Compute case-wise and cluster-wise derivative for mixed effects models with respect to fixed effects parameter, random effect (co)variances, and residual variance. This material is partially based on work supported by the National Science Foundation under Grant Number 1460719.
merDeriv is a free, open source R package for computing derivatives of mixed models estimated via lme4. Allows users to compute scores (casewise first derivatives of likelihood function) and variance-covariance matrix of all estimated parameters, including random effect (co)variances.
For further information, see:
Wang, T. & Merkle, E. C. (2018). Derivative Computations and Robust Standard Errors for Linear Mixed Effects Models in lme4.. Journal of Statistical Software, 16(9), 1–16.