Averages calculated from artificial subgroups of consecutive observations. In control charting, you can create a moving average chart for time weighted data. In time series analysis, Minitab uses moving average to smooth data and reduce random fluctuations in a time series.
For example, an office products supply company monitors inventory levels every day. They want to use moving averages of length 2 to track inventory levels to smooth the data. Here are the data collected over 8 days for one of their products.
Day |
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
Inventory Level |
4310 |
4400 |
4000 |
3952 |
4011 |
4000 |
4110 |
4220 |
Moving average |
4310 |
4355 |
4200 |
3976 |
3981.5 |
4005.5 |
4055 |
4165 |
The first moving average is 4310, which is the value of the first observation. (In time series analysis, the first number in the moving average series is not calculated; it is a missing value.) The next moving average is the average of the first two observations, (4310 + 4400) / 2 = 4355. The third moving average is the average of observation 2 and 3, (4400 + 4000) / 2 = 4200, and so on. If you want to use a moving average of length 3, three values are averaged instead of two.