Combining Deterministic and Stochastic Population Projections Salvatore BERTINO
Combining Deterministic and Stochastic Population Projections Salvatore BERTINO University “La Sapienza” of Rome Eugenio SONNINO University “La Sapienza” of Rome Giampaolo LANZIERI EUROSTAT Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections
Dealing with uncertainty in deterministic projections Scenarios: theoretical frameworks with base assumptions about future developments of demographic drivers ¡ Models: quantification of theoretical assumptions (including expert’s opinion) ¡ Variants: combinations of alternative sets of deterministic quantitative assumptions ¡ Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 2
How much uncertain? Common output: Medium/Base, Low and High variants ¡ Users seek forecasts! ¡ Pitfalls of deterministic approach about uncertainty: ¡ l l no indication of preference between variants (sometimes also ambiguous labels) no associated probability Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 3
Stochastic projections ¡ Four main methods: l l Time series analysis Ex-post projections errors Experts’ judgements Micro-simulations Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 4
Adopting a fully stochastic approach? ¡ Some arguments on the difficulties of their implementation in official projections exercises: l l Technically demanding Difficult to incorporate “demographic knowledge” Persisting subjectivity in “technical” choices (e. g. , sensitivity to base period) Wide range of outcomes of little use for practical purposes Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 5
Merging the two approaches Bertino and Sonnino method (2007) based on point-event processes of fertility, mortality and migration ¡ It requires instantaneous rates for Poisson processes for each age-sex category of the demographic components ¡ Deterministic rates as input for the simulation procedure ¡ Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 6
An (ongoing) application to EUROPOP 2008 Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 7
Deterministic uncertainty ¡ Two simple ways for the calculation of the variability of a statistic of interest: l l an estimate of the variability is available before computing the deterministic projections (e. g. , expert opinion, output of a model) the variability is calculated from the different variants after computation of the deterministic projections Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 8
Linking deterministic and stochastic uncertainty - 1 ¡ Ex-ante approach: alternative sets of deterministic rates are used as input for the micro-simulations l l The number of simulations executed for each set of assumptions can be used as proxy of the confidence attributed to the given set The formula for the prediction intervals does not change: Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 9
Linking deterministic and stochastic uncertainty - 2 ¡ Ex-post approach: the available estimate of deterministic uncertainty is used directly in the formula for projections intervals l l first method: the two variances are considered independent and p is the weight attributed to the deterministic component second method: Bayesian approach Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 10
Ex-post forecast intervals ¡ First method: ¡ Second method: Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 11
Particular ex-post intervals ¡ If σd=0: ¡ If σd=σs: Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 12
Towards a mixed approach ¡ ¡ No overlapping/substitution between deterministic or stochastic approaches, but complementariness Deterministic assumptions “drive” the projections, whose uncertainty is stochastically assessed Lisbon, 28 -30 April 2010 Joint Eurostat/UNECE Work Session on Demographic Projections 13
- Slides: 13