env.three: Simulated three-level dataset

In macc: Mediation Analysis of Causality under Confounding

Description

"env.three" is an R environment containing a data list generated from 50 subjects and 4 sessions, and the parameter settings used to generate the data.

Usage

data("env.three")

Format

An R environment.

data3

a list of length 50, each contains a list of length 4 of a data frame with 3 variables.

Theta

a 2 by 2 matrix, which is the value of the fixed effects.

Sigma

the covariance matrix of the model error terms for the single level model.

n

a 50 by 4 matrix, is the number of trials for each subject each session.

Psi

the covariance matrix of the random effects in the mixed effects model.

Lambda

the covariance matrix of the model errors in the mixed effects model.

A

a 50 by 4 matrix, is the A value in the single-level for each subject each session.

B

a 50 by 4 matrix, is the B value in the single-level for each subject each session.

C

a 50 by 4 matrix, is the C value in the single-level for each subject each session.

Details

The number of subjects is N = 50 and the number of sessions is K = 4. Under each session of each subject, the number of trials is a random draw from a Poisson distribution with mean 100. The fixed effects are set to be A = 0.5, C = 0.5, and B = -1, and the variances of the model errors are σ_{1_{ik}}^2 = 1, σ_{2_{ik}}^2 = 4 and the correlation is δ = 0.5. See Section 5.2 of the reference for details.

References

Zhao, Y., & Luo, X. (2014). Estimating Mediation Effects under Correlated Errors with an Application to fMRI. arXiv preprint arXiv:1410.7217.

Examples

data(env.three)
dt<-get("data3",env.three)

macc documentation built on May 2, 2019, 12:23 p.m.