Table of Contents

API#

Bayesian#

hmetad()

Bayesian meta-d' model with hyperparametes at the group level.

extractParameters(nR_S1, nR_S2)

Extract rates and task parameters.

MLE#

metad()

Estimate meta-d' using maximum likelihood estimation (MLE).

fit_metad(nR_S1, nR_S2, nRatings[, ...])

Fit metad model using MLE.

Plotting#

plot_confidence(nR_S1, nR_S2[, fitModel, ax])

Plot nR_S1 and nR_S2 confidence ratings.

plot_roc(nR_S1, nR_S2[, fitModel, ax])

Type2 ROC curve from observed an estimated data fit.

SDT#

scores()

Hits, misses, false alarms and correct rejection from stimuli and responses.

rates()

Compute hit and false alarm rates.

dprime()

Calculate d prime.

criterion()

Response criterion.

roc_auc()

Calculate the area under the type 2 ROC curve given from confidence ratings.

Utils#

trials2counts()

Convert raw behavioral data to nR_S1 and nR_S2 response count.

discreteRatings(ratings[, nbins, verbose, ...])

Convert from continuous to discrete ratings.

trialSimulation([d, metad, mRatio, c, ...])

Simulate nR_S1 and nR_S2 response counts.

responseSimulation([d, metad, c, nRatings, ...])

Simulate response and confidence ratings for one or a group of participants.

pairedResponseSimulation([d, d_sigma, ...])

Simulate response and confidence ratings a group with 2 experimental conditions.

type2_SDT_simuation([d, noise, c, nRatings, ...])

Type 2 SDT simulation with variable noise.

ratings2df(nR_S1, nR_S2)

Convert response count to dataframe.