| Type: | Package |
| Title: | Mock Data Generation |
| Version: | 1.0.1 |
| Date: | 2024-08-21 |
| Maintainer: | Georgios Koliopanos <george.koliopanos@cardio-care.ch> |
| Description: | Generation of synthetic data from a real dataset using the combination of rank normal inverse transformation with the calculation of correlation matrix <doi:10.1055/a-2048-7692>. Completely artificial data may be generated through the use of Generalized Lambda Distribution and Generalized Poisson Distribution <doi:10.1201/9781420038040>. Quantitative, binary, ordinal categorical, and survival data may be simulated. Functionalities are offered to generate synthetic data sets according to user's needs. |
| Encoding: | UTF-8 |
| RoxygenNote: | 7.3.2 |
| Suggests: | knitr, rmarkdown |
| VignetteBuilder: | knitr |
| License: | GPL-3 |
| Depends: | R (≥ 4.1) |
| Imports: | ggplot2 (≥ 3.4.0), patchwork (≥ 1.1.2), wesanderson (≥0.3.6.9000), Matrix (≥ 1.6.1.1), ggcorrplot (≥ 0.1.4.1),gridExtra (≥ 2.3), psych (≥ 2.2.9), GLDEX (≥ 2.0.0.9.2),MASS (≥ 7.3), gp (≥ 1.0), stats, utils, survival |
| NeedsCompilation: | no |
| Packaged: | 2024-09-09 11:33:55 UTC; geokolcc |
| Author: | Andreas Ziegler [aut], Francisco Miguel Echevarria [aut], Georgios Koliopanos [cre] |
| Repository: | CRAN |
| Date/Publication: | 2024-09-11 16:20:02 UTC |
Cleveland Dataset ('Cleveland')
Description
Rows: samples (303) x Columns: Variables (11)
Usage
data("Cleveland")Format
A data frame
Details
Cleveland Clinic Heart Disease Data set from the University of California in Irvine (UCI) machine learning data repository
Dua, Dheeru, and Casey Graff. 2017. "UCI Machine Learning Repository." University of California, Irvine,School of Information;Computer Sciences. http://archive.ics.uci.edu/ml
Selected 11 variables and impute missing valuesImputation method is described in the Supplementary file 1 of the modgo paper
References
Detrano, R. et al. (1989) “International application of a new probability algorithm for the diagnosis of coronary artery disease,”The American Journal of Cardiology,64(5), 304-310.
Examples
data("Cleveland", package="modgo")Inverse transform variables
Description
This function is used internally bymodgo. It transformsall variables to their original scale.
Usage
Inverse_transformation_variables( data, df_sim, variables, bin_variables, categ_variables, count_variables, n_samples, generalized_mode, generalized_mode_lmbds)Arguments
data | a data frame with original variables. |
df_sim | data frame with transformed variables. |
variables | variables a character vector indicating whichcolumns of |
bin_variables | a character vector listing the binary variables. |
categ_variables | a character vector listing the ordinal categoricalvariables. |
count_variables | a character vector listing the count as a subsub category of categorical variables. Count variables should be partof categorical variables vector. Count variables are treated differentlywhen using gldex to simulate them. |
n_samples | Number of rows of each simulated data set. Default isthe number of rows of |
generalized_mode | A logical value indicating if generalized lambda/poisson distributions or set up thresholds will be used togenerate the simulated values |
generalized_mode_lmbds | A matrix that contains lambdas values for each of the variables of the data set to be used for either Generalized LambdaDistribution Generalized Poisson Distribution or setting up thresholds |
Value
A data frame with all inverse transformed values.
Author(s)
Francisco M. Ojeda, George Koliopanos
Calculate Sigma with the help of polychoric and polyserial functions
Description
This function is used internally bymodgo. It conductsthe computation of the correlation matrix of the transformed variables, whichare assumed to follow a multivariate normal distribution.
