The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
library(gp3bayes)
sim <- simulate_advanced_pupil_timecourse(
n_participants = 12,
trials_per_participant = 4,
time_points = 31,
seed = 3050
)
base <- specify_advanced_pupil_timecourse_model(sim$data, temporal_structure = "smooth", family = "gaussian")
suite <- create_pupil_advanced_sensitivity_suite(base)
suite
#> <gp3bayes_pupil_advanced_sensitivity_suite>
#> Scenarios: 10
#> scenario dimension value
#> baseline baseline declared
#> likelihood_student family student
#> sigma_condition residual_scale condition
#> sigma_time residual_scale time
#> sigma_condition_time residual_scale condition_time
#> ac_ar1 autocorrelation ar1
#> ac_ar2 autocorrelation ar2
#> ac_arma11 autocorrelation arma11
#> temporal_linear temporal_structure linear
#> temporal_gaussian_process temporal_structure gaussian_processThe sensitivity suite is a pre-fit registry of alternatives. It does not fit or rank models.
robust <- materialize_pupil_advanced_sensitivity_scenario(suite, "likelihood_student")
gp <- materialize_pupil_advanced_sensitivity_scenario(suite, "temporal_gaussian_process")
fit_smooth <- fit_advanced_pupil_model_backend(base, backend = "cmdstanr")
fit_robust <- fit_advanced_pupil_model_backend(robust, backend = "cmdstanr")
fit_gp <- fit_advanced_pupil_model_backend(gp, backend = "cmdstanr")
models <- create_pupil_model_set(
smooth_gaussian = fit_smooth,
smooth_student = fit_robust,
gp_gaussian = fit_gp,
predictive_target = "future_segment"
)
cmp <- compare_pupil_models(models, criterion = "loo")
pupil_model_comparison_table(cmp)
plot_pupil_model_comparison(cmp)
pupil_model_weights(cmp, method = "stacking")Weights are returned only as explicit evidence. gp3bayes does not automatically average predictions or declare the highest-weight model substantively correct.
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.