Mean filters
Syntax: |
FILTER\MEAN x f npt
|
If the \MEAN
qualifier is used, the
filter will be the running mean, or average, filter. This filter method is
sensitive to large spikes in the data. Any large spikes, for example,
>∼1000
times normal value, should first be removed, by,
for example, the median filter.
There are two versions of the running mean filter, which are chosen by
whether npt
is positive or negative.
The window width is always |npt|
.
If npt > 0
, the average value of
each window placement is calculated by summing the relevant points and
dividing by npt
. The averaging
window butts up against the end.
If npt < 0
, a much faster method
is used which adds a new point to the right and drops an old one from the
left. The window runs off half way from each end, but pseudo points outside
the range are set to the appropriate end point values.