predict.earth {earth} | R Documentation |
Predict with an earth
model.
## S3 method for class 'earth': predict(object = stop("no 'object' arg"), newdata = NULL, type = c("link", "response", "earth", "terms"), trace = FALSE, ...)
object |
An earth object.
This is the only required argument.
|
newdata |
Make predictions using newdata , which
can be a dataframe, a matrix, or a vector with length equal to a multiple of the row length
of the original input matrix x .
Default is NULL, meaning return object 's fitted values.
|
type |
Type of prediction.
One of "link" (default), "response" , "earth" , or "term" .The "link" , "response" , and "earth" choices all return the same value unless
the earth model has a GLM component (i.e. unless the glm argument
was used in the original call to earth ).
See predict.glm for a description of the "link" and "response" options.
(In brief: for logistic models use type="response" to return probabilities.) "terms" returns an "earth" response suitable for termplot .
Only the additive terms and the first response (for multi-response models) are returned.
Also, "terms" always returns the earth (not GLM) terms. |
trace |
Default FALSE. Set to TRUE to see which data, subset, etc. predict.earth is using.
|
... |
Unused, but provided for generic/method consistency. |
If type="terms"
, a matrix with each column showing the contribution of a predictor.
Else the predicted values (a matrix for multiple response models).
data(trees) a <- earth(Volume ~ ., data = trees) predict(a) # same as a$fitted.values predict(a, c(10,80)) # yields 17.76888