Usage
Sigma_calculation(data, variables, bin_variables, categ_variables, ties_method)Arguments
data | a data frame with original variables. |
variables | variables a character vector indicating whichcolumns of |
bin_variables | a character vector listing the binary variables. |
categ_variables | a character vector listing the ordinal categoricalvariables. |
ties_method | Method on how to deal with equal valuesduring rank transformation. Acceptable input:"max","average","min". Thisparameter is passed by |
Value
A numeric matrix with correlation values.
Author(s)
Francisco M. Ojeda, George Koliopanos
Correlation of transformed variables
Description
This function is used internally bymodgo. It finishesthe computation of the correlation matrix of the transformed variables, whichare assumed to follow a multivariate normal distribution. It computes thecorrelations involving at least one categorical variable. For this purposethe biserial, tetrachoric, polyserial and polychoric correlations are used.
Usage
Sigma_transformation( data, data_z, Sigma, variables, bin_variables = c(), categ_variables = c())Arguments
data | a data frame with original variables. |
data_z | data frame with transformed variables. |
Sigma | A numeric square matrix. |
variables | variables a character vector indicating whichcolumns of |
bin_variables | a character vector listing the binary variables. |
categ_variables | a character vector listing the ordinal categoricalvariables. |
Value
A numeric matrix with correlation values.
Author(s)
Francisco M. Ojeda, George Koliopanos
Check Arguments
Description
Check that the arguments are followingthe corresponding conditions
Usage
checkArguments( data = NULL, ties_method = "max", variables = colnames(data), bin_variables = NULL, categ_variables = NULL, count_variables = NULL, n_samples = nrow(data), sigma = NULL, nrep = 100, noise_mu = FALSE, pertr_vec = NULL, change_cov = NULL, change_amount = 0, seed = 1, thresh_var = NULL, thresh_force = FALSE, var_prop = NULL, var_infl = NULL, infl_cov_stable = FALSE, tol = 1e-06, stop_sim = FALSE, new_mean_sd = NULL, multi_sugg_prop = NULL, generalized_mode = FALSE, generalized_mode_model = NULL, generalized_mode_lmbds = NULL)Arguments
data | a data frame containing the data whose characteristics are to bemimicked during the data simulation. |
ties_method | Method on how to deal with equal valuesduring rank transformation. Acceptable input:"max","average","min". Thisparameter is passed by |
variables | a vector of which variables you want to transform.Default:colnames(data) |
bin_variables | a character vector listing the binary variables. |
categ_variables | a character vector listing the ordinal categoricalvariables. |
count_variables | a character vector listing the count as a subsub category of categorical variables. Count variables should be partof categorical variables vector. Count variables are treated differentlywhen using gldex to simulate them. |
n_samples | Number of rows of each simulated data set. Default isthe number of rows of |
sigma | a covariance matrix of NxN (N= number of variables)provided by the user to bypass the covariance matrix calculations |
nrep | number of repetitions. |
noise_mu | Logical value if you want to apply noise tomultivariate mean. Default: FALSE |
pertr_vec | A named vector.Vector's names are the continuous variablesthat the user want to perturb. Variance of simulated data set mimic originaldata's variance. |
change_cov | change the covariance of a specific pair of variables. |
change_amount | the amount of change in the covarianceof a specific pair of variables. |
seed | A numeric value specifying the random seed. If |
thresh_var | A data frame that contains the thresholds(left and right)of specified variables(1st column: variable names, 2nd column: Left thresholds,3rd column: Right thresholds) |
thresh_force | A logical value indicating if you want to force thresholdin case the proportion of samples that can surpass the threshold are lessthan 10% |
