summary.vem_fit: Summary Method for VEM Fits

In fda.vi: Functional Data Analysis using Variational Inference

Summary Method for VEM Fits

Description

Provides a displayed summary of the results from vem_fit and invisibly returns a list of summary statistics, including the basis type, number of curves, selected K, active basis counts per curve, estimated model parameters, and GCV tuning results if applicable.

Reported variational posterior parameters for \sigma^2 and \tau^2 are the shape and scale of their respective Inverse-Gamma variational distributions: q(\sigma^2) = \text{IG}(\delta_1^*, \delta_2^*) and q(\tau^2) = \text{IG}(\lambda_1^*, \lambda_2^*). For composite fits (selection_metric = "per_curve"), parameters from the first curve are shown as representative values.

Usage

## S3 method for class 'vem_fit'
summary(object, ...)

Arguments

object	A vem_fit object from vem_fit.
...	Currently unused.

Value

Invisibly returns a list with element active_bases: an integer vector of active basis counts per curve.

References

da Cruz, A. C., de Souza, C. P. E., & Sousa, P. H. T. O. (2024). Fast Bayesian basis selection for functional data representation with correlated errors. arXiv:2405.20758. https://arxiv.org/abs/2405.20758

See Also

vem_fit, coef.vem_fit

Examples

  data(toy_curves)
  fit <- vem_fit(y = toy_curves$y, Xt = toy_curves$Xt, K = 8)

  summary(fit)

  # Active basis counts are returned invisibly
  s <- summary(fit)
  s$active_bases

fda.vi documentation built on June 20, 2026, 5:06 p.m.