SuperLSS#
SuperLSS fits several parameters of a response distribution together, one
predictor per parameter. Pass a family first, then one predictor declaration
per parameter using the family’s helper methods; build the terms inside each
declaration with s(), cat(),
re(), ti(), term()
and interaction(). Start with the
tutorial. The strip below follows a
model through its life. Each page under it opens with the members you reach
for first, and its tables list every member in the group, each with its own
page.
Fit several parameters of a response distribution jointly. |
The family and the parameters it models.
fit_reml estimates smoothing jointly; fit holds it fixed.
Means, every parameter, quantiles, simulated draws.
Residuals, binned moments, calibration, scores.
Risk curves, density fans, the book total.
All the groups, in the order you meet them: