summary.mcmcSAR: Summarizing Bayesian SAR Model

In PartialNetwork: Estimating Peer Effects Using Partial Network Data

Summarizing Bayesian SAR Model

Description

Summary and print methods for the class mcmcSAR.

Usage

## S3 method for class 'mcmcSAR'
summary(object, alpha = 0.95, plot.type = NULL, burnin = NULL, ...)

## S3 method for class 'summary.mcmcSAR'
print(x, ...)

## S3 method for class 'mcmcSAR'
print(x, ...)

Arguments

object	an object of class "mcmcSAR", output of the function mcmcSAR.
alpha	(optional, default = 0.95), the significance level of parameter.
plot.type	(optional) a character that indicate if the simulations from the posterior distribution should be printed (if plot.type = "sim") or if the posterior distribution densities should be plotted (plot.type = "dens"). The plots can also done using the method plot.
burnin	is the number of MCMC steps which will be considered as burn-in iterations. If NULL (default value), the 50% first MCMC steps performed are used as burn-in iterations.
...	further arguments passed to or from other methods.
x	an object of class "summary.mcmcSAR" or "mcmcSAR, output of the functions summary.mcmcSAR and print.summary.mcmcSAR.

Details

The function is smart and allows all the possible arguments with the functions summary, plot, par... such as col, lty, mfrow... summary.mcmcSAR, print.summary.mcmcSAR and print.mcmcSAR can be called by summary or print.

Value

A list consisting of:

n.group	number of groups.
N	vector of each group size.
iteration	number of MCMC steps performed.
burnin	number of MCMC steps which will be considered as burn-in iterations.
posterior	matrix (or list of matrices) containing the simulations.
hyperparms	return value of hyperparms.
accept.rate	acceptance rate of zeta.
prop.net	proportion of observed network data.
method.net	network formation model specification.
formula	input value of formula.
alpha	significance level of parameter.
ctrl.mcmc	return value of ctrl.mcmc.
...	arguments passed to methods.

PartialNetwork documentation built on May 29, 2024, 10:08 a.m.