Time Series Analysis

In the previous chapter we considered the dependence of a random variable y on a controlled variable t. As in that case we will assume here that y consists of two parts, the true value of the measured quantity η and a measurement error $\varepsilon$,

$$\displaystyle{ y_{i} =\eta _{i} +\varepsilon _{i}\quad,\qquad i = 1,2,\ldots,n\quad. }$$

(13.1.1)

In Chap. 12 we assumed that η i was a polynomial in t. The measurement error $\varepsilon _{i}$ was considered to be normally distributed about zero.