fHMM (version 1.2.2)

parameter_transformations: Parameter transformations

Description

These helper functions transform model parameters between

• constrained spaces (suffix *Con)

• and unconstrained spaces (suffix *Uncon).

The former is useful for interpretation, the latter for unconstrained optimization.

Usage

par2parUncon(par, controls, use_parameter_labels = TRUE)
parUncon2parCon(parUncon, controls, use_parameter_labels = TRUE)
parCon2par(parCon, controls, use_parameter_labels = TRUE)
par2parCon(par, controls, use_parameter_labels = TRUE)
parCon2parUncon(parCon, controls, use_parameter_labels = TRUE)
parUncon2par(parUncon, controls, use_parameter_labels = TRUE)
muCon2muUncon(muCon, link, prefix = "muUncon_", use_parameter_labels = TRUE)
muUncon2muCon(muUncon, link, prefix = "muCon_", use_parameter_labels = TRUE)
sigmaCon2sigmaUncon(
  sigmaCon,
  prefix = "sigmaUncon_",
  use_parameter_labels = TRUE
)
sigmaUncon2sigmaCon(
  sigmaUncon,
  prefix = "sigmaCon_",
  use_parameter_labels = TRUE
)
dfCon2dfUncon(dfCon, prefix = "dfUncon_", use_parameter_labels = TRUE)
dfUncon2dfCon(dfUncon, prefix = "dfCon_", use_parameter_labels = TRUE)
Gamma2gammasCon(
  Gamma,
  shift = 0.001,
  prefix = "gammasCon_",
  use_parameter_labels = TRUE
)
Gamma2gammasUncon(Gamma, prefix = "gammasUncon_", use_parameter_labels = TRUE)
gammasCon2Gamma(gammasCon, dim, prefix = "state_", use_parameter_labels = TRUE)
gammasCon2gammasUncon(
  gammasCon,
  dim,
  prefix = "gammasUncon_",
  use_parameter_labels = TRUE
)
gammasUncon2Gamma(
  gammasUncon,
  dim,
  prefix = "state_",
  use_parameter_labels = TRUE
)
gammasUncon2gammasCon(
  gammasUncon,
  dim,
  prefix = "gammasCon_",
  use_parameter_labels = TRUE
)

Value

For par2parUncon: a vector of unconstrained model parameters.

For parUncon2parCon: a vector of constrained model parameters.

For parCon2par: an object of class fHMM_parameters.

For par2parCon: a vector of constrained model parameters.

For parCon2parUncon: a vector of unconstrained model parameters.

For parUncon2par: an object of class fHMM_parameters.

For muCon2muUncon: a vector of unconstrained expected values.

For muUncon2muCon: a vector of constrained expected values.

For sigmaCon2sigmaUncon: a vector of unconstrained standard deviations.

For sigmaUncon2sigmaCon: a vector of constrained standard deviations.

For dfCon2dfUncon: a vector of unconstrained degrees of freedom.

For dfUncon2dfCon: a vector of constrained degrees of freedom.

For Gamma2gammasCon: a vector of constrained non-diagonal matrix elements (column-wise).

For Gamma2gammasUncon: a vector of unconstrained non-diagonal matrix elements (column-wise).

For gammasCon2Gamma: a transition probability matrix.

For gammasCon2gammasUncon: a vector of unconstrained non-diagonal elements of the transition probability matrix.

For gammasUncon2Gamma: a transition probability matrix.

For gammasUncon2gammasCon: a vector of constrained non-diagonal elements of a transition probability matrix.

Arguments

par

An object of class fHMM_parameters, which is a list of model parameters.

controls

Either a list or an object of class fHMM_controls.

The list can contain the following elements, which are described in more detail below:

• hierarchy, defines an hierarchical HMM,

• states, defines the number of states,

• sdds, defines the state-dependent distributions,

• horizon, defines the time horizon,

• period, defines a flexible, periodic fine-scale time horizon,

• data, a list of controls that define the data,

• fit, a list of controls that define the model fitting

Either none, all, or selected elements can be specified.

Unspecified parameters are set to their default values, see below.

Specifications in controls override individual specifications.

use_parameter_labels

Either TRUE to label the parameters or FALSE, if not (this can save computation time).

parUncon

An object of class parUncon, which is a numeric vector with identified and unconstrained model parameters in the following order:

1. non-diagonal transition probabilities gammasUncon

2. expectations muUncon

3. standard deviations sigmaUncon (if any)

4. degrees of freedom dfUncon (if any)

5. fine-scale parameters for each coarse-scale state, in the same order (if any)

parCon

An object of class parCon, which is a numeric vector with identified (and constrained) model parameters in the following order:

1. non-diagonal transition probabilities gammasCon

2. expectations muCon

3. standard deviations sigmaCon (if any)

4. degrees of freedom dfCon (if any)

5. fine-scale parameters for each coarse-scale state, in the same order (if any)

muCon, muUncon

A vector of (un-) constrained expected values.

link

Either TRUE or FALSE, determining whether to apply the link function.

prefix

A character prefix for labeling the parameters.

sigmaCon, sigmaUncon

A vector of (un-) constrained standard deviations.

dfCon, dfUncon

A vector of (un-) constrained degrees of freedom.

shift

A small, positive numeric for shifting boundary probabilities. By default, shift = 1e-3.

gammasCon, gammasUncon

A vector of (un-) constrained non-diagonal transition probabilities.

dim

An integer, the dimension of the transition probability matrix.