Stochastic Population Forecasting Based on Combinations of Expert Evaluations Within the Bayesian Paradigm

Abstract

This article suggests a procedure to derive stochastic population forecasts adopting an expert-based approach. As in previous work by Billari et al. (2012), experts are required to provide evaluations, in the form of conditional and unconditional scenarios, on summary indicators of the demographic components determining the population evolution: that is, fertility, mortality, and migration. Here, two main purposes are pursued. First, the demographic components are allowed to have some kind of dependence. Second, as a result of the existence of a body of shared information, possible correlations among experts are taken into account. In both cases, the dependence structure is not imposed by the researcher but rather is indirectly derived through the scenarios elicited from the experts. To address these issues, the method is based on a mixture model, within the so-called SupraBayesian approach, according to which expert evaluations are treated as data. The derived posterior distribution for the demographic indicators of interest is used as forecasting distribution, and a Markov chain Monte Carlo algorithm is designed to approximate this posterior. This article provides the questionnaire designed by the authors to collect expert opinions. Finally, an application to the forecast of the Italian population from 2010 to 2065 is proposed.

Projection of population structure in China using least squares support vector machine in conjunction with a Leslie matrix model

“…Various approaches have been developed to project population characteristics (Booth, 2006;Land, 1986). Stochastic population forecasts have been commonly employed in the last decade (Alkema et al, 2011;Billari, Graziani, & Melilli, 2014;Hyndman & Booth, 2008;Lu, Hao, & Wang, 2009;Raftery, Alkema, & Gerland, 2014). These approaches are generally based on projecting agespecific mortality and fertility rate data, and introducing the projected time series rates in a Leslie matrix model (Lutz & Samir, 2010;Miller, Jensen, & Hammill, 2002;O'Neill, Balk, Brickman, & Ezra, 2001;Ortega & Poncela, 2005;Smit, Kater, Jak, & Van den Heuvel-Greve, 2006;Zeng, Land, Wang, & Gu, 2013).…”

Mokesčių ir socialinio draudimo įmokų masto ir struktūros įtakos darbo rinkai vertinimas pasitelkiant stochastiškai informatyvią ekspertinę sistemą

“…Deja, šiuo metu dar neturime nuodugnių mokslinių diskusijų apie ekspertinių sistemų tinklų kūrimą. Kujszczyk et al (1993) Billari et al (2011), Kelman et al (2002 nuomone, ekspertiniai vertinimai tampa ne tik populiarūs, bet ir veiksnūs. Tačiau ir ekspertų atsakomybė tampa vis didesnė, nes imama spręsti vis sudėtingesnes ir svarbesnes problemas.…”

Towards causal forecasting of international migration

“…Wolfgang Lutz and colleagues were among the first to introduce expert judgments (Lutz et al 1998;Lutz and Goldstein 2004) and to quantify the underlying narrative in argument-based scenarios (Lutz and Scherbov 2003). In recent years, the Bayesian approach has become the leading paradigm in probabilistic forecasting (see, e.g., Bijak (2011); Bijak and Wiśniowski (2010); Azose and Raftery (2015); Billari et al (2014); Disney et al (2015); Bijak et al (2016)). It offers a coherent framework for combining data from different sources, and for assessing the multiple uncertainties in forecasting.…”