TY - JOUR
T1 - Hierarchical Bayesian inference for concurrent model fitting and comparison for group studies
AU - Piray, Payam
AU - Dezfouli, Amir
AU - Heskes, Tom
AU - Frank, Michael J.
AU - Daw, Nathaniel D.
N1 - Funding Information:
We acknowledge support from NIDA through grant R01DA038891, part of the CRCNS program (N.D.D). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Publisher Copyright:
© 2019 Piray et al.
PY - 2019/6
Y1 - 2019/6
N2 - Computational modeling plays an important role in modern neuroscience research. Much previous research has relied on statistical methods, separately, to address two problems that are actually interdependent. First, given a particular computational model, Bayesian hierarchical techniques have been used to estimate individual variation in parameters over a population of subjects, leveraging their population-level distributions. Second, candidate models are themselves compared, and individual variation in the expressed model estimated, according to the fits of the models to each subject. The interdependence between these two problems arises because the relevant population for estimating parameters of a model depends on which other subjects express the model. Here, we propose a hierarchical Bayesian inference (HBI) framework for concurrent model comparison, parameter estimation and inference at the population level, combining previous approaches. We show that this framework has important advantages for both parameter estimation and model comparison theoretically and experimentally. The parameters estimated by the HBI show smaller errors compared to other methods. Model comparison by HBI is robust against outliers and is not biased towards overly simplistic models. Furthermore, the fully Bayesian approach of our theory enables researchers to make inference on group-level parameters by performing HBI t-test.
AB - Computational modeling plays an important role in modern neuroscience research. Much previous research has relied on statistical methods, separately, to address two problems that are actually interdependent. First, given a particular computational model, Bayesian hierarchical techniques have been used to estimate individual variation in parameters over a population of subjects, leveraging their population-level distributions. Second, candidate models are themselves compared, and individual variation in the expressed model estimated, according to the fits of the models to each subject. The interdependence between these two problems arises because the relevant population for estimating parameters of a model depends on which other subjects express the model. Here, we propose a hierarchical Bayesian inference (HBI) framework for concurrent model comparison, parameter estimation and inference at the population level, combining previous approaches. We show that this framework has important advantages for both parameter estimation and model comparison theoretically and experimentally. The parameters estimated by the HBI show smaller errors compared to other methods. Model comparison by HBI is robust against outliers and is not biased towards overly simplistic models. Furthermore, the fully Bayesian approach of our theory enables researchers to make inference on group-level parameters by performing HBI t-test.
UR - http://www.scopus.com/inward/record.url?scp=85068438148&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068438148&partnerID=8YFLogxK
U2 - 10.1371/journal.pcbi.1007043
DO - 10.1371/journal.pcbi.1007043
M3 - Article
C2 - 31211783
AN - SCOPUS:85068438148
SN - 1553-734X
VL - 15
JO - PLoS Computational Biology
JF - PLoS Computational Biology
IS - 6
M1 - e1007043
ER -