Skip to contents

Generate independent Gaussian covariates and (binary) logistic response data.

logistic_gaussian_dgp.Rd

Generate independent normally-distributed covariates and logistic response data.

Usage

logistic_gaussian_dgp(
  n,
  p,
  s = p,
  betas = NULL,
  betas_sd = 1,
  intercept = 0,
  data_split = FALSE,
  train_prop = 0.5,
  return_values = c("X", "y", "support"),
  ...
)

Arguments

n

Number of samples.

p

Number of features.

s

Sparsity level of features. Coefficients corresponding to features after the s position (i.e., positions i = s + 1, ..., p) are set to 0.

betas

Coefficient vector for observed design matrix. If a scalar is provided, the coefficient vector is constant. If NULL (default), entries in the coefficient vector are drawn iid from N(0, betas_sd^2). Can also be a function that generates the coefficient vector; see generate_coef().

betas_sd

(Optional) SD of normal distribution from which to draw betas. Only used if betas argument is NULL or is a function in which case betas_sd is optionally passed to the function as sd; see generate_coef().

intercept

Scalar intercept term.

data_split

Logical; if TRUE, splits data into training and test sets according to train_prop.

train_prop

Proportion of data in training set if data_split = TRUE.

return_values

Character vector indicating what objects to return in list. Elements in vector must be one of "X", "y", "support".

...

Not used.

Value

A list of the named objects that were requested in return_values. See brief descriptions below.

X

A data.frame.

y

A response vector of length nrow(X).

support

A vector of feature indices indicating all features used in the true support of the DGP.

Note that if data_split = TRUE and "X", "y" are in return_values, then the returned list also contains slots for "Xtest" and "ytest".

Details

Data is generated via: $$log(p / (1 - p)) = intercept + betas \%*\% X,$$ where p = P(y = 1 | X), X is a standard Gaussian random matrix, and the true underlying support of this data is the first s features in X (unless specified otherwise by betas).

Examples

# generate data from: log(p / (1 - p)) = betas_1 * x_1 + betas_2 * x_2, where
# betas_1, betas_2 ~ N(0, 1) and X ~ N(0, I_10)
sim_data <- logistic_gaussian_dgp(n = 100, p = 10, s = 2, betas_sd = 1)