Predicted values and estimate of standard errors based on an "autoFRK" model object.

# S3 method for class 'FRK'
predict(
  object,
  obsData = NULL,
  obsloc = NULL,
  mu.obs = 0,
  newloc = obsloc,
  basis = NULL,
  mu.new = 0,
  se.report = FALSE,
  ...
)

Arguments

object

a model object obtained from "autoFRK".

obsData

a vector with observed data used for prediction. Default is NULL, which uses the Data input from object.

obsloc

a matrix with rows being coordinates of observation locations for obsData. Only object using mrts basis functions can have obsloc different from the loc input of object; not applicable for user-specified basis functions. Default is NULL, which uses the loc input of object.

mu.obs

a vector or scalar for the deterministic mean values at obsloc. Default is 0.

newloc

a matrix with rows being coordinates of new locations for prediction. Default is NULL, which gives prediction at the locations of the observed data.

basis

a matrix with each column being a basis function taken values at newloc. It can be omitted if object was fitted using default mrts basis functions.

mu.new

a vector or scalar for the deterministic mean values at newloc. Default is 0.

se.report

logical; if TRUE then the standard error of prediction is reported.

...

not used but needed for the S3 generic/method compatibility.

Value

A list with the components described below.

pred.value

a matrix with the (i,t) element being the predicted value at i-th location and time t.

se

a vector with the i-th element being the standard error of the predicted value at the i-th location.

See also

Author

ShengLi Tzeng, Hsin-Cheng Huang and Wen-Ting Wang.