Multidimensional Well-Being: A Bayesian Networks Approach
- PDF / 1,291,955 Bytes
- 27 Pages / 439.37 x 666.142 pts Page_size
- 13 Downloads / 200 Views
Multidimensional Well‑Being: A Bayesian Networks Approach Lidia Ceriani1 · Chiara Gigliarano2 Accepted: 6 July 2020 © Springer Nature B.V. 2020
Abstract The study of multidimensional well-being has long recognized the importance of formalizing the interaction between dimensions, but came short of treating this formally. In this paper, we show that the statistical technique of Bayesian Networks is an intuitive and powerful instrument that allows to model the dependence structure among the different dimension of well-being. Moreover, Bayesian Networks are useful to understand the effectiveness of policies directed to one or more dimensions, as well as to design more effective interventions to improve well-being. The new approach is illustrated with an empirical application for a selection of Western and Eastern European countries. Keywords Multivariate analysis · Directed acyclic graphs · Probabilistic inference · Wellbeing
1 Introduction Starting from Amartya Sen seminal contribution (Sen 1980, 1985), the economic literature has underlined the necessity of defining individual well-being as a multidimensional concept rather than relying only on income or consumption. Notwithstanding a variety of definitions of multidimensional well-being and multiple approaches developed in the last two decades by researchers, governments, national statistical offices, and international organizations, the list of aspects of someone’s life that matter for defining her well-being has been consolidated around the following dimensions: (1) material living standards, including level of income, consumption and wealth; (2) health; (3) education; (4) extent of personal activities, including work; (5) political voice and governance; (6) participation to social activities and civil society; (7) social connections and relationships; (8) security, * Chiara Gigliarano [email protected] Lidia Ceriani [email protected] 1
School of Foreign Service, Georgetown University, ICC 394, 37th St NW & O St NW, Washington, DC 20057, USA
2
Department of Economics, Università degli Studi dell’Insubria, Via Monte Generoso, 71, 21100 Varese, VA, Italy
13
Vol.:(0123456789)
L. Ceriani, C. Gigliarano
of economic as well as physical nature; (9) satisfaction with life, (10) environment. See, among others, Aaberge and Brandolini (2015); OECD (2015); CNEL and ISTAT (2015), and Stiglitz et al. (2010). The current literature typically distinguishes between two different approaches for measuring multidimensional well-being: a dashboard approach, and some form of aggregation. In the first case, well-being is displayed in a “a portfolio of dimension-wise wellbeing indicators” (Chakravarty 2018, p. 3). Examples of dashboard approach include, among others, the OECD’s Better Life Index (OECD 2015), the Italian Equitable and Sustainable Well-being (CNEL and ISTAT 2015), and the United Kingdom’s National Wellbeing Measure (Office for National Statistics 2015). By keeping each indicator separate, this approach has two main advantages. It h
Data Loading...
