Summary statistics for multistep objects

Description

Calculates a variety of summary statistics for multistep (multidimensional step function) objects.

Usage

## S3 method for class 'multistep'
max(x, ..., na.rm)
## S3 method for class 'multistep'
min(x, ..., na.rm)
## S3 method for class 'multistep'
dim(x)
## S3 method for class 'multistep'
abs(x)
## S3 method for class 'multistep'
summary(object, ...)

Arguments

Dummy variables for compatibility:

Details

'max' and 'min' returns the maximum or minimum respectively of each covariate component.

'dim' returns the number of non-zero steps in each covariate component.

'abs' returns the total variation of each covariate component.

'summary' returns a list containing all of the above.

Value

For 'max', 'min', 'abs', 'dim', a vector with length equal to the number of covariates.

For 'summary', a list containing 'max', 'min', 'totalvar', 'dim', each being a vector of length equal to the number of covariates.

Author(s)

Zhou Fang

References

Zhou Fang and Nicolai Meinshausen (2009), Liso for High Dimensional Additive Isotonic Regression, available at http://blah.com

See Also

multistep

Examples

## Use the method on a simulated data set
set.seed(79)
n <- 100; p <- 50

## Simulate design matrix and response
x <- matrix(runif(n * p, min = -2.5, max = 2.5), nrow = n, ncol = p)
y <- scale(3 * (x[,1]> 0), scale=FALSE)  + x[,2]^3 + rnorm(n)

## try lambda = 2
fits <- liso.backfit(x,y, 2)

## Plot some diagnostics
plot(max(fits))
plot(min(fits))
plot(abs(fits))
plot(dim(fits))
print(summary(fits))

Results