Modelling Ordinal Responses with Uncertainty: a Hierarchical Marginal Model with Latent Uncertainty components
Preprint
Abstract
This paper proposes a multivariate model for ordinal rating responses, allowing for uncertainty in answering. In responding to rating questions, an individual may give answers either according to his/her knowledge (feeling) or to his/her level of indecision (uncertainty), typically driven by a response style. Since ignoring this uncertainty may lead to misleading results, we define the joint distribution of the ordinal responses via a mixture of components, characterized by uncertainty in answering to a subset of variables. The effectiveness of the proposed model is attested through applications to real data and supported by a Monte Carlo study.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- A class of mixture models for multidimensional ordinal dataStatistical Modelling, 2016
- Mixture models for ordinal responses to account for uncertainty of choiceAdvances in Data Analysis and Classification, 2016
- Varying uncertainty in CUB modelsAdvances in Data Analysis and Classification, 2016
- Uncertainty and framing in a valuation taskJournal of Economic Psychology, 2013
- Middle category endorsement in odd-numbered Likert response scales: Associated item characteristics, cognitive demands, and preferred meaningsJournal of Research in Personality, 2009
- Identifiability of extended latent class models with individual covariatesComputational Statistics & Data Analysis, 2008
- A mixture model for preferences data analysisComputational Statistics & Data Analysis, 2005
- General Knowledge Overconfidence: Cross-National Variations, Response Style, and “Reality”Organizational Behavior and Human Decision Processes, 1997
- Multivariate Logistic ModelsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1995
- The Optimal Number of Response Alternatives for a Scale: A ReviewJournal of Marketing Research, 1980