var_prop | A named vector that provides a proportion ofvalue=1 for a specific binary variable(=name of the vector) that will bethe proportion of this value in the simulated data sets.[this may increaseexecution time drastically] |
var_infl | A named vector.Vector's names are the continuous variablesthat the user want to perturb and increase their variance |
infl_cov_stable | Logical value. If TRUE,perturbation is applied tooriginal data set and simulations values mimic the perturbed original dataset.Covariance matrix used for simulation = original data's correlations.If FALSE, perturbation is applied to the simulated data sets. |
tol | A numeric value that set uptolerance(relative to largest variance) for numerical lack ofpositive-definiteness in Sigma |
stop_sim | A logical value indicating if the analysis shouldstop before simulation and produce only the correlation matrix |
new_mean_sd | A matrix that contains two columns named"Mean" and "SD" that the user specifies desired Means and Standard Deviationsin the simulated data sets for specific continues variables. The variablesmust be declared as ROWNAMES in the matrix |
multi_sugg_prop | A named vector that provides a proportion ofvalue=1 for specific binary variables(=name of the vector) that will bethe close to the proportion of this value in the simulated data sets. |
generalized_mode | A logical value indicating if you want to use generalized distribution to simulate your data |
generalized_mode_model | A matrix that contains two columns named "Variable" and"Model". This matrix can be used only if a generalized_mode_model argument isprovided. It specifies what model should be used for each Variable.Model values should be "RMFMKL", "RPRS", "STAR" or a combination of them,e.g. "RMFMKL-RPRS" or "STAR-STAR", in case the use wants a bimodal simulation.The user can select Generalised Poisson model for poisson variables,but this model cannot be included in bimodal simulation. |
generalized_mode_lmbds | A matrix that contains lmbds values for each of thevariables of the data set to be used for either Generalized Lambda DistributionGeneralized Poisson Distribution or setting up thresholds |
Value
No value, called for checking arguments ofmodgo
Author(s)
Francisco M. Ojeda, George Koliopanos
Plots correlation matrix of original and simulated data
Description
Produces a graphical display of the correlation matrix of the original dataset, a single simulated dataset and also of the average of the correlation matrices across all simulations for an object returned bymodgo.
Usage
corr_plots( Modgo_obj, sim_dataset = 1, variables = colnames(Modgo_obj[["simulated_data"]][[1]]))Arguments
Modgo_obj | An object returned by |
sim_dataset | Number indicating the simulated dataset in |
variables | A character vector indicating the columns in the data to be used in plots. |
Value
A patchwork object created bywrap_plotsdepicting correlation matrices.
Author(s)
Francisco M. Ojeda, George Koliopanos
Examples
data("Cleveland",package="modgo")test_modgo <- modgo(data = Cleveland, bin_variables = c("CAD","HighFastBloodSugar","Sex","ExInducedAngina"), categ_variables =c("Chestpaintype"))corr_plots(test_modgo)Plots distribution of original and simulated data
Description
Produces a graphical display of the distribution of the variablesof the original dataset and a single simulated dataset for an object returned bymodgo.
Usage
distr_plots( Modgo_obj, variables = colnames(Modgo_obj[["original_data"]]), sim_dataset = 1, wespalette = "Cavalcanti1", text_size = 12)Arguments
Modgo_obj | An object returned by |
variables | A character vector indicating the columns in the data to be used in plots. |
sim_dataset | Number indicating the simulated dataset in |
wespalette | a name of the selected wesanderson color pallet |
text_size | a number for the size of the annotation text |
Details
For continuous variables box-and-whisker plots are displayed, while categorical variables bar charts are produced.
Value
A ggplot object depicting distribution of different variables.
