setup.parameters: Setup parameter structure specific to model (internal use)

In RMark: R Code for Mark Analysis

Setup parameter structure specific to model (internal use)

Description

Defines list of parameters used in the specified type of model (model) and adds default values for each parameter to the list of user specified values (eg formula, link etc) defined in the call to make.mark.model

Usage

setup.parameters(
  model,
  parameters = list(),
  nocc = NULL,
  check = FALSE,
  number.of.groups = 1
)

Arguments

model	type of model ("CJS", "Burnham" etc)
parameters	list of model parameter specifications
nocc	number of occasions (value only specified if needed)
check	if TRUE only the vector of parameter names is returned par.list
number.of.groups	number of groups defined for data

Details

The primary difference in setting up models for MARK is the number and types of parameters that are included in the model. This function sets up the list of parameters used in the model and defines values for each parameter that affect how the PIM and design data are structured in the input file for program MARK. Some of the values of the parameter list are user specified such as formula, link,fixed so this function only adds to the list of values that are not specified by the user. That is, it takes the input argument parameters and adds list elements for parameters not specified by the user and adds default values for each type of parameter and then returns the modified list. The structure of the argument parameters and the return value of this function are the same as the structure of the argument parameters in make.mark.model and argument model.parameters in mark. They are lists with an element for each type of parameter in the model and the name of each list element is the parameter name (e.g., "p", "Phi","S", etc). For each parameter there are a list of values (e.g., formula, link, num etc as defined below). Thus parameters is a list of lists.

Value

The return value depends on the argument check. If it is TRUE then the return value is a vector of the names of the parameters used in the specified type of model. For example, if model="CJS" then the return value is c("Phi","p"). This is used by the function valid.parameters to make sure that parameter specifications are valid for the model (i.e., specifying recovery rate r for "CJS" would give an error). If the function is called with the default of check=FALSE, the function returns a list of parameter specifications which is a modification of the argument parameters which adds parameters not specified and default values for all types of parameters that were not specified. The list length and names of the list elements depends on the type of model. Each element of the list is itself a list with varying numbers of elements which depend on the type of parameter although some elements are the same for all parameters. Below the return value list is shown generically with parameters named p1,...,pk.

p1	List of specifications for parameter 1
p2	List of specifications for parameter 2
.
.
.
pk	List of specifications for parameter k

The elements for each parameter list all include:

begin	0 or 1; beginning time for the first
	parameter relative to first occasion
num	0 or -1; number of parameters relative to
	number of occassions
type	type of PIM structure; either "Triang" or "Square"
formula	formula for parameter model (e.g., ~time)
link	link function for parameter (e.g., "logit")

and may include:

share	only valid for p in closed capture models;
	if TRUE p and c models shared
mix	only valid for closed capture heterogeneity
	models; if TRUE mixtures are used
rows	only valid for closed capture heterogeneity models
fixed	fixed values specified by user and
	not used modified in this function

Author(s)

Jeff Laake

See Also

setup.model,valid.parameters

RMark documentation built on Aug. 14, 2022, 1:05 a.m.