25.4 Concluding thoughts

If you start with a known differential equation and want to add stochasticity to a parameter, here is a process:

  • Replace whatever parameter with a “parameter + Noise” term (i.e aa+ Noise ).
  • Collect terms multiplied by Noise - they will form the stochastic part of the differential equation.
  • The deterministic part of the differential equation should be your original differential equation.

The most general form of the stochastic differential equation is: dy=f(y,α,t)dt+g(y,α,t)dW(t), where y is the vector of state variables you want to solve for, and α is your vector of parameters, and dW(t) is the stochastic noise from the random walk.

At a given initial condition, the Euler-Maruyama method applies locally linear approximations to forecast the solution forward Δt time units: yn+1=yn+f(yn,α,tn)Δt+g(yn,α,tn)σrnorm(N)Δt, where rnorm(N) is N dimensional random variable from a normal distribution with mean 0.