Skip to content

Minor enhancement for the pst_Q model #176

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bugoverdose wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

Minor enhancement for the pst_Q model #176

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
efeaa10
feat(pst_Q): add plot_pst_Q
bugoverdose Dec 17, 2025
32937f1
feat(pst_Q): add prediction error as generated quantities
bugoverdose Dec 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions R/R/hBayesDM_model.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,6 +298,9 @@ hBayesDM_model <- function(task_name = "",
if ((model_name == "hgf_ibrb") && (model_type == "single")) {
pars <- c(pars, paste0("logit_", names(parameters)))
}
if ((task_name == "pst") && (model_name == "Q")) {
pars <- c(pars, "pe")
}
pars <- c(pars, "log_lik")
if (modelRegressor) {
pars <- c(pars, names(regressors))
Expand Down
8 changes: 8 additions & 0 deletions R/inst/plotting/plot_functions.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -405,6 +405,14 @@ plot_cra_exp <- function(obj, fontSize = 10, ncols = 3, binSize = 30) {
return(h_all)
}

plot_pst_Q <- function(obj, fontSize = 10, ncols = 2, binSize = 30) {
pars = obj$parVals
h1 = plotDist(sample = pars$mu_alpha, fontSize = fontSize, binSize = binSize, xLim = c(0,1), xLab = expression(paste(alpha, " (Learning Rate)")))
h2 = plotDist(sample = pars$mu_beta, fontSize = fontSize, binSize = binSize, xLim = c(0,10), xLab = expression(paste(beta, " (Inverse Temp.)")))
h_all = multiplot(h1, h2, cols = ncols)
return(h_all)
}

plot_pst_gainloss_Q <- function(obj, fontSize = 10, ncols = 3, binSize = 30) {
pars = obj$parVals
h1 = plotDist(sample = pars$mu_alpha_pos, fontSize = fontSize, binSize = binSize, xLim = c(0,2), xLab = expression(paste(alpha[pos], " (+Learning Rate)")))
Expand Down
20 changes: 9 additions & 11 deletions commons/stan_files/pst_Q.stan
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,24 +31,23 @@ transformed parameters {
vector<lower=0,upper=1>[N] alpha;
vector<lower=0,upper=10>[N] beta;

alpha = Phi_approx(mu_pr[1] + sigma[1] * alpha_pr);
beta = Phi_approx(mu_pr[2] + sigma[2] * beta_pr) * 10;
alpha = Phi_approx(mu_pr[1] + sigma[1] * alpha_pr);
beta = Phi_approx(mu_pr[2] + sigma[2] * beta_pr) * 10;
}

model {
// Priors for group-level parameters
mu_pr ~ normal(0, 1);
mu_pr ~ normal(0, 1);
sigma ~ normal(0, 0.2);

// Priors for subject-level parameters
alpha_pr ~ normal(0, 1);
beta_pr ~ normal(0, 1);
beta_pr ~ normal(0, 1);

for (i in 1:N) {
int co; // Chosen option
real delta; // Difference between two options
real pe; // Prediction error
//real alpha;
vector[6] ev; // Expected values

ev = initial_values;
Expand All @@ -71,19 +70,18 @@ generated quantities {
// For group-level parameters
real<lower=0,upper=1> mu_alpha;
real<lower=0,upper=10> mu_beta;
real pe[N, T]; // Prediction error

// For log-likelihood calculation
real log_lik[N];

mu_alpha = Phi_approx(mu_pr[1]);
mu_beta = Phi_approx(mu_pr[2]) * 10;
mu_alpha = Phi_approx(mu_pr[1]);
mu_beta = Phi_approx(mu_pr[2]) * 10;

{
for (i in 1:N) {
int co; // Chosen option
real delta; // Difference between two options
real pe; // Prediction error
//real alpha;
vector[6] ev; // Expected values

ev = initial_values;
Expand All @@ -97,8 +95,8 @@ generated quantities {
delta = ev[option1[i, t]] - ev[option2[i, t]];
log_lik[i] += bernoulli_logit_lpmf(choice[i, t] | beta[i] * delta);

pe = reward[i, t] - ev[co];
ev[co] += alpha[i] * pe;
pe[i, t] = reward[i, t] - ev[co];
ev[co] += alpha[i] * pe[i, t];
}
}
}
Expand Down