predict.augSIMEX {augSIMEX} | R Documentation |

## Predict Method for the model fits by augSIMEX

### Description

This function returns the predictions and optionally estimates the standard errors of the predictions from a fitted augSIMEX object.

### Usage

```
## S3 method for class 'augSIMEX'
## S3 method for class 'augSIMEX'
predict(object, newdata = NULL, type = c("link", "response","terms"),
se.fit = FALSE, dispersion = NULL, terms = NULL, na.action = na.pass, ...)
```

### Arguments

`object` |
the “augSIMEX" object gotten from |

`newdata` |
An optional data frame in which to look for variables with which to predict. If not specified, the prediction will be conducted on the original main data. |

`type` |
the type of prediction needed. The default is on the scale of the linear predictors; the alternative " |

`se.fit` |
a logical variable indicating if standard errors are required. |

`dispersion` |
a numeric variable specifying the dispersion of the fit to be assumed when computing the standard errors. |

`terms` |
a character vector specifies which terms are to be returned. This is the case for |

`na.action` |
function determining what should be done with missing values in |

`...` |
other arguments that are passed into the function. |

### Details

The specifications of the arugments are the same as the setting in `glm`

function. The user may refer to the `predict.glm`

.

### Author(s)

Qihuang Zhang and Grace Y. Yi.

### See Also

### Examples

```
data(ToyUni)
example <- augSIMEX(mainformula = Y ~ Xstar + Zstar + W, family = binomial(link = logit),
mismodel = pi|qi ~ W,
meformula = Xstar ~ X + Z + W,
data = ToyUni$Main,validationdata = ToyUni$Validation, subset = NULL,
err.var = "Xstar", mis.var = "Zstar", err.true = "X", mis.true = "Z",
err.mat = NULL,
lambda = NULL, M = 5, B = 2, nBoot = 2, extrapolation="quadratic")
predict(example)
```

*augSIMEX*version 3.7.4 Index]