Conformal prediction

This function allows you to specify the method used to perform conformal prediction.

Usage

conformal(object, ...)

# S3 method for class 'cvforecast'
conformal(object, method = c("scp", "acp", "pid", "mcp"), ...)

Arguments

object

An object of class "cvforecast". It must have an argument x for original univariate time series, an argument MEAN for point forecasts and ERROR for forecast errors on validation set. See the results of a call to cvforecast.

...

Additional arguments to be passed to the selected conformal method.

method

A character string specifying the conformal method to be applied. Possible options include "scp" (scp), "acp"(acp), "pid"(pid), and "mcp"(mcp).

Examples

# Simulate time series from an AR(2) model
library(forecast)
series <- arima.sim(n = 1000, list(ar = c(0.8, -0.5)), sd = sqrt(1))

# Cross-validation forecasting
far2 <- function(x, h, level) {
  Arima(x, order = c(2, 0, 0)) |>
    forecast(h = h, level)
}
fc <- cvforecast(series, forecastfun = far2, h = 3, level = c(80, 95),
                 forward = TRUE, initial = 1, window = 100)

# Classical conformal prediction with equal weights
scpfc <- conformal(fc, method = "scp", symmetric = FALSE, ncal = 100, rolling = TRUE)
summary(scpfc)
#> SCP 
#> 
#> Call:
#>  scp(object = object, symmetric = FALSE, ncal = 100, rolling = TRUE) 
#> 
#>  cp_times = 799 (the forward step included) 
#> 
#> Forecasts of the forward step:
#> Cross-validation
#> 
#> Call:
#>  scp(object = object, symmetric = FALSE, ncal = 100, rolling = TRUE) 
#> 
#>  fit_times =  (the forward step included) 
#> 
#> Forecasts of the forward step:
#>      Point Forecast     Lo 80    Hi 80     Lo 95    Hi 95
#> 1001     -0.5165515 -2.015214 0.910992 -2.615997 1.526088
#> 1002     -0.1132015 -2.043974 1.533047 -3.245547 3.232007
#> 1003      0.2844349 -1.819366 1.857624 -2.714702 3.733580
#> 
#> Cross-validation error measures:
#>       ME   MAE   MSE  RMSE    MPE    MAPE MASE RMSSE Winkler_95 MSIS_95
#> CV 0.004 0.959 1.452 1.088 33.284 206.539  0.9 0.809      5.813   5.463

# ACP with asymmetric nonconformity scores and rolling calibration sets
acpfc <- conformal(fc, method = "acp", symmetric = FALSE, gamma = 0.005, ncal = 100, rolling = TRUE)
summary(acpfc)
#> ACP 
#> 
#> Call:
#>  acp(object = object, gamma = 0.005, symmetric = FALSE, ncal = 100,  
#>      rolling = TRUE) 
#> 
#>  cp_times = 799 (the forward step included) 
#> 
#> Forecasts of the forward step:
#> Cross-validation
#> 
#> Call:
#>  acp(object = object, gamma = 0.005, symmetric = FALSE, ncal = 100,  
#>      rolling = TRUE) 
#> 
#>  fit_times =  (the forward step included) 
#> 
#> Forecasts of the forward step:
#>      Point Forecast Lo 80 Hi 80 Lo 95 Hi 95
#> 1001     -0.5165515    NA    NA    NA    NA
#> 1002     -0.1132015    NA    NA    NA    NA
#> 1003      0.2844349    NA    NA    NA    NA
#> 
#> Cross-validation error measures:
#>       ME   MAE   MSE  RMSE    MPE    MAPE MASE RMSSE Winkler_95 MSIS_95
#> CV 0.004 0.959 1.452 1.088 33.284 206.539  0.9 0.809        NaN     NaN