Higher-level random-effect correlations (corpairs)

Reports the higher-level random-effect correlation edge(s) — the between-unit coupling u_level,y1 <-> u_level,y2 among random effects sharing a grouping level (class 3 in docs/design/07-bivariate-covariance-edges.md). For a drm_pair() these are the declared corpair edges (auto-detected from shared grouping factors); for a drm_sem() they are the declared higher-level covariance edges. As with rho12(), the estimate is read back from a live bivariate drmTMB fit and is NA in the pure-R lane. Reported separately from the residual rho12 because the two answer different biological questions (between-unit average coupling vs within-observation residual coupling).

Usage

corpairs(object, ...)

# S3 method for class 'drm_pair'
corpairs(object, ...)

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

Arguments

object

A drm_pair or drm_sem.

...

Unused.

Value

A drm_corpairs data frame: level, y1, y2, estimate.

References

Bollen KA (1989). Structural Equations with Latent Variables. Wiley, New York.

Brooks ME, Kristensen K, van Benthem KJ, Magnusson A, Berg CW, Nielsen A, Skaug HJ, Maechler M, Bolker BM (2017). “glmmTMB Balances Speed and Flexibility Among Packages for Zero-Inflated Generalized Linear Mixed Models.” The R Journal, 9(2), 378–400. doi:10.32614/RJ-2017-066 .

See also

rho12(), covary(), covariances(), drm_pair().

Examples

corpairs(drm_pair(activity ~ x + (1 | id), boldness ~ x + (1 | id)))
#> <higher-level correlation (corpair): 1 edge>
#>  level       y1       y2 estimate
#>     id activity boldness       NA
#> estimate NA: rho12/corpair are declared; a joint bivariate drmTMB fit is needed
#> to read fitted values back (OQ-14, 0.4 engine).