Author(s)
Andreas Ziegler, Francisco M. Ojeda, George Koliopanos
Examples
data("Cleveland",package="modgo")test_modgo <- modgo(data = Cleveland, bin_variables = c("CAD","HighFastBloodSugar","Sex","ExInducedAngina"), categ_variables =c("Chestpaintype"))distr_plots(test_modgo)Inverse gldex transformation
Description
Inverse transforms z values of a vector to simulated values driven bythe original dataset using Generalized Lambda and Generalized Poisson percentile functions
Usage
general_transform_inv(x, data = NULL, n_samples, lmbds)Arguments
x | a vector of z values |
data | a data frame with original variables. |
n_samples | number of samples you need to produce. |
lmbds | a vector with generalized lambdas values |
Value
A numeric vector with inverse transformed values
Author(s)
Andreas Ziegler, Francisco M. Ojeda, George Koliopanos
Examples
data("Cleveland",package="modgo")test_rank <- rbi_normal_transform(Cleveland[,1])test_generalized_lmbds <- generalizedMatrix(Cleveland, bin_variables = c("Sex", "HighFastBloodSugar", "CAD"))test_inv_rank <- general_transform_inv(x = test_rank, data = Cleveland[,1], n_samples = 100, lmbds = test_generalized_lmbds[,1])Generalized Lambda and Poisson preparation
Description
Prepare the four moments matrix for GLD and GPD
Usage
generalizedMatrix( data, variables = colnames(data), bin_variables = NULL, generalized_mode_model = NULL, multi_sugg_prop = NULL)Arguments
data | a data frame with original variables. |
variables | a vector of which variables you want to transform.Default:colnames(data) |
bin_variables | a character vector listing the binary variables. |
generalized_mode_model | A matrix that contains two columns named "Variables" and"Model". This matrix can be used only if a generalized_mode_model argument isprovided. It specifies what model should be used for each Variable.Model values should be "RMFMKL", "RPRS", "STAR" or a combination of them,e.g. "RMFMKL-RPRS" or "STAR-STAR", in case the use wants a bimodal simulation.The user can select Generalized Poisson model for poisson variables,but this model cannot be included in bimodal simulation |
multi_sugg_prop | A named vector that provides a proportion ofvalue=1 for specific binary variables(=name of the vector) that will bethe close to the proportion of this value in the simulated data sets |
Value
A numeric matrix with the four moments for each distribution and a number that corresponds to a GLD model
Author(s)
Francisco M. Ojeda, George Koliopanos
Examples
data("Cleveland",package="modgo")Variables <- c("Age","STDepression")Model <- c("rprs", "star-rmfmkl")model_matrix <- cbind(Variables, Model)test_modgo <- generalizedMatrix(data = Cleveland, generalized_mode_model = model_matrix, bin_variables = c("CAD","HighFastBloodSugar","Sex","ExInducedAngina"))Generate new data set by using previous correlation matrix
Description
This function is used internally bymodgo. It conductsthe computation of the correlation matrix of the transformed variables, whichare assumed to follow a multivariate normal distribution.
Usage
generate_simulated_data( data, df_sim, variables, bin_variables, categ_variables, count_variables, n_samples, generalized_mode, generalized_mode_lmbds, multi_sugg_prop, pertr_vec, var_infl, infl_cov_stable)Arguments
data | a data frame with original variables. |
df_sim | a data frame with simulated values. |
variables | variables a character vector indicating whichcolumns of |
bin_variables | a character vector listing the binary variables. |
categ_variables | a character vector listing the ordinal categoricalvariables. |
count_variables | a character vector listing the count as a subsub category of categorical variables. Count variables should be partof categorical variables vector. Count variables are treated differentlywhen using gldex to simulate them. |
n_samples | Number of rows of each simulated data set. Default isthe number of rows of |
generalized_mode | A logical value indicating if generalized lambda/poissondistributions or set up thresholds will be used to generate the simulated values |
generalized_mode_lmbds | A matrix that contains lmbds values for each of thevariables of the data set to be used for either Generalized Lambda DistributionGeneralized Poisson Distribution or setting up thresholds |
multi_sugg_prop | A named vector that provides a proportion ofvalue=1 for specific binary variables(=name of the vector) that will bethe close to the proportion of this value in the simulated data sets. |
pertr_vec | A named vector.Vector's names are the continuous variablesthat the user want to perturb. Variance of simulated data set mimic originaldata's variance. |
var_infl | A named vector.Vector's names are the continuous variablesthat the user want to perturb and increase their variance |
infl_cov_stable | Logical value. If TRUE,perturbation is applied tooriginal data set and simulations values mimic the perturbed original dataset.Covariance matrix used for simulation = original data's correlations.If FALSE, perturbation is applied to the simulated data sets. |
Value
A data frame with simulated values
Author(s)
Francisco M. Ojeda, George Koliopanos
MOck Data GeneratiOn
Description
modgo Create mock dataset from a real one by usingranked based inverse normal transformation. Data with perturbedcharacteristics can be generated.
