Expand description
Shared analytic kernel for latent-variable families with lognormal structure.
The kernel object K_{k,m}(μ, σ) := E[exp(k·U − m·exp(U))], where
U ~ N(μ, σ²), is the only special function required by all latent families.
It satisfies exact μ-recurrences (see kernel_ratio_jet) and the
corresponding heat-equation σ-identities, so fixed-σ latent families reduce
to evaluating kernel bundles at shifted arguments.
Row likelihoods for binary and survival models are small signed sums of
kernel terms; LogKernelSumJet evaluates their log-derivatives from
log-space kernel bundles and treats non-positive signed sums as invalid rows.
Structs§
- Kernel
SumTerm - A single signed term in a kernel sum: coefficient × K_{k,m}.
- LatentC
LogLog Jet5 - Fifth-order latent-cloglog inverse-link jet.
- Latent
Survival Row - Row-level sufficient statistics for one latent survival observation.
- Latent
Survival RowJet - Row-level log-likelihood and μ-derivatives for the latent survival model.
- LogKernel
SumJet - Derivatives of
log(Σ_j a_j · K_{k_j, m_j}(μ, σ))with respect to μ. - LogLognormal
Kernel Bundle - Kernel bundle storing
log K_{k,m}values instead ofK_{k,m}. - Probit
Frailty Scale Jet - Probit frailty scaling factor with t-derivatives (t = log σ).
Enums§
- Frailty
Spec - Frailty modifier specification at the family level.
- Hazard
Loading - How the hazard multiplier frailty loads onto the hazard components.
- Latent
Survival Event Type - Event type for compiled survival sufficient statistics.
- Lognormal
Kernel Error - Errors produced by the lognormal-kernel frailty/marginal-slope validators.
Functions§
- kernel_
ratio_ jet - Computes the value-space derivative ratios
∂ⁿ_μ K_{k,m} / K_{k,m}from a log-space bundle. - latent_
cloglog_ inverse_ link_ jet - latent_
cloglog_ jet5 - log_
kernel_ bundle - Builds a log-space kernel bundle for
k = 0, 1, …, max_kat fixed(m, μ, σ). - log_
kernel_ term