A generative model for rank data based on an insertion sorting algorithm - Archive ouverte HAL Access content directly
Journal Articles Computational Statistics and Data Analysis Year : 2013

A generative model for rank data based on an insertion sorting algorithm

Christophe Biernacki
  • Function : Author
  • PersonId : 853117
Julien Jacques

Abstract

An original and meaningful probabilistic generative model for full rank data modelling is proposed. Rank data arise from a sorting mechanism which is generally unobservable for statisticians. Assuming that this process relies on paired comparisons, the insertion sort algorithm is known as being the best candidate in order to minimize the number of potential paired misclassifications for a moderate number of objects to be ordered. Combining this optimality argument with a Bernoulli event during paired comparison step, a model that possesses desirable theoretical properties, among which are unimodality, symmetry and identifiability is obtained. Maximum likelihood estimation can also be performed easily through an EM or a SEM-Gibbs algorithm (depending on the number of objects to be ordered) by involving the latent initial presentation order of the objects. Finally, the practical relevance of the proposal is illustrated through its adequacy with several real data sets and a comparison with a standard rank data model.
Fichier principal
Vignette du fichier
Preprint-ISR.pdf (181.79 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00441209 , version 1 (15-12-2009)
hal-00441209 , version 2 (25-06-2010)
hal-00441209 , version 3 (13-10-2012)

Identifiers

Cite

Christophe Biernacki, Julien Jacques. A generative model for rank data based on an insertion sorting algorithm. Computational Statistics and Data Analysis, 2013, 58, pp.162-176. ⟨10.1016/j.csda.2012.08.008⟩. ⟨hal-00441209v3⟩
226 View
882 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More