Why Would You Use a Moving Window For Calculating Statistics?

Question

I have a grid where I am calculating rates (kind of).  My boss asked me why I used this moving grid.  I could not answer her, I just thought it was cool.

Basically, I have a grid that is 25 miles on each side (625 square miles), I then remade the grid by shifting it 5 miles to the south a total of 4 times.  The blocks were also shifted 5 miles to the east a total of 4 times (meaning I shifted the original block 24 times.

So what is the advantage in doing this?  Is it written in a best practice text or something similar?  By doing this method, I will get the absolute highest area vs just one grid, I understand that.

Am I making sense?  Any advice or referrals would be appreciated.

Thanks

Blocks.png

DanPatterson_Retired · Answer

a moving window is usually used to filter out 'noisy' data which can arise from a variety of circumstances.  The most common useage is in the area of remote sensing where the sensor response may reflect 'error' or just the inherent spatial variation that exists in the landscape.  filtering with such things as the average (for interval ratio data like elevation, temperature etc) provides a dampening to spikes and provides a more generalized representation of the spatial pattern.  Other filters like the most frequent, mode or dominant would be more useful  for other data measured on a nominal or ordinal scale.

It just isn't the 'windowing' that is important, it is also the size and shape of the window, they all have there useages.

The other type of filter is the 'jumping' or 'block' window, that has similar functionality to the 'moving' window but it moves in predefined chunks, each chunk is the size of the specified window.  There is also a link within the help section of my link that describes the block statistics as well.

Hope that gets you started about thinking about the whole idea of why one might use the focal toolset.  When you want to look at stuff over time then the local toolset is the place to go and if you are interested in how 'zones' or blocks of raster data behave or their characteristics, then there is the zonal toolset which brings you into other areas such as geometry and spatial configuration.

Have fun

WilliamTrachtman · Answer

Dan_Patterson‌, that is a cool tool.  I essentially did something the very similar to that.

But my question is more of a philosophical one.  Why would you use a moving window in general vs just one static grid?

Thanks

DanPatterson_Retired · Answer

There is no need to move the map around... you can calculate statistics for a 'moving window' by simply using...

Focal Statistics—Help | ArcGIS for Desktop

perhaps the confusion, since it is far easier to calculate moving statistics by moving a predefined kernel (eg 5x5) over the map than to move the map itself.