Dynamic panel regression with fuzzy outputs: A two-stage estimation framework

Traditional panel data models, while effective in managing longitudinal and cross-sectional variations, are not suitable for handling imprecise data in real-world scenarios caused by vagueness, subjectivity or measurement limitations. To address these issues, this paper introduces a fuzzy linear dynamic panel data model that incorporates fuzzy response variables. Unlike existing approaches, the proposed model accounts for temporal dynamics through lagged fuzzy responses and enables accurate modeling of imprecise data. A two-stage estimation procedure utilizing the least absolute error criterion is proposed for parameter estimation. The method is validated using two real-world data sets, demonstrating superior predictive accuracy compared to existing fuzzy panel models. Thus, this work extends the applicability of panel regression to fuzzy environments and offers a robust framework for analyzing uncertain longitudinal data.