Usage
modgo( data, ties_method = "max", variables = colnames(data), bin_variables = NULL, categ_variables = NULL, count_variables = NULL, n_samples = nrow(data), sigma = NULL, nrep = 100, noise_mu = FALSE, pertr_vec = NULL, change_cov = NULL, change_amount = 0, seed = 1, thresh_var = NULL, thresh_force = FALSE, var_prop = NULL, var_infl = NULL, infl_cov_stable = FALSE, tol = 1e-06, stop_sim = FALSE, new_mean_sd = NULL, multi_sugg_prop = NULL, generalized_mode = FALSE, generalized_mode_model = NULL, generalized_mode_lmbds = NULL)Arguments
data | a data frame containing the data whose characteristics are to bemimicked during the data simulation. |
ties_method | Method on how to deal with equal valuesduring rank transformation. Acceptable input:"max","average","min". Thisparameter is passed by |
variables | a vector of which variables you want to transform.Default:colnames(data) |
bin_variables | a character vector listing the binary variables. |
categ_variables | a character vector listing the ordinal categoricalvariables. |
count_variables | a character vector listing the count as a subsub category of categorical variables. Count variables should be partof categorical variables vector. Count variables are treated differentlywhen using gldex to simulate them. |
n_samples | Number of rows of each simulated data set. Default isthe number of rows of |
sigma | a covariance matrix of NxN (N= number of variables)provided by the user to bypass the covariance matrix calculations |
nrep | number of repetitions. |
noise_mu | Logical value if you want to apply noise tomultivariate mean. Default: FALSE |
pertr_vec | A named vector.Vector's names are the continuous variablesthat the user want to perturb. Variance of simulated data set mimic originaldata's variance. |
change_cov | change the covariance of a specific pair of variables. |
change_amount | the amount of change in the covarianceof a specific pair of variables. |
seed | A numeric value specifying the random seed. If |
thresh_var | A data frame that contains the thresholds(left and right)of specified variables(1st column: variable names, 2nd column: Left thresholds,3rd column: Right thresholds) |
thresh_force | A logical value indicating if you want to force thresholdin case the proportion of samples that can surpass the threshold are lessthan 10% |
var_prop | A named vector that provides a proportion ofvalue=1 for a specific binary variable(=name of the vector) that will bethe proportion of this value in the simulated data sets.[this may increaseexecution time drastically] |
var_infl | A named vector.Vector's names are the continuous variablesthat the user want to perturb and increase their variance |
infl_cov_stable | Logical value. If TRUE,perturbation is applied tooriginal data set and simulations values mimic the perturbed original dataset.Covariance matrix used for simulation = original data's correlations.If FALSE, perturbation is applied to the simulated data sets. |
tol | A numeric value that set uptolerance(relative to largest variance) for numerical lack ofpositive-definiteness in Sigma |
stop_sim | A logical value indicating if the analysis shouldstop before simulation and produce only the correlation matrix |
new_mean_sd | A matrix that contains two columns named"Mean" and "SD" that the user specifies desired Means and Standard Deviationsin the simulated data sets for specific continues variables. The variablesmust be declared as ROWNAMES in the matrix |
multi_sugg_prop | A named vector that provides a proportion ofvalue=1 for specific binary variables(=name of the vector) that will bethe close to the proportion of this value in the simulated data sets. |
generalized_mode | A logical value indicating if generalized lambda/poissondistributions or set up thresholds will be used to generate the simulated values |
generalized_mode_model | A matrix that contains two columns named "Variable" and"Model". This matrix can be used only if a generalized_mode_model argument isprovided. It specifies what model should be used for each Variable.Model values should be "rmfmkl", "rprs", "star" or a combination of them,e.g. "rmfmkl-rprs" or "star-star", in case the use wants a bimodal simulation.The user can select Generalised Poisson model for poisson variables,but this model cannot be included in bimodal simulation |
generalized_mode_lmbds | A matrix that contains lambdas values for each of thevariables of the data set to be used for either Generalized Lambda DistributionGeneralized Poisson Distribution or setting up thresholds |
Details
Simulated data is generated based on available data. The simulated datamimics the characteristics of the original data. The algorithm used isbased on the ranked based inverse normal transformation (Koliopanos etal. (2023)).
