vcov.riley: Calculate Variance-Covariance Matrix for a Fitted Riley Model...

In metamisc: Meta-Analysis of Diagnosis and Prognosis Research Studies

Calculate Variance-Covariance Matrix for a Fitted Riley Model Object

Description

Returns the variance-covariance matrix of the main parameters of a fitted model object.

Usage

## S3 method for class 'riley'
vcov(object, ...)

Arguments

object	a riley object.
...	arguments to be passed on to other functions

Details

The variance-covariance matrix is obtained from the inverse Hessian as provided by optim.

Value

A matrix of the estimated covariances between the parameter estimates in the Riley model: logit of sensitivity (mu1), logit of false positive rate (mu2), additional variation of mu1 beyond sampling error (psi1), additional variation of mu2 beyond sampling error (psi2) and a transformation of the correlation between psi1 and psi2 (rhoT). The original correlation is given as inv.logit(rhoT)*2-1.

Note

A warning message is casted when the Hessian matrix contains negative eigenvalues. This implies that the identified minimum for the (restricted) negative log-likelihood is a saddle point, and that the solution is therefore not optimal.

Author(s)

Thomas Debray <[e-mail]>

References

Riley, RD., Thompson, JR., & Abrams, KR. (2008). “An alternative model for bivariate random-effects meta-analysis when the within-study correlations are unknown.” Biostatistics, 9, 172–186.

See Also

riley

metamisc documentation built on Sept. 25, 2022, 5:05 p.m.