anova-methods {cold} | R Documentation |

## Methods for function `anova`

### Description

Computes an analysis deviance table for two nested fitted model objects of class `cold`

.

### Usage

```
## S4 method for signature 'cold'
anova(object, ...)
```

### Arguments

`object` |
an object of class |

`...` |
an object of class |

### Warning

The comparison between two models by anova will only be valid if they are fitted to the same dataset.

### Methods

`signature(object = "ANY")`

:Generic function.

`signature(object="cold")`

:Anova for

`cold`

object.

### Note

It uses the naive solution of Pinheiro et al. (2000) to calculate the p-value when the difference between the models is the number of random effects.

### References

Pinheiro, J.C. and Bates, D.M. (2000). Mixed-Effects Models in S and S-PLUS.
*Springer-Verlag.*

### Examples

```
##### data = seizure
seiz1 <- cold(y ~ lage + lbase + v4 + trt + trt:lbase, data = seizure,
start = NULL, dependence = "AR1")
seiz2 <-cold(y ~ lage + lbase + v4 + trt, data = seizure, start = NULL,
dependence = "AR1")
anova(seiz1, seiz2)
##### data = datacold
mod0 <- cold(z ~ Time * Treatment, data = datacold, time = "Time",
id = "Subject", dependence = "ind")
mod0R <- cold(z ~ Time * Treatment, random = ~ 1, data = datacold,
time = "Time", id = "Subject", dependence = "indR")
summary(mod0R)
anova(mod0, mod0R)
```

[Package

*cold*version 2.0-3 Index]