Fisher's C statistic for a fitted distributional SEM

Combines the independence-claim p-values from dsep() into Fisher's C, C = -2 * sum(log(p)), which is chi-squared with 2k degrees of freedom under the hypothesis that all missing arrows are absent. A small p-value indicates the DAG omits a needed path.

Usage

fisher_c(object, ...)

# S3 method for class 'drm_sem'
fisher_c(object, ...)

# S3 method for class 'drm_dsep'
fisher_c(object, ...)

Arguments

object: A drm_sem object or the result of dsep().
...: Unused.

Value

A one-row data frame with fisher_c, df, n_claims, p.value.

Details

This is the Fisher-combined goodness-of-fit test introduced by Shipley (2000) for path models on directed acyclic graphs and extended to generalized multilevel models by Shipley (2009); piecewiseSEM (Lefcheck 2016) is the established R implementation. The construction itself is unchanged here; what differs is that the p-values being combined are the any-component likelihood-ratio claims of dsep() rather than mean-only claims.

References

Shipley B (2000). “A New Inferential Test for Path Models Based on Directed Acyclic Graphs.” Structural Equation Modeling, 7(2), 206–218. doi:10.1207/S15328007SEM0702_4 .

Shipley B (2009). “Confirmatory Path Analysis in a Generalized Multilevel Context.” Ecology, 90(2), 363–368. doi:10.1890/08-1034.1 .

Lefcheck JS (2016). “piecewiseSEM: Piecewise Structural Equation Modelling in R for Ecology, Evolution, and Systematics.” Methods in Ecology and Evolution, 7(5), 573–579. doi:10.1111/2041-210X.12512 .

Examples

if (FALSE) { # \dontrun{
sem <- drm_sem(
  size = drm_node(drmTMB::bf(size ~ temp + habitat, sigma ~ temp),
                  family = stats::gaussian()),
  abundance = drm_node(drmTMB::bf(abundance ~ size + temp, zi ~ habitat),
                       family = drmTMB::nbinom2()),
  data = dat)
fisher_c(sem)
} # }