Post-hoc estimation

Post-hoc estimation for linear mixed models fitted by REML, operating on tensors: best linear unbiased estimation (BLUE) of the fixed effects, best linear unbiased prediction (BLUP) of the random effects, and marginal and conditional fitted values and residuals.

torch_openreml.blue(y, x, v)	Compute the best linear unbiased estimator (BLUE) of the fixed effects.
torch_openreml.blup(y, x, z, g, v)	Compute the best linear unbiased predictor (BLUP) of the random effects.
torch_openreml.marginal_predict(y, x, v)	Compute marginal fitted values from fixed effects only.
torch_openreml.marginal_residual(y, x, v)	Compute marginal residuals from fixed effects only.
torch_openreml.predict(y, x, z, g, v)	Compute conditional fitted values including random effects.
torch_openreml.residual(y, x, z, g, v)	Compute conditional residuals including random effects.
torch_openreml.loglik(y, x, v)	Evaluate the REML log-likelihood.