The batched moving averages of measurement data and their applications in data treatment

We consider the effect of using batched moving averages of measurement data. We show that for a moving average (MA) process the process formed by batched moving averages is again a moving average process but of a lower order. In particular, when the size of the moving step is sufficiently large, the new process is an MA(1) process. Applications are discussed for finding the appropriate amount of averaging such that new process formed by the batched moving averages will resemble white noise thus permitting the statistical methodologies. A real example is used to illustrate the proposed procedure.