Mediate: Mediation Analysis and Bayes Factor Computation

In arashl1364/BFMediate: Mediation Analysis Using a Combination of Bayesian Estimation Methods, Latent Variable Models, and Bayes Factors

Mediation Analysis and Bayes Factor Computation

Description

Mediation Analysis and Bayes Factor Computation

Usage

Mediate(Data, Model, Prior, R, burnin)

Arguments

Data	list(X, M, Y) for "Simple", list(X, m_star, y_star) for "Cont", list(X, m_tilde, Y) for "MCat", list(X, M, y_tilde) for "YCat", and list(X, m_tilde, y_tilde) for "MYCat"
Model	can be either "Simple", "Cont", "MCat", "YCat", "MYCat". In case of Simple, a simple partial mediation is estimated, Baron and Kenny (1986), and Preacher and Hayes (2004) proposed methods are also computed
Prior	list(A_M,A_Y)
R	number of MCMC iterations, default = 10000
burnin	number of MCMC draws before the posterior is converged

Details

Model

For Data arguments and Models, see

• PartialMed for "Simple"

• MeasurementMCat for "MCat"

• MeasurementYCat for "YCat"

• MeasurementMYCat for "MYCat"

Prior = list(A_M,A_Y) [optional]

A_M

vector of coefficients' prior variances of eq.1, default = rep(100,2)

A_Y

vector of coefficients' prior variances of eq.2, default = c(100,100,1)

Value

BK = list(eq1, eq2, Indirect_se, FullMed) (only for "Simple"!)

eq1

the summary of the eq.1 regression

eq2

the summary of the eq.2 regression

Indirect_se

the standard error of the indirect effect a la Sobel(1982)

FullMed

the significance test result for the direct effect

PH = list(Indirect_mean, Indirect_CI, Direct_CI)

Indirect_mean

the bootstrapped mean of the indirect effect

Indirect_CI

the bootstrapped 95% confidence interval of the indirect effect

Direct_CI

the bootstrapped 95% confidence interval of the direct effect

list(evidence, Indirect_CI, Direct_CI, BF,...) (For all the models)

evidence

the interpretation of the BF in terms of evidence in favor of full mediation according to Kass and Raftery (1995)

Indirect_CI

the Bayesian 95% HDI (confidence interval) of the indirect effect

Direct_CI

the Bayesian 95% HDI (confidence interval) of the direct effect

BF

the Bayes factor(BF_01) of the corresponding model (see Laghaie and Otter (2020))

For the rest of the values, see

• PartialMed for "Simple"

• MeasurementMCat for "MCat"

• MeasurementYCat for "YCat"

• MeasurementMYCat for "MYCat"

Examples

simPartialMed = function(beta_M,beta_Y, sigma_M, sigma_Y,N,X) {
eps_M = rnorm(N)*sigma_M      # generate errors for M (independent)
eps_Y = rnorm(N)*sigma_Y      # generate errors for Y (independent)
M = beta_M[1] + beta_M[2] * X + eps_M # generate latent mediator M
Y = beta_Y[1] + beta_Y[2] * M + beta_Y[3] * X + eps_Y  # generate dependent variable
list(X = X, M = M, Y = Y)
}

# Set up data generating parameters
N = 1000    # number of observations
sigma_M = .2^.5    # error std M
sigma_Y = .2^.5    # error std Y
beta_M = c(1, .3)   # beta_0M and beta_1
beta_Y = c(1, .5, 0)    # beta_0Y, beta_2, beta_3
X = rnorm(N,mean = 1,sd = 1)   # generate random X
# Generate data based on parameters
Data = simPartialMed(beta_M,beta_Y,sigma_M,sigma_Y,N,X)

#Estimation
A_M = c(100,100);  # Prior variance for beta_0M, beta_1
A_Y = c(100,100,1) # Prior variance for beta_0Y, beta_2, beta_3
R = 2000
out = Mediate(Data = Data, Model = 'Simple',
                Prior = list(A_M = A_M, A_Y = A_Y),R=5000, burnin = 3000)

# Results
out$BK$FullMed
out$PH$Indirect_CI
colMeans(out$Simple$beta_Y)
out$Simple$BF

arashl1364/BFMediate documentation built on Oct. 11, 2023, 5:54 p.m.