powered by
To produce forecast means (instead of forecast medians) it is necessary to adjust the back-transformation function relative to the forecast variance.
biasadj(bt_fn, fvar)
The back-transformation function
The forecast variance
More details about bias adjustment can be found in the transformations vignette: read the vignette: vignette("transformations", package = "fable")
vignette("transformations", package = "fable")
# NOT RUN { adj_fn <- biasadj(exp, 1:10) y <- rnorm(10) exp(y) adj_fn(y) # }
Run the code above in your browser using DataLab