calcBIC {stepNorm} | R Documentation |

## Extract BIC from a Fitted Model

### Description

Computes the Bayesian Information Criterion for a fitted parametric model.

### Usage

calcBIC(fit, subset=TRUE, scale = 0, enp, loss.fun = square)

### Arguments

`fit` |
fitted model; see details below |

`subset` |
A "logical" or "numeric" vector indicating the subset of
points used to compute the fitted model. |

`scale` |
optional numeric specifying the scale parameter of the
model; see `scale` in `step` . |

`enp` |
equivalent number of parameters in the fitted model. If
missing, the `enp` component from fit will be used. |

`loss.fun` |
the loss function used to calculate deviance; the
default uses the squared deviation from the fitted values;
one could also use abosulate deviations (`abs` ). |

### Details

The argument `fit`

can be an object of class
`marrayFit`

, in which case the `residuals`

component
from the `marrayFit`

object will be extracted to calculate
the deviance; the user can also pass in a numeric vector, in which
case it will be interpreted as the residuals and the user needs to
specify the argument `enp`

.

The criterion used is

*BIC = -2*log{L} + k * enp,*

where L is the likelihood and `enp`

the equivalent number of
parameters of `fit`

. For linear models (as in `marrayFit`

),
*-2log{L}* is computed from the deviance.

`k = log(n)`

corresponds to the BIC and is the penalty for
the number of parameters.

### Value

A numeric vector of length 4, giving

`Dev` |
the deviance of the `fit` . |

`enp` |
the equivalent number of parameters of the
`fit` . |

`penalty` |
the penalty for number of parameters. |

`Criterion` |
the Akaike Information Criterion for `fit` . |

### Author(s)

Yuanyuan Xiao, yxiao@itsa.ucsf.edu,

Jean Yee Hwa Yang, jean@biostat.ucsf.edu

### See Also

`AIC`

, `deviance`

, `calcAIC`

.

### Examples

## load in swirl data
data(swirl)
## fit a model
fit <- fitWithin(fun="medfit")
## res is an object of class marrayFit
res <- fit(swirl[,1])
## calculate BIC
calcBIC(res)
## or could pass in the residual vector, but then argument "enp" needs to be specified
calcBIC(res$residual, enp=1)

[Package

*stepNorm* version 1.0.2

Index]