Value
A list with the following components:
simulated_data | A list of data frames containing the simulated data. |
original_data | A data frame with the input data. |
correlations | a list of correlation matrices. The ith element is thecorrelation matrix for the ith simulated dataset. The |
bin_variables | character vector listing the binary variables |
categ_variables | a character vector listing the ordinalcategorical variables |
covariance_matrix | Covariance matrix used when generating observationsfrom a multivariate normal distribution. |
seed | Random seed used. |
samples_produced | Number of rows of each simulated dataset. |
sim_dataset_number | Number of simulated datasets produced. |
A list with the following components:
simulated_data | A list of data frames containing the simulated data. |
original_data | A data frame with the input data. |
correlations | a list of correlation matrices. The ith element is thecorrelation matrix for the ith simulated dataset. The |
bin_variables | character vector listing the binary variables |
categ_variables | a character vector listing the ordinalcategorical variables |
covariance_matrix | Covariance matrix used when generating observationsfrom a multivariate normal distribution. |
seed | Random seed used. |
samples_produced | Number of rows of each simulated dataset. |
sim_dataset_number | Number of simulated datasets produced. |
Author(s)
Francisco M. Ojeda, George Koliopanos
References
Koliopanos, G. and Ojeda, F. and Ziegler Andreas (2023),“A simple-to-use R package for mimicking study data by simulations,”Methods Inf Med.
Examples
data("Cleveland",package="modgo")test_modgo <- modgo(data = Cleveland, bin_variables = c("CAD","HighFastBloodSugar","Sex","ExInducedAngina"), categ_variables =c("Chestpaintype"))MOck Data GeneratiOn
Description
modgo_survival Create mock dataset from a real one by usingGeneralized Lambdas Distributions and by seperating the data set in 2 basedin the event status.
Usage
modgo_survival( data, event_variable = NULL, time_variable = NULL, surv_method = 1, ties_method = "max", variables = colnames(data), bin_variables = NULL, categ_variables = NULL, count_variables = NULL, n_samples = nrow(data), sigma = NULL, nrep = 100, noise_mu = FALSE, pertr_vec = NULL, change_cov = NULL, change_amount = 0, seed = 1, thresh_var = NULL, thresh_force = FALSE, var_prop = NULL, var_infl = NULL, infl_cov_stable = FALSE, tol = 1e-06, stop_sim = FALSE, new_mean_sd = NULL, multi_sugg_prop = NULL, generalized_mode = TRUE, generalized_mode_model = NULL, generalized_mode_model_event = "rprs", generalized_mode_model_no_event = "rprs", generalized_mode_lmbds = NULL)Arguments
data | a data frame containing the data whose characteristics are to bemimicked during the data simulation. |
event_variable | a character string listing the event variable. |
time_variable | a character string listing the time variable. |
surv_method | A numeric value that indicates which one of the 2 survivalmethods will be used.First method(surv_method = 1): Event and no event data sets are using different covariance matrices for the simulation.Second method(surv_method = 2): Event and no event data setsare using the same covariance matrix for the simulation |
ties_method | Method on how to deal with equal valuesduring rank transformation. Acceptable input:"max","average","min". Thisparameter is passed by |
variables | a vector of which variables you want to transform.Default:colnames(data) |
bin_variables | a character vector listing the binary variables. |
categ_variables | a character vector listing the ordinal categoricalvariables. |
count_variables | a character vector listing the count as a subsub category of categorical variables. Count variables should be partof categorical variables vector. Count variables are treated differentlywhen using gldex to simulate them. |
n_samples | Number of rows of each simulated data set. Default isthe number of rows of |
sigma | a covariance matrix of NxN (N= number of variables)provided by the user to bypass the covariance matrix calculations |
nrep | number of repetitions. |
noise_mu | Logical value if you want to apply noise tomultivariate mean. Default: FALSE |
