User: | Open Learning Faculty Member:
I was surprised to see that all three sampling techniques showed marginal differences in time required to sample. Perhaps it was the way I performed the exercise, but systematic sampling (12h36m) was barely faster than random sampling (12h40m), which was also minutely faster than haphazard sampling (12h42m). I’m not sure how the simulation calculates estimated sampling time, but intuitively it seems like haphazard sampling should be the fastest method.
In terms of percent error, systematic sampling yielded the worst results for a common species (eastern hemlock, 15.4% sweet birch, 17%) and haphazard sampling yielded the worth results for rare species (striped maple, 200% yellow pine, 160%). Random sampling yielded the most accurate results for both common (7.7% and 6.5% error) and rare species (0% and 25% error).
I imagine in reality that haphazard sampling should be the fastest technique, with consistently inaccurate results for rare species and potentially accurate results for common species, that systematic sampling would be the second fastest technique, with marginally accurate results for both common and rare species assuming that environmental gradients are crossed, and that random sampling is consistently the most accurate but takes the longest.
