ifa.bic: A function to compute the BIC

In ifa: Independent Factor Analysis

Description

A function to compute the Bayesian Information Criterion (BIC), also known as Schwarz's Bayesian criterion (SBC), for the fitted IFA model, according to the formula -2*log-likelihood + npar*log(nobs), where npar represents the number of parameters and nobs the number of observations in the fitted model.

Usage

ifa.bic(output)

Arguments

output

The fitted IFA model object, a list including the log-likelihood, the number of observations and the number of parameters.

Value

It returns a numeric value with the corresponding BIC.

Author(s)

Cinzia Viroli

References

Schwarz, G. (1978) Estimating the Dimension of a Model, Annals of Statistics, 6, 461-464.

Viroli, C. (2005). Choosing the number of factors in Independent Factor Analysis model, Metodoloski Zvezki, Advances in Methodology and Statistics, Vol. II, N. 2, 219-229. Available at $www2.stat.unibo.it/viroli$.

See Also

ifa.aic

Examples

data(memory)
fit<-ifa.em(memory$x,c(2,2),it=50,eps=0.001)
ifa.bic(fit)

ifa documentation built on May 2, 2019, 1:07 p.m.