The conditional model is handled with joint fixed-effect covariance. Zero-inflation or hurdle occurrence terms are returned as a separate component. Random-effect modes are included as a compact aggregate term. A single random-intercept grouping variable retains its actual stratum labels for CDI displays; more complex random structures remain aggregates. Random-effect uncertainty uses the joint conditional latent covariance. Lognormal models require a log link for their arithmetic mean. Dispersion may vary, but its effects are not decomposed: the diagnostics describe mean-model terms. Unlike brms, glmmTMB does not parameterise log-location. Offsets have the same single-component restrictions as the GLM adapter, and nominal summaries are observed-response summaries, not automatically exposure-adjusted CPUE.
Arguments
- model
A fitted object from [glmmTMB::glmmTMB()].
- focus
Name of the focus variable, usually year.
- data
Optional model data. The model frame is used by default.
- weights
Optional numeric observation weights or the name of a weight column in `data`.
- reference_data
Optional prediction grid defining the common standardisation distribution. By default the observed data are used.
- reference_weights
Optional numeric weights, or a column name, for `reference_data`.
- uncertainty
One of `"auto"`, `"none"`, `"analytic"`, or `"simulation"`.
- retain
One of `"summary"`, `"derived_draws"`, or `"disk"`.
- probs
Lower and upper interval probabilities.
- ndraws
Number of joint coefficient draws for simulation uncertainty.
- seed
Optional simulation seed.
- draws_path
Output path used when `retain = "disk"`.
- keep_model
Retain the fitted model inside the diagnostic object.
- ...
Reserved for future backend options.