This is an attempt to use stan's AD features to calculate a hessian for the RSSp likelihood
1 | evd_dnorm_hess_stan(par, D, quh)
|
par |
a (up to) length 2 numeric vector. 'par[1]' corresponds to the sigma_u^2 parameter, and 'par[2]' corresponds to the confounding parameter. If the model does not include confounding, 'par' can be a length one vector. |
quh |
The precomputed matrix vector product 'crossprod(Q,u_hat)' (passed as a length 'p' vector) |
D. |
The eigenvalues of the LD matrix, passed as a length 'p' vector |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.