On the use of Weighted Regression in Conjoint Analysis

Salwa Benammou (1) , Besma Souissi (2) , Gilbert Saporta (3)

1 Faculté de Droit et de Sciences Economiques et Politiques de Sousse
2 Institut Supérieur de Gestion Sousse
3 CEDRIC - MSDMA - CEDRIC. Méthodes statistiques de data-mining et apprentissage

Conjoint analysis seeks to explain an ordered categorical ordinal variable according to several variables using a multiple regression scheme. A common problem encountered, there, is the presence of missing values in classi cation-ranks. In this paper, we are interested in the cases where consumers provide a ranking of some products instead of rating these products (i.e. explained variable presents missing values).In order to deal with this problem, we propose a weighted regression scheme. We empirically show (in several cases of weighting) that, if the number of missing values is not too large, the data remain useful, and our results are close to those of the complete order. A simulation study con rms these ndings.

Mots clés: conjoint analysis; missing values; weighted regression

Domaines: Informatique [cs]; Statistiques [math.ST]

Salwa Benammou, Besma Souissi, Gilbert Saporta. On the use of Weighted Regression in Conjoint Analysis. COMPSTAT'2010, 19th International Conference on Computational Statistics, Aug 2010, Paris, France. pp.777-784. ⟨hal-01125764⟩