# Construct Design Matrices

### Description

`model.matrixBayes`

creates a design matrix.

### Usage

1 2 |

### Arguments

`object` |
an object of an appropriate class. For the default method, a model formula or terms object. |

`data` |
a data frame created with |

`contrasts.arg` |
A list, whose entries are contrasts suitable for
input to the |

`xlev` |
to be used as argument of |

`keep.order` |
a logical value indicating whether the terms should
keep their positions. If |

`drop.baseline` |
Drop the base level of categorical Xs, default is TRUE. |

`...` |
further arguments passed to or from other methods. |

### Details

`model.matrixBayes`

is adapted from `model.matrix`

in the `stats`

pacakge and is designed for the use of `bayesglm`

.
It is designed to keep baseline levels of all categorical varaibles and keep the
variable names unodered in the output. The design matrices created by
`model.matrixBayes`

are unidentifiable using classical regression methods,
though; they can be identified using `bayesglm`

.

### Author(s)

Yu-Sung Su suyusung@tsinghua.edu.cn

### References

Andrew Gelman, Aleks Jakulin, Maria Grazia Pittau and Yu-Sung Su. (2009).
“A Weakly Informative Default Prior Distribution For
Logistic And Other Regression Models.”
*The Annals of Applied Statistics* 2 (4): 1360–1383.
http://www.stat.columbia.edu/~gelman/research/published/priors11.pdf

### See Also

`model.frame`

, `model.extract`

,
`terms`

, `terms.formula`

,
`bayesglm`

.

### Examples

1 2 3 4 5 | ```
ff <- log(Volume) ~ log(Height) + log(Girth)
str(m <- model.frame(ff, trees))
(model.matrix(ff, m))
class(ff) <- c("bayesglm", "terms", "formula")
(model.matrixBayes(ff, m))
``` |