Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Fixing Sample Biases in Experimental Data Using Agent-Based Modelling

Farjam, Mike LU and Bravo, Giangiacomo (2020) 14th Social Simulation Conference, 2018 In Springer Proceedings in Complexity p.155-159
Abstract

We present how agent-based models can be used to correct for biases in a sample. The approach is generally useful for behavioural experiments where participants interact over time. The model we developed copied mechanics of a behavioural experiment conducted earlier, and agents in the model faced the same strategic choices as human participants did. We used the data from the experiment to calibrate agent behaviour such that agents reproduced patterns observed in the experiment. After this learning phase, we resampled agents such that their characteristics (political orientation) were similar to those found in the real world. We found that after the correction for the bias, agents produced patterns closer to those commonly found.

Please use this url to cite or link to this publication:
author
and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Agent-based modelling, Bias, Experiment, Methodology
host publication
Advances in Social Simulation - Looking in the Mirror, 2018
series title
Springer Proceedings in Complexity
editor
Wijermans, Nanda ; Bravo, Giangiacomo ; Borit, Melania and Verhagen, Harko
pages
5 pages
publisher
Springer Nature
conference name
14th Social Simulation Conference, 2018
conference location
Stockholm, Sweden
conference dates
2018-08-20 - 2018-08-24
external identifiers
  • scopus:85087890066
ISSN
2213-8692
2213-8684
ISBN
978-3-030-34127-5
9783030341268
DOI
10.1007/978-3-030-34127-5_14
language
English
LU publication?
no
id
215622e4-e9a7-4434-981a-89ab01aff344
date added to LUP
2021-02-19 10:31:33
date last changed
2024-10-03 21:05:00
@inproceedings{215622e4-e9a7-4434-981a-89ab01aff344,
  abstract     = {{<p>We present how agent-based models can be used to correct for biases in a sample. The approach is generally useful for behavioural experiments where participants interact over time. The model we developed copied mechanics of a behavioural experiment conducted earlier, and agents in the model faced the same strategic choices as human participants did. We used the data from the experiment to calibrate agent behaviour such that agents reproduced patterns observed in the experiment. After this learning phase, we resampled agents such that their characteristics (political orientation) were similar to those found in the real world. We found that after the correction for the bias, agents produced patterns closer to those commonly found.</p>}},
  author       = {{Farjam, Mike and Bravo, Giangiacomo}},
  booktitle    = {{Advances in Social Simulation - Looking in the Mirror, 2018}},
  editor       = {{Wijermans, Nanda and Bravo, Giangiacomo and Borit, Melania and Verhagen, Harko}},
  isbn         = {{978-3-030-34127-5}},
  issn         = {{2213-8692}},
  keywords     = {{Agent-based modelling; Bias; Experiment; Methodology}},
  language     = {{eng}},
  pages        = {{155--159}},
  publisher    = {{Springer Nature}},
  series       = {{Springer Proceedings in Complexity}},
  title        = {{Fixing Sample Biases in Experimental Data Using Agent-Based Modelling}},
  url          = {{http://dx.doi.org/10.1007/978-3-030-34127-5_14}},
  doi          = {{10.1007/978-3-030-34127-5_14}},
  year         = {{2020}},
}