R help - Dec 2012 - Spatial AND Temporal Dependency with lme, or other function?

Hi,

I've got a new dataset which I don't know how to analyze with R. My
knowledge about R is limited for this kind of problem. I've tried to find a
solution with some spatio temporel packages and lme/lmer functions, but
didn't find any similar example.

I've got 10 locations on a coast on which the number of walrus was noted.
I've got a distance measure between each location. We also have an indicator
of the presence of tourists, and the number of seals. These information on each
location were noted 10 times ( 2 summers * 5 weeks). We want to know how the
number of walrus is affected by the tourists, the number of seals, the week of
the summer and the location. For example, we think that they are moving east at
the end of the summer, when there are more tourist in the west, and less seals
in the east.

My problem is how to take into account the spatial and temporal dependency. The
locations are beside one another, so the number of walrus in one location is
closely related to the closest location. I would like to take into account the
distance between each site for the dependency. And we took 10 measures in time
at each location, so I should take into account this correlation too.

I've looked at lme function to model the dependency. It's correct with
only spatial or temporal, but I don't know how to take into account both
dependencies at the same time.

If you know how to do it with lme, or with any other function/package, let me
know!

Thanks in advance, and have a nice day!

Sophie


	[[alternative HTML version deleted]]