|
Contents
| Quality Encyclopedia
| Discussion Blogs
When
to Use an Autocorrelation Chart
Standard control charts require
that observations from the process are independent of one another. Failure
to meet this requirement increases the chance that the control chart will
indicate a process shift when the process has NOT shifted (a false alarm).
Therefore, the Autocorrelation Function is a good tool to use to check the
independence assumption. If control limits on an X-bar chart are particularly
tight, with many out of control points, autocorrelation should be suspected.
If the autocorrelation
is only significant at low lags (adjacent data points), you can increase
the time between acquiring data points to lessen its effect. In other cases,
there might be auto correlation due to sampling from multiple streams in
a process. For example, when monitoring order processing times, if each
data point is the time taken by each one of five employees operating at
a different average level, then an autocorrelation would appear at lag 5.
|
