Similarity-based model for ordered categorical data. (16th March 2019)

• Record Type: Journal Article
• Authors: Gayer, Gabi; Lieberman, Offer; Yaffe, Omer
• Is Part Of: Econometric reviews. Volume 38:Number 3(2019)
• Page Start: 263
• Page End: 278
• Publication Date: 2019-03-16
• Subjects: Consistency -- ergodicity -- mixing -- ordered probit -- similarity -- stationarity; C22; Econometrics -- Periodicals; 330.015195
• DOI: 10.1080/07474938.2017.1308054
• Languages: English
• ISSNs: 0747-4938

Abstract

ABSTRACT: In a large variety of applications, the data for a variable we wish to explain are ordered and categorical. In this paper, we present a new similarity-based model for the scenario and investigate its properties. We establish that the process is ψ -mixing and strictly stationary and derive the explicit form of the autocorrelation function in some special cases. Consistency and asymptotic normality of the maximum likelihood estimator of the model's parameters are proven. A simulation study supports our findings. The results are applied to the Netflix data set, comprised of a survey on users' grading of movies.