znuclear {bestglm} | R Documentation |

## Nuclear plant data. Quantitative inputs logged and standardized.

### Description

Data on 32 nuclear power plants.
The response variable is cost and there are ten covariates.

### Usage

`data(znuclear)`

### Format

A data frame with 32 observations on the following 12 variables.
All quantitative variables, except date, have been logged and standardized
to have mean 0 and variance 1.

`date`

Quantitative covariate. The date on which the
construction permit was issued. The data are measured in years since
January 1 1990 to the nearest month.

`T1`

Quantitative covariate. The time between application for
and issue of the construction permit.

`T2`

Quantitative covariate. The time between issue of
operating license and construction permit.

`capacity`

Quantitative covariate. The net capacity of the
power plant (MWe).

`PR`

Binary covariate. Value 1, indicates the prior existence
of a LWR plant at the same site.

`NE`

Binary covariate, located in North-East USA

`CT`

Binary covariate, presence of cooling tower

`BW`

Binary covariate, where 1 indicates that the nuclear
steam supply system was manufactured by Babcock-Wilcox.

`N`

Quantitative covariate. The cumulative number of power
plants constructed by each architect-engineer.

`PT`

Binary covariate, partial turnkey guarantee.

`cost`

Outcome. The capital cost of construction in millions
of dollars adjusted to 1976 base.

### Details

Davison (2003) explores fitting models to this data using forward
and backward stepwise regression. In this modelling logs of quantiative
variablesare used. We have also standardized this data to facilitate comparison
with other techniques such as LARS and principal component regression.

Davison and Hinkley (1997, Example 6.8, 6.10, 6.12) use this data in
a series of examples.
Example 6.8: estimation of prediction error.
Example 6.10: prediction error using cross-validation and bootstrapping.
Example 6.12: subset model selection using cross-validation.

### Source

Obtained from the CRAN package boot.

### References

Davison, A. C. (2003). Statistical Models. Cambridge: Cambridge University Press.

Davison, A.C. and Hinkley, D.V. (1997). Bootstrap Methods and their Application.
Cambridge University Press.

### Examples

```
data(znuclear)
bestglm(znuclear, IC="BICq")
```

[Package

*bestglm* version 0.37.3

Index]