An original approach to anomalies in intertemporal choices through functional data analysis: Theory and application for the study of Hikikomori syndrome

Abstract

The pattern of intertemporal preferences is related to critical behavioural aspects involving individuals' emotional and cognitive spheres. The characteristics of the discount function can provide a quantitative interpretation of pathological conditions, such as addiction, depression, and Attention Deficit Hyperactivity Disorder (ADHD). In the literature on intertemporal preferences, researchers commonly refer to parametric models, which are often characterized by structural limitations, mainly when behavioral anomalies manifest in the dynamics of choices. This paper proposes using Functional Data Analysis (FDA) as an innovative tool to analyze discount functions' characteristics and interpret intertemporal choices' anomalies, overcoming the limits of a completely parametric approach. To show the potential of FDA in studying intertemporal decisions, this research proposes a novel methodology for dealing with discount functions and a possible application to the so-called Hikikomori condition. The latter is a social phenomenon that has recently raised concerns and claimed the need for in-depth studies. Although the application focuses on an original implementation of the functional analysis of variance approach to capture possible differences between groups of curves, the main novelty of the paper lies in the methodology for treating discount functions via FDA in the context of intertemporal choices.