Bayesian statistics and modelling

Schoot, Rens van de; Depaoli, Sarah; King, Ruth; Krämer, Bianca; Märtens, Kaspar; Tadesse, Mahlet G.; Vannucci, Marina; Gelman, Andrew; Veen, Duco; Willemsen, Joukje; Yau, Christopher

doi:10.1038/s43586-020-00001-2

Cited by 647 publications

(440 citation statements)

References 215 publications

Supporting

Mentioning

381

Contrasting

Unclassified

Order By: Relevance

“…Wilson & Collins put together a great guide for those interested in modeling behavioral data (Wilson & Collins, 2019), and Zhang et al discuss the important pitfalls and best practices of using RL models to the fields of social, cognitive and affective neuroscience (Zhang, Lengersdorff, Mikus, Gläscher, & Lamm, 2020). In addition to computational modeling, an overview of Bayesian statistics for parameter estimation is intuitively presented in this primer (van de Schoot et al, 2021). Tutorials and software packages are becoming invaluable assets for practical learning of computational modeling of behavioral data.…”

Section: Discussionmentioning

confidence: 99%

Computational modeling of behavioral tasks: An illustration on a classic reinforcement learning paradigm

Suthaharan¹,

Corlett²,

Ang³

2021

TQMP

View full text Add to dashboard Cite

There has been a growing interest among psychologists, psychiatrists and neuroscientists in applying computational modeling to behavioral data to understand animal and human behavior. Such approaches can be daunting for those without experience. This paper presents a stepby-step tutorial to conduct parameter estimation in R via three techniques: Maximum Likelihood Estimation (MLE), Maximum A Posteriori (MAP) and Expectation-Maximization with Laplace approximation (EML). We first demonstrate how to simulate a classic reinforcement learning paradigmthe two-armed bandit task -for N = 100 subjects; and then explain how to develop the computational model and implement the MLE, MAP and EML methods to recover the parameters. By presenting a sufficiently detailed walkthrough on a familiar behavioral task, we hope this tutorial could benefit readers interested in applying parameter estimation methods in their own research.

show abstract

Section: Discussionmentioning

confidence: 99%

Computational modeling of behavioral tasks: An illustration on a classic reinforcement learning paradigm

Suthaharan¹,

Corlett²,

Ang³

2021

TQMP

View full text Add to dashboard Cite

show abstract

“…Level-2 VPT is smaller than its Level-1 counterpart, as Level-2 VPT is more complex and may rely on the coordinated e↵ort of more distinct networks, although this finding remains to be confirmed due to relatively small sample size and high heterogeneity in NIBS methods. Moreover, the Bayesian statistics (Schmalz et al, 0;van de Schoot et al, 2021) is able to provide a more thorough investigation into null results when more VPT studies are accumulated in the future.…”

Section: Discussionmentioning

confidence: 99%

Effects of non-invasive brain stimulation on visual perspective taking: A meta-analytic study

Yao

Chopurian

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Visual perspective taking (VPT) is a critical ability required by complex social interaction. Non-invasive brain stimulation (NIBS) has been increasingly used to examine the causal relationship between brain activity and VPT, yet with heterogeneous results. In the current study, we conducted two meta-analyses to examine the effects of NIBS of the right temporoparietal junction (rTPJ) or dorsomedial prefrontal cortex (dmPFC) on VPT, respectively. We performed a comprehensive literature search to identify qualified studies, and computed the standardized effect size (ES) for each combination of VPT level (Level-1: visibility judgment; Level-2: mental rotation) and perspective (self and other). Twelve studies (rTPJ: 11 studies, 20 ESs; dmPFC: 4 studies, 18 ESs) were included in the meta-analyses. Random-effects models were used to generate the overall effects. Subgroup analyses for distinct VPT conditions were also performed. We found that stimulation of rTPJ significantly improved participants' visibility judgment from the allocentric perspective, whereas dmPFC stimulation mainly influenced Level-1 performance from the egocentric perspective. For both areas, the effects of stimulation on Level-2 performance are negligible. These findings suggest that the rTPJ and dmPFC are involved in basic allocentric and egocentric perspective-taking processes, respectively. Notably, contrary to some theoretical models, neither of them appears to be necessary for more complex VPT with a higher requirement of mental rotation. These findings may help clarify the causal roles of the rTPJ and dmPFC in VPT and emphasize the importance of specifying VPT conditions in experimental designs.

show abstract

“…In (18) the symmetry is already parametrized exactly as in the final result (12): As it increases, the inflection point I y moves towards the upper limit. At c = 0 it lies centered between the limits.…”

Section: A Appendixmentioning

confidence: 99%

Bayesian calibration, process modeling and uncertainty quantification in biotechnology

Helleckes

Osthege

Wiechert

et al. 2021

Preprint

View full text Add to dashboard Cite

High-throughput experimentation has revolutionized data-driven experimental sciences and opened the door to the application of machine learning techniques. Nevertheless, the quality of any data analysis strongly depends on the quality of the data and specifically the degree to which random effects in the experimental data-generating process are quantified and accounted for. Accordingly calibration, i.e. the quantitative association between observed quantities with measurement responses, is a core element of many workflows in experimental sciences. Particularly in life sciences, univariate calibration, often involving non-linear saturation effects, must be performed to extract quantitative information from measured data. At the same time, the estimation of uncertainty is inseparably connected to quantitative experimentation. Adequate calibration models that describe not only the input/output relationship in a measurement system, but also its inherent measurement noise are required. Due to its mathematical nature, statistically robust calibration modeling remains a challenge for many practitioners, at the same time being extremely beneficial for machine learning applications. In this work, we present a bottom-up conceptual and computational approach that solves many problems of understanding and implementing non-linear, empirical calibration modeling for quantification of analytes and process modeling. The methodology is first applied to the optical measurement of biomass concentrations in a high-throughput cultivation system, then to the quantification of glucose by an automated enzymatic assay. We implemented the conceptual framework in two Python packages, with which we demonstrate how it makes uncertainty quantification for various calibration tasks more accessible. Our software packages enable more reproducible and automatable data analysis routines compared to commonly observed workflows in life sciences. Subsequently, we combine the previously established calibration models with a hierarchical Monod-like differential equation model of microbial growth to describe multiple replicates of Corynebacterium glutamicum batch microbioreactor cultures. Key process model parameters are learned by both maximum likelihood estimation and Bayesian inference, highlighting the flexibility of the statistical and computational framework.

show abstract

Bayesian statistics and modelling

Abstract: A way to summarize one's updated knowledge, balancing prior knowledge with observed data.

Cited by 647 publications

References 215 publications

Computational modeling of behavioral tasks: An illustration on a classic reinforcement learning paradigm

Computational modeling of behavioral tasks: An illustration on a classic reinforcement learning paradigm

Effects of non-invasive brain stimulation on visual perspective taking: A meta-analytic study

Bayesian calibration, process modeling and uncertainty quantification in biotechnology

Contact Info

Product

Resources

About