dot-bf_gee_deviance: Compute Whitened Deviance for GEE Convergence Monitoring

In lgspline: Lagrangian Multiplier Smoothing Splines for Smooth Function Estimation

Compute Whitened Deviance for GEE Convergence Monitoring

Description

Evaluates deviance in the whitened (decorrelated) space when the family supplies fam$custom_dev.resids. In that case the raw deviance residuals are divided by \sqrt{W} and then pre-multiplied by \mathbf{V}^{-1/2} before squaring and averaging. If only fam$dev.resids is available, the function falls back to the usual mean deviance (and otherwise mean squared error). Used in the GEE refinement loop (Case c) of blockfit_solve.

Usage

.bf_gee_deviance(y_vec, mu_vec, W_vec, ord, obs_wt, VhInv, fam, ...)

Arguments

y_vec	Numeric vector of observed responses.
mu_vec	Numeric vector of fitted means.
W_vec	Numeric vector of damped Newton-Raphson weights at current iterate.
ord	Integer vector of observation indices (passed to custom deviance residual functions).
obs_wt	Numeric vector of observation weights.
VhInv	\mathbf{V}^{-1/2} matrix (permuted to partition ordering).
fam	GLM family object.
...	Additional arguments forwarded to fam$custom_dev.resids.

Value

Scalar; the mean whitened deviance.

lgspline documentation built on May 8, 2026, 5:07 p.m.