I am trying to decide how to get my starting parameters optimized for a simple exponential decay model. My regression formula is:
y ~ Be^(at)
Where y is the remaining value at time,t, remaining after decay, B0 is initial value, a is the decay and t is time.
Is a self starting function like R's SSasym appropriate? I've eyeballed initial starting values and also used this function and the results are significant different.