View source: R/transform-parameters.R
standardized_to_direct | R Documentation |
Transform the parameters between the parameterizations that are used in the package.
standardized_to_direct(par, n_scales, jacobian = FALSE) direct_to_standardized(par, n_scales)
par |
concatenated vector with the fixed effect slopes and the scale parameters that should be transformed. |
n_scales |
integer with the number of scale parameters. |
jacobian |
logical indicating if the Jacobian matrix of transformation should be computed. |
standardized_to_direct
:
returns the parameters using the direct parameterizations. See
vignette("pedmod", package = "pedmod")
for the definition. There is
an attribute called 'variance proportions' with the proportion of variance
of each effect assuming that all the scale matrices are correlation matrices.
There is an attribute called jacobian with the Jacobian matrix if
jacobian
is TRUE
.
direct_to_standardized
:
the parameters using the standardized parameterizations. See
vignette("pedmod", package = "pedmod")
for the definition.
# transform backwards and forwards set.seed(1) smp <- runif(10, -1, 1) res <- standardized_to_direct(smp, 2L, jacobian = TRUE) back_val <- direct_to_standardized(res, 2L) all.equal(smp, back_val, check.attributes = FALSE) res
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.