Uncertainties in modeling low probability/high consequence events: application to population projections and models of sea-level rise

Author

Shlyakhter, Alexander I. ; Kammen, Daniel M.

Author_Institution

Dept. of Phys., Harvard Univ., Cambridge, MA, USA

fYear

1993

fDate

25-28 Apr 1993

Firstpage

246

Lastpage

253

Abstract

The authors present a simple method for estimating uncertainty in modeling and forecasts based on an analysis of errors in old measurements and projections. They develop an empirical method of quantifying the uncertainty in a time-series of historical forecasts for which the actual values are now known. Probabilities of large deviations are parametrized by an exponential function with one free parameter. This formulation is illustrated by quantifying uncertainties in national population projections and by estimating the probability of extreme sea-level rise resulting from global warming

Keywords

demography; forecasting theory; probability; statistical analysis; time series; uncertainty handling; empirical method; exponential function; extreme sea-level rise; forecasts; global warming; historical forecasts; national population projections; old measurements; population projections; time-series; uncertainty; Current measurement; Data analysis; Demand forecasting; Error analysis; Fasteners; Gaussian distribution; Global warming; Predictive models; Probability distribution; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Uncertainty Modeling and Analysis, 1993. Proceedings., Second International Symposium on

Conference_Location

College Park, MD

Print_ISBN

0-8186-3850-8

Type

conf

DOI

10.1109/ISUMA.1993.366761

Filename

366761