search

kaitlyngaynor / hopland-hunting

Exploration of Hopland hunter GPS data
Apache License 2.0
1 stars 0 forks source link

Confusion around zero inflation #9

Closed kaitlyngaynor closed 2 years ago

kaitlyngaynor commented 2 years ago

There are many (~30%) steps with a length of 0. The coordinates are identical between the two fixes. We suspect this is due to the inability of the iGotU to detect satellites, and that it fills in missing locations with the previous location.

Look at step lengths that follow a 0 and see if they are disproportionately large. If not, then maybe they are ok.

kaitlyngaynor commented 2 years ago

We looked into the non-zero step lengths of steps following 0s. They are mostly small; the largest is ~500 meters (very reasonable speed). They are generally smaller than the steps that do not follow 0s. So we see no issue with 'false' zeros. It is likely that they represent truly stationary points, or stationary enough.

https://github.com/kaitlyngaynor/hopland-hunting/commit/eddb5804705db80ffcb6fda21dab35f887653938