ABSTRACT
The main issue with the approach is that it is computationally expensive and assumes that STL decomposition is appropriate for time series. Furthermore, it assumes that the residuals from this decomposition do not contain any information and are independent. In this chapter, the authors focus on a discussion of uncertainty in ADAM, specifically about the estimates of parameters. In fact, in some instances the error term can be provided by a user, so it would not be random. One of the basic conventional statistical ways of capturing uncertainty about estimates of parameters is via the calculation of the covariance matrix of parameters. An alternative way of constructing the matrix is via the bootstrap. The one implemented in smooth is based on the coefbootstrap method from the greybox package, which implements the modified case resampling. In case of ETS and ARIMA, some of the parameters are bounded and the estimates might lie near the bounds.
