varycoef (version 0.3.5)

predict.SVC_mle: Prediction of SVCs (and response variable)

Description

Prediction of SVCs (and response variable)

Usage

# S3 method for SVC_mle
predict(
  object,
  newlocs = NULL,
  newX = NULL,
  newW = NULL,
  newdata = NULL,
  compute.y.var = FALSE,
  ...
)

Value

The function returns a data frame of n.new rows and with columns

• SVC_1, ..., SVC_p: the predicted SVC at locations newlocs.

• y.pred, if newX and newW are provided

• y.var, if newX and newW are provided and compute.y.var is set to TRUE.

• loc_x, loc_y, the locations of the predictions

Arguments

object

(SVC_mle)
Model obtained from SVC_mle function call.

newlocs

(NULL or matrix(n.new, 2))
If NULL, then function uses observed locations of model to estimate SVCs. Otherwise, these are the new locations the SVCs are predicted for.

newX

(NULL or matrix(n.new, q))
If provided (together with newW), the function also returns the predicted response variable.

newW

(NULL or matrix(n.new, p))
If provided (together with newX), the function also returns the predicted response variable.

newdata

(NULL or data.frame(n.new, p))
This argument can be used, when the SVC_mle function has been called with an formula, see examples.

compute.y.var

(logical(1))
If TRUE and the response is being estimated, the predictive variance of each estimate will be computed.

...

further arguments

Author

Jakob Dambon

References

Dambon, J. A., Sigrist, F., Furrer, R. (2021) Maximum likelihood estimation of spatially varying coefficient models for large data with an application to real estate price prediction, Spatial Statistics tools:::Rd_expr_doi("10.1016/j.spasta.2020.100470")

See Also

SVC_mle

Examples

## ---- toy example ----
## We use the sampled, i.e., one dimensional SVCs
str(SVCdata)
# sub-sample data to have feasible run time for example
set.seed(123)
id <- sample(length(SVCdata$locs), 50)

## SVC_mle call with matrix arguments
fit_mat <- with(SVCdata, SVC_mle(
  y[id], X[id, ], locs[id], 
  control = SVC_mle_control(profileLik = TRUE, cov.name = "mat32")))

## SVC_mle call with formula
df <- with(SVCdata, data.frame(y = y[id], X = X[id, -1]))
fit_form <- SVC_mle(
  y ~ X, data = df, locs = SVCdata$locs[id], 
  control = SVC_mle_control(profileLik = TRUE, cov.name = "mat32")
)

## prediction

# predicting SVCs
predict(fit_mat, newlocs = 1:2)
predict(fit_form, newlocs = 1:2)

# predicting SVCs and response providing new covariates
predict(
  fit_mat, 
  newX = matrix(c(1, 1, 3, 4), ncol = 2), 
  newW = matrix(c(1, 1, 3, 4), ncol = 2), 
  newlocs = 1:2
)
predict(fit_form, newdata = data.frame(X = 3:4), newlocs = 1:2)