Tidy method for fitted ame_als / lame_als objects

Returns a data frame with one row per regression coefficient, compatible with the broom idiom, so that ALS fits compose with modelsummary / kableExtra pipelines next to MCMC fits. Standard errors come from the sandwich covariance (vcov.ame_als) by default, or from the bootstrap object attached to x$bootstrap when present (preferred, fully propagated). statistic is estimate / std.error; p.value is the Normal-approximation two-sided tail \(2(1 - \Phi(|z|))\) from the bootstrap or sandwich standard error. It is a Wald-style summary for the point estimator, not a posterior probability.

Usage

# S3 method for class 'ame_als'
tidy(x, conf.int = TRUE, conf.level = 0.95, ...)

# S3 method for class 'lame_als'
tidy(x, conf.int = TRUE, conf.level = 0.95, ...)

Arguments

x

A fitted ame_als / lame_als object.

conf.int

Logical; include conf.low / conf.high columns. Default TRUE.

conf.level

Confidence level. Default 0.95.

...

Passed to vcov.ame_als (e.g. cluster = "dyad").

Value

Data frame with columns term, estimate, std.error, statistic, p.value, conf.low, conf.high, plus a se_source column recording "bootstrap" or "sandwich".

Details

Only the intercept and dyadic-covariate coefficients are returned, matching coef(fit) on the sandwich-covered subset. Additive (a, b), multiplicative (U, V), and node-covariate parameters are not included; use ame_als_bootstrap and inspect the bootstrap object directly if you need them.

Examples

# \donttest{
data(YX_bin_list)
Y1 <- 1 * (YX_bin_list$Y[[1]] > 0); diag(Y1) <- NA
fit <- ame_als(Y = Y1, Xdyad = YX_bin_list$X[[1]],
               family = "binary", R = 1, verbose = FALSE)
tidy(fit)
#> Warning: ! `vcov.ame_als()` for "binary" returns the conditional sandwich on the
#>   surrogate working likelihood -- anti-conservative.
#> ℹ Refit with `ame_als(..., bootstrap = 200)` for fully propagated uncertainty.
#> ℹ Or call `confint(fit)` after attaching a bootstrap with
#>   `ame_als_bootstrap()`.
#> # A tibble: 4 × 8
#>   term       estimate std.error statistic   p.value conf.low conf.high se_source
#>   <chr>         <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl> <chr>    
#> 1 intercept     0.200    0.0357      5.61   1.99e-8    0.130     0.270 sandwich 
#> 2 dyad1_dyad    0.758    0.0155     49.0    0          0.727     0.788 sandwich 
#> 3 dyad2_dyad    0.896    0.0163     55.1    0          0.864     0.928 sandwich 
#> 4 dyad3_dyad    1.11     0.0204     54.3    0          1.07      1.15  sandwich 
# }