pertr_vec | A named vector.Vector's names are the continuous variablesthat the user want to perturb. Variance of simulated data set mimic originaldata's variance. |
change_cov | change the covariance of a specific pair of variables. |
change_amount | the amount of change in the covarianceof a specific pair of variables. |
seed | A numeric value specifying the random seed. If |
thresh_var | A data frame that contains the thresholds(left and right)of specified variables(1st column: variable names, 2nd column: Left thresholds,3rd column: Right thresholds) |
thresh_force | A logical value indicating if you want to force thresholdin case the proportion of samples that can surpass the threshold are lessthan 10% |
var_prop | A named vector that provides a proportion ofvalue=1 for a specific binary variable(=name of the vector) that will bethe proportion of this value in the simulated data sets.[this may increaseexecution time drastically] |
var_infl | A named vector.Vector's names are the continuous variablesthat the user want to perturb and increase their variance |
infl_cov_stable | Logical value. If TRUE,perturbation is applied tooriginal data set and simulations values mimic the perturbed original dataset.Covariance matrix used for simulation = original data's correlations.If FALSE, perturbation is applied to the simulated data sets. |
tol | A numeric value that set uptolerance(relative to largest variance) for numerical lack ofpositive-definiteness in Sigma |
stop_sim | A logical value indicating if the analysis shouldstop before simulation and produce only the correlation matrix |
new_mean_sd | A matrix that contains two columns named"Mean" and "SD" that the user specifies desired Means and Standard Deviationsin the simulated data sets for specific continues variables. The variablesmust be declared as ROWNAMES in the matrix |
multi_sugg_prop | A named vector that provides a proportion ofvalue=1 for specific binary variables(=name of the vector) that will bethe close to the proportion of this value in the simulated data sets. |
generalized_mode | A logical value indicating if generalized lambda/poissondistributions or set up thresholds will be used to generate the simulated values |
generalized_mode_model | A matrix that contains two columns named "Variable" and"Model". This matrix can be used only if a generalized_mode_model argument isprovided. It specifies what model should be used for each Variable.Model values should be "rmfmkl", "rprs", "star" or a combination of them,e.g. "rmfmkl-rprs" or "star-star", in case the use wants a bimodal simulation.The user can select Generalised Poisson model for poisson variables,but this model cannot be included in bimodal simulation |
generalized_mode_model_event | A matrix that contains two columns named "Variable" and"Model" and it is to be used for the event data set(event = 1). This matrix can be used only if a generalized_mode_model argument isprovided. It specifies what model should be used for each Variable.Model values should be "rmfmkl", "rprs", "star" or a combination of them,e.g. "rmfmkl-rprs" or "star-star", in case the use wants a bimodal simulation.The user can select Generalised Poisson model for poisson variables,but this model cannot be included in bimodal simulation |
generalized_mode_model_no_event | A matrix that contains two columns named "Variable" and"Model" and it is to be used for the non-event data set(event = 0). This matrix can be used only if a generalized_mode_model argument isprovided. It specifies what model should be used for each Variable.Model values should be "rmfmkl", "rprs", "star" or a combination of them,e.g. "rmfmkl-rprs" or "star-star", in case the use wants a bimodal simulation.The user can select Generalised Poisson model for poisson variables,but this model cannot be included in bimodal simulation |
generalized_mode_lmbds | A matrix that contains lambdas values for each of thevariables of the data set to be used for either Generalized Lambda DistributionGeneralized Poisson Distribution or setting up thresholds |
Details
Simulated data is generated based on available data. The simulated datamimics the characteristics of the original data. The algorithm used isbased on the ranked based inverse normal transformation (Koliopanos etal. (2023)).
