Learn R Programming

hBayesDM (version 1.2.1)

Hierarchical Bayesian Modeling of Decision-Making Tasks

Description

Fit an array of decision-making tasks with computational models in a hierarchical Bayesian framework. Can perform hierarchical Bayesian analysis of various computational models with a single line of coding (Ahn et al., 2017) .

Copy Link

Version

Install

install.packages('hBayesDM')

Monthly Downloads

494

Version

1.2.1

License

GPL-3

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/CCS-Lab/hBayesDM

Maintainer

Woo-Young Ahn

Last Published

September 23rd, 2022

Functions in hBayesDM (1.2.1)

bandit4arm_singleA_lapse

4 Parameter Model, without C (choice perseveration) but with xi (noise). Single learning rate both for R and P.

bandit4arm_lapse

5 Parameter Model, without C (choice perseveration) but with xi (noise)

Compute Highest-Density Interval

Rescorla-Wagner (Delta) Model

bandit2arm_delta

Rescorla-Wagner (Delta) Model

bandit4arm_lapse_decay

5 Parameter Model, without C (choice perseveration) but with xi (noise). Added decay rate (Niv et al., 2015, J. Neuro).

bandit4arm_2par_lapse

3 Parameter Model, without C (choice perseveration), R (reward sensitivity), and P (punishment sensitivity). But with xi (noise)

Rescorla-Wagner (Gamma) Model

bandit4arm2_kalman_filter

bandit4arm_4par

4 Parameter Model, without C (choice perseveration)

banditNarm_lapse

5 Parameter Model, without C (choice perseveration) but with xi (noise)

banditNarm_kalman_filter

banditNarm_singleA_lapse

4 Parameter Model, without C (choice perseveration) but with xi (noise). Single learning rate both for R and P.

Cumulative Model

banditNarm_lapse_decay

5 Parameter Model, without C (choice perseveration) but with xi (noise). Added decay rate (Niv et al., 2015, J. Neuro).

Exponential-Weight Mean-Variance Model

banditNarm_delta

Rescorla-Wagner (Delta) Model

Re-parameterized version of BART model with 4 parameters

banditNarm_4par

4 Parameter Model, without C (choice perseveration)

banditNarm_2par_lapse

3 Parameter Model, without C (choice perseveration), R (reward sensitivity), and P (punishment sensitivity). But with xi (noise)

Drift Diffusion Model

Exponential Model

dbdm_prob_weight

Probability Weight Function

Exponential Subjective Value Model

Constant-Sensitivity (CS) Model

choiceRT_ddm_single

Drift Diffusion Model

Linear Subjective Value Model

Choice Reaction Time task, linear ballistic accumulator modeling

choiceRT_lba_single

Choice Reaction Time task, linear ballistic accumulator modeling

Constant-Sensitivity (CS) Model

dd_hyperbolic_single

Hyperbolic Model

Hyperbolic Model

hBayesDM-package

Hierarchical Bayesian Modeling of Decision-Making Tasks

RW + noise + bias

Function to estimate mode of MCMC samples

Extract Model Comparison Estimates

hBayesDM Model Base Function

RW (rew/pun) + noise + bias + pi

RW + noise + bias + pi

Function to plot multiple figures

General Purpose Plotting for hBayesDM. This function plots hyper parameters.

Plots individual posterior distributions, using the stan_plot function of the rstan package

Other-Conferred Utility (OCU) Model

Value-Plus-Perseverance

Plots highest density interval (HDI) from (MCMC) samples and prints HDI in the R console. HDI is indicated by a red line. Based on John Kruschke's codes.

Plots the histogram of MCMC samples.

Outcome-Representation Learning Model

Prospect Valence Learning (PVL) Delta

Prospect Valence Learning (PVL) Decay-RI

Print model-fits (mean LOOIC or WAIC values in addition to Akaike weights) of hBayesDM Models

Experience-Weighted Attraction Model

prl_rp_multipleB

Reward-Punishment Model

prl_fictitious_multipleB

Fictitious Update Model

Reward-Punishment Model

Fictitious Update Model

prl_fictitious_woa

Fictitious Update Model, without alpha (indecision point)

Drift Diffusion Model

prl_fictitious_rp

Fictitious Update Model, with separate learning rates for positive and negative prediction error (PE)

prl_fictitious_rp_woa

Fictitious Update Model, with separate learning rates for positive and negative prediction error (PE), without alpha (indecision point)

Prospect Theory, without risk aversion (RA) parameter

Signal detection theory model

Prospect Theory, without loss aversion (LA) parameter

Prospect Theory

Q Learning Model

Reinforcement Learning Drift Diffusion Model 1

Gain-Loss Q Learning Model

Function for extracting Rhat values from an hBayesDM object

Reinforcement Learning Drift Diffusion Model 6

Happiness Computational Model

Hybrid Model, with 4 parameters

Hybrid Model, with 7 parameters (original model)

Ideal Observer Model

Sequential Learning Model

Rescorla-Wagner (Delta) Model

Hybrid Model, with 6 parameters