Question
The 1-step ahead forecast error at time t, which is denoted e
t, is the difference between the observed value and the 1-step ahead forecast of X
t:
e
t = x
t -
\(\hat{x}_t\)
The sum of squared errors, or SSE, is given by
SSE =
\(\large \sum_{t=1}^ne_t^2 = \sum_{t=1}^n(x_t-\hat{x}_t)^2\)
Given observed values x
1 ,x
2 ,...,x
n ,the optimal value of the smoothing parameter α for simple exponential smoothing is the value that [...].