Hi All
I am a masters student and I have a statistical question. I have an
experiment evaluating the
effects of intertidal elevation (fixed; 3 levels) and seaweed canopy cover
(fixed; 2 levels) on species
richness. Quadrats are randomly distributed across 5 sites (random factor) with
4 replicates in
each elevation and canopy treatment combination per site; therefore, I am using
a nested model.
The model is described by Underwood in his Experiments in Ecology textbook
(1997, page 367)
and is:
df
Mean square denominator
Intertidal Zone 2 S(I*C)
Canopy Cover 1 S(I*C)
Intertidal zone * Canopy cover 2 S(I*C)
Site (Intertidal zone * Canopy Cover) 24 Error
Error 90
The usual procedure is to run this main effects model and, when there is a
significant interaction
term, to run simple effects at each level of A) intertidal zone and B) canopy
cover using this model
(as an example for each level of intertidal elevation):
df Mean square
denominator
Canopy Cover 1 S(C)
Site(Canopy) 8 Error
Error 90
Essentially, my data shows significance in the main model for Intertidal zone
(p = 0.0019),
Canopy cover (p = 0.0034) and for the nested site term (p < 0.0001), but there
is no significance
in the interaction term (p = 0.6978). Regardless of this non-significant
interaction term, I still ran
simple effects, for each intertidal elevation separately, and found
significance in the canopy
treatment at two of the intertidal elevations (p = 0.0013 and p = 0.0003), with
no significant
difference occurring in the third elevation (p = 0.4842). Does anyone know why
I may be getting
a non-significant interaction term even when canopy effects depend on the level
of elevation
being considered?
Any advice would be greatly appreciated
Thanks
Cortney Watt
