mvpc_gen_data

Missing data generation

Package

MVPC

Version

d901361

Docs

here

Paper

Mohan et al.[1], Rubin[2]

Graph type

DAG

Module

mvpc_gen_data

Description

Module for synthetic Gaussian data generation with different types of missingness: missing at random (MAR), missing completely at random (MCAR), and missing not at random (MNAR) Mohan et al.[1], Rubin[2].

Some fields described

  • mode different methods to generate data sets with different missingness mechanisms, such as mcar, mar and mnar

  • num_extra_e number of the variables with missing values that lead to wrong results

  • num_m number of the variables with missing values

  • p_missing_e The probability of missing values when the missingness condition is not satisfied, e.g., missingness indicator R = 0

  • p_missing_h The probability of missing values when the missingness condition is satisfied, e.g., missingness indicator R = 1

Example

[
  {
    "id": "missing",
    "num_extra_e": 2,
    "num_m": 5,
    "mode": "mar",
    "p_missing_h": 0.9,
    "p_missing_e": 0.1,
    "standardized": false,
    "n": 1001
  }
]