Functional Partial Least Squares Regression

Performs functional partial least squares regression for functional time series.

fplsr(
  data,
  order = 6,
  type = c("simpls", "nipals"),
  unit.weights = TRUE,
  weight = FALSE,
  beta = 0.1,
  interval = FALSE,
  method = c("delta", "boota"),
  alpha = 0.05,
  B = 100,
  adjust = FALSE,
  backh = 10
)

Arguments

data

A functional time series object of class fts.

order

Number of components to include in the model (default: 6).

type

Type of PLS algorithm: "simpls" (default) or "nipals".

unit.weights

Logical. If TRUE, use unit weights (default: TRUE).

weight

Logical. If TRUE, use weighted PLS (default: FALSE).

beta

Weight parameter for exponential weighting (default: 0.1).

interval

Logical. If TRUE, compute prediction intervals (default: FALSE).

method

Method for prediction intervals: "delta" (default) or "boota".

alpha

Significance level for prediction intervals (default: 0.05).

B

Number of bootstrap replications (default: 100).

adjust

Logical. If TRUE, adjust for bias (default: FALSE).

backh

Number of steps back for validation (default: 10).

Value

An object of class fm containing:

x1

Time points

y1

Grid points

ypred

Predicted functional time series

y

Original functional time series

Ypred

Predicted values

B

Regression coefficients

P

X loadings

Q

Y loadings

T

X scores

R

Weights

fitted

Fitted values

residuals

Residuals

meanX

Mean of X

meanY

Mean of Y

call

Function call

References

Hyndman, R.J., & Shang, H.L. (2009). Forecasting functional time series. Journal of the Korean Statistical Society, 38(3), 199-221.

See also

forecastfplsr, plotfplsr

Examples

if (FALSE) { # \dontrun{
# Load example data
data(pm_10_GR)

# Fit functional PLS regression
fit <- fplsr(pm_10_GR, order = 3)

# Plot results
plot(fit)
} # }