PhilSci Archive

Probabilistic Forecasting: Why Model Imperfection Is a Poison Pill

Frigg, Roman and Bradley, Seamus and Machete, Reason and Smith, Leonard A. (2013) Probabilistic Forecasting: Why Model Imperfection Is a Poison Pill.

[img]
Preview
Text
EPSA_Paper.pdf

Download (2MB) | Preview

Abstract

Mathematical models have gained prominence among the scientific methods used to generate forecasts. This raises the question of exactly what these models deliver: can these models provide the results as advertised? The aim of this paper is to urge some caution. We argue that if there is only the slightest model imperfection, then treating model outputs as decision relevant probabilistic forecasts can be misleading.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Published Article or Volume
Creators:
CreatorsEmailORCID
Frigg, Romanr.p.frigg@lse.ac.uk
Bradley, SeamusSeamus.Bradley@lrz.uni-muenchen.de
Machete, Reason
Smith, Leonard A.lenny@maths.ox.ac.uk
Keywords: mathematical models, structural model error, UKCP
Subjects: Specific Sciences > Physics > Classical Physics
General Issues > Models and Idealization
Depositing User: Roman Frigg
Date Deposited: 19 Jul 2022 13:01
Last Modified: 19 Jul 2022 13:01
Item ID: 20935
Subjects: Specific Sciences > Physics > Classical Physics
General Issues > Models and Idealization
Date: 2013
URI: https://philsci-archive.pitt.edu/id/eprint/20935

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item