gompertz: Gompertz model with log-normal observations.
Description
gompertz is a pomp object encoding a stochastic Gompertz population model with log-normal measurement error.
Arguments
Details
The state process is $X[t+1]=K^(1-S) X[t]^S eps[t]$, where $S=e^{-r}$ and the $eps[t]$ are i.i.d. lognormal random deviates with variance $sigma^2$.
The observed variables $Y_t$ are distributed as $lognormal(log(X[t]),tau)$.
Parameters include the per-capita growth rate $r$, the carrying capacity $K$, the process noise s.d. $sigma$, the measurement error s.d. $tau$, and the initial condition $X[0]$.
The pomp object includes parameter transformations that log-transform the parameters for estimation purposes.