Robust Inference in Risk Elicitation Tasks
(2020) In Journal of Risk and Uncertainty 61(3). p.195-209- Abstract
- Recent experimental evidence suggests that noisy behavior correlates strongly with personal characteristics. Since decision noise leads to bias in most elicitation tasks, there is a risk of falsely interpreting noise-driven relationships as preference driven. This puts previous studies that found a negative relation between personality measures and risk aversion into perspective and in particular raises the question of how to achieve robust inference in this domain. This paper shows, by way of an economic experiment with subjects from all walks of life, that using structural estimation to model heterogeneity of noise in combination with a balanced design allows us to mitigate the bias problem. Our estimations show that cognitive ability is... (More)
- Recent experimental evidence suggests that noisy behavior correlates strongly with personal characteristics. Since decision noise leads to bias in most elicitation tasks, there is a risk of falsely interpreting noise-driven relationships as preference driven. This puts previous studies that found a negative relation between personality measures and risk aversion into perspective and in particular raises the question of how to achieve robust inference in this domain. This paper shows, by way of an economic experiment with subjects from all walks of life, that using structural estimation to model heterogeneity of noise in combination with a balanced design allows us to mitigate the bias problem. Our estimations show that cognitive ability is related to noisy behavior rather than risk preferences. We also find age and education to be strongly related to noise, but the personality characteristics obtained using the Big Five inventory are less related to noise and more robustly correlated to risk preferences. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/552b18f3-5c69-463f-9297-74add24d0a96
- author
- Andersson, Ola ; Holm, Håkan J. LU ; Tyran, Jean-Robert and Wengström, Erik LU
- organization
- publishing date
- 2020-12-10
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Journal of Risk and Uncertainty
- volume
- 61
- issue
- 3
- pages
- 15 pages
- publisher
- Springer
- external identifiers
-
- scopus:85097488183
- ISSN
- 0895-5646
- DOI
- 10.1007/s11166-020-09341-6
- language
- English
- LU publication?
- yes
- id
- 552b18f3-5c69-463f-9297-74add24d0a96
- date added to LUP
- 2020-12-04 11:13:30
- date last changed
- 2022-04-26 22:21:01
@article{552b18f3-5c69-463f-9297-74add24d0a96,
abstract = {{Recent experimental evidence suggests that noisy behavior correlates strongly with personal characteristics. Since decision noise leads to bias in most elicitation tasks, there is a risk of falsely interpreting noise-driven relationships as preference driven. This puts previous studies that found a negative relation between personality measures and risk aversion into perspective and in particular raises the question of how to achieve robust inference in this domain. This paper shows, by way of an economic experiment with subjects from all walks of life, that using structural estimation to model heterogeneity of noise in combination with a balanced design allows us to mitigate the bias problem. Our estimations show that cognitive ability is related to noisy behavior rather than risk preferences. We also find age and education to be strongly related to noise, but the personality characteristics obtained using the Big Five inventory are less related to noise and more robustly correlated to risk preferences.}},
author = {{Andersson, Ola and Holm, Håkan J. and Tyran, Jean-Robert and Wengström, Erik}},
issn = {{0895-5646}},
language = {{eng}},
month = {{12}},
number = {{3}},
pages = {{195--209}},
publisher = {{Springer}},
series = {{Journal of Risk and Uncertainty}},
title = {{Robust Inference in Risk Elicitation Tasks}},
url = {{http://dx.doi.org/10.1007/s11166-020-09341-6}},
doi = {{10.1007/s11166-020-09341-6}},
volume = {{61}},
year = {{2020}},
}