Value
A list with the following components:
simulated_data | A list of data frames containing the simulated data. |
original_data | A data frame with the input data. |
correlations | a list of correlation matrices. The ith element is thecorrelation matrix for the ith simulated dataset. The |
bin_variables | character vector listing the binary variables |
categ_variables | a character vector listing the ordinalcategorical variables |
covariance_matrix | Covariance matrix used when generating observationsfrom a multivariate normal distribution. |
seed | Random seed used. |
samples_produced | Number of rows of each simulated dataset. |
sim_dataset_number | Number of simulated datasets produced. |
Author(s)
Francisco M. Ojeda, George Koliopanos
Examples
data("cancer", package = "survival")cancer_data <- na.omit(cancer)cancer_data$sex <- cancer_data$sex - 1cancer_data$status <- cancer_data$status - 1test_surv <- modgo_survival(data = cancer_data, surv_method = 1, bin_variables = c("status", "sex"), categ_variables = "ph.ecog", event_variable = "status", time_variable = "time", generalized_mode_model_no_event = "rmfmkl", generalized_mode_model_event = "rprs")Modgo multi-studies
Description
Combines modgo objects from a multiple studies to a single one in order to calculate new correlations and visualise the data
Usage
multicenter_comb(modgo_1, ...)Arguments
modgo_1 | a list modgo object. |
... | multiple modgo object names. |
Value
A modgo object/list that consist the merging of multiplemodgo objects.
Author(s)
Francisco M. Ojeda, George Koliopanos
Rank based inverse normal transformation
Description
Applies the rank based inverse normal transformation to numeric vector.
Usage
rbi_normal_transform(x, ties_method = c("max", "min", "average"))Arguments
x | a numeric vector |
ties_method | Method on how to deal with equal values during rank transformation.Acceptable input:"max","average","min". Thisparameter is passed to the parameter |
Details
The rank based inverse normal transformation (Beasley et al. (2009)), transforms values of a vector to ranks and then applies the quantile function of the standard normal distribution.
Value
A numeric vector with rank transformed values.
Author(s)
Andreas Ziegler, Francisco M. Ojeda, George Koliopanos
References
Beasley, T.M. and Erickson S. and Allison D.B. (2009), “Rank-based inverse normal transformations are increasingly used, but are they merited?,”Behavior genetics39, 580-595.
Examples
data("Cleveland",package="modgo")test_rank <- rbi_normal_transform(Cleveland[,1])Inverse of rank based inverse normal transformation
Description
Transforms a vectorx using the inverse of rank based inverse normal transformation associated with a given vectorx_original. This inverseis defined asF_n^{-1}\Phi(x), whereF_n^{-1} is the inverse empirical cumulative distribution function ofx_original and\Phi is the cumulative distribution function of a standard normal random variable.
Usage
rbi_normal_transform_inv(x, x_original)Arguments
x | a numeric vector. |
x_original | a numeric vector from the original dataset |
Value
A numeric vector with inverse transformed values
Author(s)
Andreas Ziegler, Francisco M. Ojeda, George Koliopanos
Examples
data("Cleveland",package="modgo")test_rank <- rbi_normal_transform(Cleveland[,1])test_inv_rank <- rbi_normal_transform_inv(x = test_rank, x_original = Cleveland[,1])