Start Here

Website workflow note. This page reflects the current exported API and recommended wrapper-first usage. Last updated: 2026-02-19.

For the full package narrative, see the main package vignettes (basic, unconditional, conditional, and causal).

Workflow roadmap

Quick start

This vignette gives a minimal, fully working workflow for an unconditional model and a conditional model. Everything uses short MCMC runs so the vignette renders quickly.

---

Unconditional Model (CRP, bulk-only)

data("nc_pos200_k3")
y <- nc_pos200_k3$y

bundle_uncond <- bundle(
  y = y,
  backend = "crp",
  kernel = "gamma",
  GPD = FALSE,
  components = 5,
  mcmc = mcmc
)

fit_uncond <- load_or_fit("quickstart-start-here-fit_uncond", quiet_mcmc(dpmix(bundle_uncond, mcmc = list(show_progress = FALSE))))
summary(fit_uncond)

pred_q <- predict(fit_uncond, type = "quantile", p = c(0.5, 0.9), interval = "credible")
head(pred_q$fit)
plot(pred_q)

---

Conditional Model (SB, bulk-only)

data("nc_posX100_p3_k2")
yc <- nc_posX100_p3_k2$y
X <- as.matrix(nc_posX100_p3_k2$X)

bundle_cond <- bundle(
  y = yc,
  X = X,
  backend = "sb",
  kernel = "lognormal",
  GPD = FALSE,
  components = 5,
  mcmc = mcmc
)

fit_cond <- load_or_fit("quickstart-start-here-fit_cond", quiet_mcmc(dpmix(bundle_cond, mcmc = list(show_progress = FALSE))))
summary(fit_cond)

x_new <- X[1:20, , drop = FALSE]
pred_mean <- predict(fit_cond, newdata =x_new, type = "mean", interval = "credible", nsim_mean = 200)
head(pred_mean$fit)
plot(pred_mean)

---

Useful S3 Methods

params(fit_uncond)
plot(fit_uncond, family = c("traceplot", "running"))

---

Next Steps

• start/roadmap: workflow map and routing
• examples/ex01: full three-phase workflow (spec -> bundle -> MCMC)
• examples/ex01-ex08: unconditional/conditional models with and without GPD
• examples/ex09-ex14: causal workflows

---

Workflow Navigation

• Previous: none (start of workflow series)
• Next: basic-model-compile-run
• Workflow index: Roadmap
• Practical entry: Examples

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: Start Here
• 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.