numerical efficiency still represents a big impediment. The aim of the paper is to discuss the problems one encounters in the implementation of higher order asymptotics and how some of these might be overcome.
1999
11
251
271
On the implementation of approximate conditional inference / R., Bellio; Brazzale, Alessandra Rosalba. - In: STATISTICA APPLICATA. - ISSN 1125-1964. - STAMPA. - 11:(1999), pp. 251-271.
R., Bellio; Brazzale, Alessandra Rosalba
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/607774
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact