This class can be used to estimate a Box-Cox transformation and apply it to existing and future data
Usage
BoxCoxTrans(y, ...)
## S3 method for class 'default':
BoxCoxTrans(y, x = rep(1, length(y)), fudge = 0.2, numUnique = 3, na.rm = FALSE, ...)
## S3 method for class 'BoxCoxTrans':
predict(object, newdata, ...)
Arguments
y
a strictly positive numeric vector of data to be transformed
x
an optional dependent variable to be used in a liner model
fudge
a tolerance value: lambda values within +/-fudge will be coerced to 0 and within 1+/-fudge will be coerced to 1
numUnique
how many unique values should y have to estimate the transformation?
na.rm
a logical value indicating whether NA values should be stripped from y and x before the computation proceeds.
...
for BoxCoxTrans: options ot pass to boxcox. plotit should not be passed through. For predict.BoxCoxTrans, additional arguments are ignored.
object
an object of class BoxCoxTrans
newdata
a numeric vector of values to transform
Value
BoxCoxTrans returns a list of class BoxCoxTrans with elements
lambdaestimated transformation value
fudgevalue of fudge
nnumber of data points used to estimate lambda
summarythe results of summary(y)
ratiomax(y)/min(y)
skewnesssample skewness statistic
predict.BoxCoxTrans returns a numeric vector of transformed values
Details
This function is basically a wrapper for the boxcox function in the MASS library. It can be used to estimate the transformation and apply it to new data.
If any(y <= 0)<="" code=""> or if length(unique(y)) < numUnique, lambda is not estimated and no transformation is applied.=>
References
Box, G. E. P. and Cox, D. R. (1964) An analysis of transformations (with discussion). Journal of the Royal Statistical Society B, 26, 211-252.