Tidy parameter estimates table

Description

Extracts all estimated parameters (theta, omega diagonal, sigma) into a single tidy data frame, adding percent relative standard error (\95-transformed estimates and CIs.

Usage

ferx_estimates(fit)

Arguments

fit: A ferx_fit object returned by [ferx_fit](ferx_fit.qmd).

Details

Omega is reported on the variance scale (matching the .ferx model file convention). For block omega, only the diagonal variances are included.

[ferx_cor_matrix](ferx_cor_matrix.qmd) for parameter correlations. Other diagnostics: [check_diagnostics](check_diagnostics.qmd)(), [ferx_cor_matrix](ferx_cor_matrix.qmd)(), [ferx_cov_screen](ferx_cov_screen.qmd)(), [ferx_eta_cov](ferx_eta_cov.qmd)(), [ferx_plot_trace](ferx_plot_trace.qmd)(), [ferx_runlog_iters](ferx_runlog_iters.qmd)(), [ferx_trace](ferx_trace.qmd)(), [ferx_warnings](ferx_warnings.qmd)(), [summary.ferx_fit](summary.ferx_fit.qmd)()

Concept

diagnostics

Value

A data frame with columns param, transform, estimate, se, rse_pct, lower_95, upper_95, estimate_natural, lower_95_natural, upper_95_natural, init_as_sd. SE-derived and natural-scale columns are NA when not applicable or when the covariance step was not run. init_as_sd is TRUE for omega, sigma, or kappa rows where the user annotated the initial value with (sd) in the model file; always FALSE for theta rows.

Examples

ex  <- ferx_example("warfarin")
fit <- ferx_fit(ex$model, ex$data, method = "gn", covariance = FALSE)
ferx_estimates(fit)