CausalMixGPD
  • Home
  • Roadmaps
    • Website roadmap
    • Package roadmap
  • Start
    • Start Hub
    • Roadmap
    • Usage Diagrams
    • Start Here
    • Basic Compile and Run
    • Backends and Workflow
    • Troubleshooting
  • Tracks
    • Quickstart
    • Modeling (1-arm)
    • Causal
    • Clustering
    • Kernels & tails
    • Customization
  • Examples
  • Kernels
  • Advanced
  • Developers
  • Reference
    • Reference hub
    • Function reference by job
  • News
  • Cite
  • Coverage
  • API Reference

On this page

  • What must hold
  • Where to implement
  • What to test
  • Prereqs
  • Outputs
  • Interpretation
  • Next

How to add or modify a tail option

This page covers modifications to the GPD splice (or alternative tail designs, if added later).

What must hold

  • Support consistency: tail piece must respect the same support as the bulk.
  • Continuity at splice: densities and CDFs should match at the splice point.
  • Numerical stability: log-density computations must be stable for extreme values.

Where to implement

  • Base tail utilities usually live in R/0-base-kernels.R.
  • Legality checks live in R/00-global-contracts.R.
  • Kernel-specific splice wrappers live in each R/*-mixgpd.R.

What to test

  • continuity at splice for multiple parameter draws
  • predictive quantiles for extreme \(\\tau\) behave sensibly

Prereqs

  • Required packages and data for this page are listed in the setup chunks above.

Outputs

  • This page renders model fits, diagnostics, and summary artifacts generated by package APIs.

Interpretation

  • Canonical concept page: Spec And Contracts
  • Treat this page as an application/example view and use the canonical page for core definitions.

Next

  • Continue to the linked canonical concept page, then return for implementation-specific details.
(c) CausalMixGPD - Bayesian semiparametric modeling for heavy-tailed data
- - Cite - API - GitHub