PhilSci Archive

Why Average When You Can Stack? Better Methods for Generating Accurate Group Credences

Kinney, David (2021) Why Average When You Can Stack? Better Methods for Generating Accurate Group Credences. [Preprint]

[img]
Preview
Text
Why_Average_When_You_Can_Stack_Archive_Version.pdf

Download (437kB) | Preview

Abstract

Formal and social epistemologists have devoted significant attention to the question of how to aggregate the credences of a group of agents who disagree about the probabilities of events. Most of this work focuses on strategies for calculating the mean credence function of the group. In particular, Moss (2011) and Pettigrew (2019) argue that group credences should be calculated by taking a linear mean of the credences of each individual in the group. Both of these arguments begin from the premise that that sole determinant of a credence function's epistemic value is its accuracy, before introducing additional premises to derive the conclusion that credences ought to be aggregated by linear averaging. In this paper, I argue that if the epistemic value of a credence function is determined solely by its accuracy, then we should not generate group credences by finding the mean of the credences of the individuals in a group. Rather, where possible, we should aggregate the underlying statistical models that individuals use to generate their credence function, using "stacking" techniques from statistics and machine learning first developed by Wolpert (1992). My argument draws on a result by Le and Clarke (2017) that shows the power of stacking techniques to generate predictively accurate aggregations of statistical models, even when all models being aggregated are highly inaccurate.


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

Item Type: Preprint
Creators:
CreatorsEmailORCID
Kinney, Daviddavid.kinney@santafe.edu
Keywords: group credences belief aggregation social epistemology
Subjects: General Issues > Social Epistemology of Science
Depositing User: Dr David Kinney
Date Deposited: 12 Aug 2021 03:14
Last Modified: 12 Aug 2021 03:14
Item ID: 19432
Subjects: General Issues > Social Epistemology of Science
Date: 10 August 2021
URI: http://philsci-archive.pitt.edu/id/eprint/19432

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item