Probabilistic forecasting using stochastic diffusion models, with applications to cohort processes of marriage and fertility

We study prediction and error propagation in Hernes, Gompertz, and logistic models for innovation diffusion. We develop a unifying framework in which the models are linearized with respect to cohort age and predictions are derived from the underlying linear process. We develop and compare methods for deriving the predictions and show how Monte Carlo simulation can be used to estimate prediction uncertainty for a wide class of underlying linear processes. For an important special case, random walk with, we develop an analytic prediction variance estimator. Both the Monte Carlo method and the analytic variance estimator allow the forecasters to make precise the level of within-model prediction uncertainty in innovation diffusion models. Empirical applications to first births, first marriages and cumulative fertility illustrate the usefulness of these methods.