bnpmediation: Posterior Means and 95% C.I.s of the NIE, NDE and TE

In lit777/BNPMediation: Estimate the Natural Direct and Indirect Effects using Dirichlet Processes Mixture Models

Description

Obtain posterior means and credible intervals of the effects.

Usage

bnpmediation(obj1, obj0, q, NN = 100, n1, n0, extra.thin = 5)

Arguments

obj1	The fitted model of the observed data under Z=1 from DPdensity
obj0	The fitted model of the observed data under Z=0 from Dpdensity
q	A dimension of the observed data, i.e., number of covariates plus 2
NN	Number of samples drawn for each iteration from the joint distribution of the mediator and the covariates. Default is 100.
n1	Number of observations under Z=1
n0	Number of observations under Z=0
extra.thin	Giving the extra thinning interval

Value

ENIE Posterior mean of the NIE

ENDE Posterior mean of the NDE

ETE Posterior mean of the TE

IE.c.i 95% C.I. of the NIE

DE.c.i 95% C.I. of the NDE

TE.c.i 95% C.I. of the TE

Y11 Posterior samples of Y11

Y00 Posterior samples of Y00

Y10 Posterior samples of Y10

lit777/BNPMediation documentation built on July 23, 2019, 2:54 a.m.