mstDataSimulation {epts}R Documentation

Simulate Multisite Trial (MST) Data

Description

This function simulates a multiple intervention arms Multisite Trial (MST) data. The model includes intervention and pre-test scores as covariates.

Usage

mstDataSimulation(
  ni,
  tpi,
  np,
  ns,
  sigma,
  sigmab0,
  sigmab1,
  B0,
  es,
  seed,
  attritionrates,
  covariates
)

Arguments

ni

The number of intervention groups excluding the control group.

tpi

The proportions (in percent) of total participants assigned to each group, with the first value for the control group. It should be specified as a numeric vector of length ni + 1.

np

The number of pupils per school.

ns

The number of schools.

sigma

The standard deviation of the individual-level error.

sigmab0

The standard deviation of random intercepts at the school level.

sigmab1

The standard deviation of random slopes for the intervention effect.

B0

The intercept of the model.

es

The standardized effect sizes for each intervention group. It should be specified as a numeric vector.

seed

The random seed for reproducibility.

attritionrates

The attrition proportions for each group, including the control group. It should be specified as a numeric vector of length ni + 1.

covariates

List of covariate specifications. Each element should be a list with the following fields:

name

Character. Name of the covariate.

type

Character. Either "continuous" or "categorical".

sd

Numeric. Standard deviation (only for continuous covariates).

coefficient

Numeric. Coefficient (only for continuous covariates).

levels

Character vector. Category levels (only for categorical covariates).

probs

Numeric vector. Sampling probabilities (must sum to 1) (categorical only).

reference

Character. Reference category (categorical only).

coefficients

Named list of numeric values. Coefficients for each non-reference level.

Value

A data.frame containing:

pupils

Pupil ID

schools

School ID

interventions

Intervention group assignment (0 = control, 1 to ni = intervention groups)

covariates

Simulated covariates

posttest

Posttest score (NA if attrited)

Examples

covariates <- list(
 list(name = "pretest", type = "continuous", sd = 1, coefficient = 1.7),
 list(name = "gender", type = "categorical", levels = c("Male", "Female"), 
 probs = c(0.3, 0.7), reference = "Male", coefficients = list(B = -0.5)),
 list(name = "ethnicity", type = "categorical", levels = c("White", "Black", "Asian"),
 probs = c(0.3, 0.3, 0.4), reference = "White", coefficients = list(B = 1.02, C = 1.3))
)

mstdata <- mstDataSimulation(ni = 3, ns = 10, np = 100, tpi = c(30, 30, 20, 20),
sigma = 1, sigmab0 = 0.5, sigmab1 = 0.5, B0 = 1.45, 
es = c(0.2, 0.3, 0.1), seed = 1234, attritionrates = c(0.1, 0.1, 0.1, 0), covariates = covariates) 
head(mstdata)


[Package epts version 1.2.2 Index]