This article provides out-of-sample forecasts of Nevada gross gaming
revenue (GGR) and taxable sales using a battery of linear and non-linear forecasting
models and univariate and multivariate techniques. The linear models include vector
autoregressive and vector error-correction models with and without Bayesian priors.
The non-linear models include non-parametric and semi-parametric models, smooth
transition autoregressive models, and artificial neural network autoregressive models.
In addition to GGR and taxable sales, we employ recently constructed coincident and
leading employment indexes for Nevada’s economy. We conclude that the non-linear
models generally outperform