## Prior hyperparameters hyperparameters = { \ "eps_shape": 2, "eps_scale": 1, \ "w_shape": 2, "w_scale": 1, \ "r_scale": 1, \ "K_mean": 1, "K_sd": 1, "K_a": 0, "K_b": 10**10, \ "theta_scale": 1, \ "n0_mean": 1, "n0_sd": 1, "n0_a": 0, "n0_b": 10**10} def updateHyperparametersWithData(hyperparameters, observations): hyperparameters["K_mean"] = mean(observations) hyperparameters["K_sd"] = 2 * sqrt(var(observations)) hyperparameters["n0_mean"] = mean(observations) hyperparameters["n0_sd"] = 2 * sqrt(var(observations)) return hyperparameters modeltheta = ParameterModel(name = "Population Dynamic model theta (M2), reparameterized", dimension = 6) modeltheta.setHyperparameters(hyperparameters) modeltheta.setUpdateHyperparametersWithData(updateHyperparametersWithData) modeltheta.setPriorlogdensity(logdprior) modeltheta.setPriorgenerator(rprior) modeltheta.setParameterNames(["expression(sigma[epsilon]^2)", "expression(sigma[W]^2)", \ "expression(log(N[0]))", "expression(r)", "expression(K)", "expression(theta)"]) modeltheta.setTransformation(["log", "log", "none", "log", "log", "log"]) modeltheta.setRtruevalues([0.05**2, 0.05**2, log(1), 0.18, 1, 0.2])
return parameters ## Prior hyperparameters hyperparameters = { \ "eps_shape": 2, "eps_scale": 1, \ "w_shape": 2, "w_scale": 1, \ "r_scale": 1, \ "K_mean": 1, "K_sd": 1, "K_a": 0, "K_b": 10**10, \ "theta_scale": 1, \ "n0_mean": 1, "n0_sd": 1, "n0_a": 0, "n0_b": 10**10} def updateHyperparametersWithData(hyperparameters, observations): hyperparameters["K_mean"] = mean(observations) hyperparameters["K_sd"] = 2 * sqrt(var(observations)) hyperparameters["n0_mean"] = mean(observations) hyperparameters["n0_sd"] = 2 * sqrt(var(observations)) return hyperparameters modeltheta = ParameterModel( name="Population Dynamic model theta (M2), reparameterized", dimension=6) modeltheta.setHyperparameters(hyperparameters) modeltheta.setUpdateHyperparametersWithData(updateHyperparametersWithData) modeltheta.setPriorlogdensity(logdprior) modeltheta.setPriorgenerator(rprior) modeltheta.setParameterNames(["expression(sigma[epsilon]^2)", "expression(sigma[W]^2)", \ "expression(log(N[0]))", "expression(r)", "expression(K)", "expression(theta)"]) modeltheta.setTransformation(["log", "log", "none", "log", "log", "log"])