experimental_design: Eperimental design class
In nikitagusarov/dcesimulatr: Discrete Choice Experiment Simulator
experimental_design R Documentation
Eperimental design class
Description
The 'experimental_design' R6 class regroups different alternatives.
It contains all the essential information of the desired experimental design.
It serves as a wrapper for simultaneous interactions with alternative profiiles.
The object is used for choice sets generation procedures.
Public fields
alternativesA list of alternatives to use for experimental design construction.
designAn experimental design specification.
This field assumes that a savvy user may desire to extend the number of available experimental designs.
In the default configuration available designs are: "random", "factorial" and "mixed".
nA number of choice sets per individual for "random" design configuration.
resampleLogical.
Indicates whether the design part generated from factors should be resampled (shuffled)
identicalLogical.
Declares whether the choice sets should be identical across individuals or not.
replaceLogical.
States whether the replacement should be performed when sampling from full factorial design.
Default to FALSE.
Methods
Public methods
-
-
-
-
-
-
Method new()
Create new experimental design object.
It's possible to create the whole object with one command.
Usage
experimental_design$new(
alternatives = list(NULL),
design = "random",
n = NULL,
resample = NULL,
replace = FALSE,
identical = FALSE
)
Arguments
alternativesA list of alternatives to use for experimental design construction.
designAn experimental design specification.
This field assumes that a savvy user may desire to extend the number of available experimental designs.
In the default configuration available designs are: "random", "factorial" and "mixed".
The preset value is "random".
nA number of choice sets per individual for "random" design configuration.
NULL by deafult.
resampleDeclares whether the dataset should be resampled (shuffled) in case of factorial design element presence.
replaceLogical.
If resampling strategy is used then this parameter indicates the resampling strategy, see sample() for more details.
identicalLogical.
Declares whether the choice sets should be identical across individuals or not.
The default value if FALSE.
Returns
An 'experimental_design' object.
Method add_alternative()
Add new alternative to the list of available alternatives.
Usage
experimental_design$add_alternative(alternative, alternative_name = NULL)
Arguments
alternativeAn 'alternative' object to be included into experimental design.
alternative_nameAn added alternative name, not required.
Is NULL by default.
Method set_design()
Set a new 'design' configuration.
Usage
experimental_design$set_design(design = "random")
Arguments
designSpecification of the desired design.
The default designs are "random" (default), "factorial" and "mixed".
Method get_attributes()
Get a vector of available attributes' names across all alternatives.
Usage
experimental_design$get_attributes(index = NULL)
Arguments
indexA list of index of attributes to be querried.
Returns
Character list of the attributes by alternative.
Method get_design()
Get specified design.
Usage
experimental_design$get_design()
Returns
Character value of the experimental design.
Method clone()
The objects of this class are cloneable with this method.
Usage
experimental_design$clone(deep = FALSE)
Arguments
deepWhether to make a deep clone.
Examples
# Create alternatives
alt1 <- alternative$new()
alt1$add_attributes(Quality = runif(min = 0, max = 1), Price = rnorm(mean = 5))
alt2 <- alternative$new()
alt2$add_attributes(Size = runif(min = 0, max = 1), Price = rnorm(mean = 6))
# Regroup alternatives into design
edesign <- experimental_design$new(alternatives = list(alt1, alt2))
nikitagusarov/dcesimulatr documentation built on Jan. 7, 2023, 4:27 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
| experimental_design | R Documentation |
Eperimental design class
Description
The 'experimental_design' R6 class regroups different alternatives. It contains all the essential information of the desired experimental design. It serves as a wrapper for simultaneous interactions with alternative profiiles. The object is used for choice sets generation procedures.
Public fields
alternativesA list of alternatives to use for experimental design construction.
designAn experimental design specification. This field assumes that a savvy user may desire to extend the number of available experimental designs. In the default configuration available designs are: "random", "factorial" and "mixed".
nA number of choice sets per individual for "random" design configuration.
resampleLogical. Indicates whether the design part generated from factors should be resampled (shuffled)
identicalLogical. Declares whether the choice sets should be identical across individuals or not.
replaceLogical. States whether the replacement should be performed when sampling from full factorial design. Default to FALSE.
Methods
Public methods
Method new()
Create new experimental design object. It's possible to create the whole object with one command.
Usage
experimental_design$new( alternatives = list(NULL), design = "random", n = NULL, resample = NULL, replace = FALSE, identical = FALSE )
Arguments
alternativesA list of alternatives to use for experimental design construction.
designAn experimental design specification. This field assumes that a savvy user may desire to extend the number of available experimental designs. In the default configuration available designs are: "random", "factorial" and "mixed". The preset value is "random".
nA number of choice sets per individual for "random" design configuration. NULL by deafult.
resampleDeclares whether the dataset should be resampled (shuffled) in case of factorial design element presence.
replaceLogical. If resampling strategy is used then this parameter indicates the resampling strategy, see sample() for more details.
identicalLogical. Declares whether the choice sets should be identical across individuals or not. The default value if FALSE.
Returns
An 'experimental_design' object.
Method add_alternative()
Add new alternative to the list of available alternatives.
Usage
experimental_design$add_alternative(alternative, alternative_name = NULL)
Arguments
alternativeAn 'alternative' object to be included into experimental design.
alternative_nameAn added alternative name, not required. Is NULL by default.
Method set_design()
Set a new 'design' configuration.
Usage
experimental_design$set_design(design = "random")
Arguments
designSpecification of the desired design. The default designs are "random" (default), "factorial" and "mixed".
Method get_attributes()
Get a vector of available attributes' names across all alternatives.
Usage
experimental_design$get_attributes(index = NULL)
Arguments
indexA list of index of attributes to be querried.
Returns
Character list of the attributes by alternative.
Method get_design()
Get specified design.
Usage
experimental_design$get_design()
Returns
Character value of the experimental design.
Method clone()
The objects of this class are cloneable with this method.
Usage
experimental_design$clone(deep = FALSE)
Arguments
deepWhether to make a deep clone.
Examples
# Create alternatives alt1 <- alternative$new() alt1$add_attributes(Quality = runif(min = 0, max = 1), Price = rnorm(mean = 5)) alt2 <- alternative$new() alt2$add_attributes(Size = runif(min = 0, max = 1), Price = rnorm(mean = 6)) # Regroup alternatives into design edesign <- experimental_design$new(alternatives = list(alt1, alt2))
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.