We provide a discussion of “Multivariate dynamic modeling for Bayesian forecasting of business revenue” by Yanchenko, Tierney, Lawson, Hellmayr, Cron, and West. As perfectly exhibited in the paper, the dynamic linear model framework is tremendously diverse and flexible, with many modeling and fine-tuning options that can be suited to a wide range of applications. On the other hand, the sheer amount of flexibility in these models means there can still be strategies that lead to potential forecasting gains. Consequently, in this comment we explore possible extensions to the specification presented in the paper that might add value to this and future business revenue forecasting applications.
This paper proposes a new semiparametric estimator of models where the response random variable is a fraction. The estimator is constructed by optimizing a semiparametric quasi-maximum likelihood that utilizes kernel smoothing. Under suitable conditions, the consistency and asymptotic normality of the proposed estimator is established allowing for data-driven bandwidth choices as well as random trimming, and its flexibility and robustness are showcased in a Monte Carlo experiment and an empirical application.
We propose a Bayesian estimation procedure for the generalized Bass model that is used in product diffusion models. Our method forecasts product sales early based on previous similar markets; that is, we obtain pre-launch forecasts by analogy. We compare our forecasting proposal to traditional estimation approaches, and alternative new product diffusion specifications. We perform several simulation exercises, and use our method to forecast the sales of room air conditioners, BlackBerry handheld devices, and compressed natural gas. The results show that our Bayesian proposal provides better predictive performances than competing alternatives when little or no historical data are available, which is when sales projections are the most useful.
We introduce a Bayesian instrumental variable procedure with spatial random effects that handles endogeneity, and spatial dependence with unobserved heterogeneity. We find through a limited Monte Carlo experiment that our proposal works well in terms of point estimates and prediction. We apply our method to analyze the welfare effects generated by a process of electricity tariff unification on the poorest households. In particular, we deduce an Equivalent Variation measure where there is a budget constraint for a two-tiered pricing scheme, and find that 10% of the poorest municipalities attained welfare gains above 2% of their initial income.