We model a regression density nonparametrically so that at each value of the covariates the density is a mixture of normals with the means, variances and mixture probabilities of the components changing smoothly as a function of the covariates. The model extends existing models in two important...

While a large literature on return predictability has shown a link between valuation levels and expected rates of aggregate returns in-sample, we document a link between valuation levels and the shape of the distribution of cumulative (for example, over 12 and 24 months) total returns. Return...

We show that uncertainty about parameters of the short rate model can account for the rejections of the expectations hypothesis for the term structure of interest rates. We assume that agents employ Bayes rule to learn parameter values in the context of a model that is subject to stochastic...

Andrieu et al. (2010) prove that Markov chain Monte Carlo samplers still converge to the correct posterior distribution of the model parameters when the likelihood is estimated by the particle filter (with a finite number of particles) is used instead of the likelihood. A critical issue for...

We summarize some methods useful in formulating and solving Hansen-Sargent robust control problems, and suggest extensions to discretionary and simple rule policies. Matlab and Gauss software is provided. Applications to the term structure of interest rates and to the time inconsistency of...

We study the inflation uncertainty reported by individual forecasters in the Survey of Professional Forecasters 1969-2001. Three popular measures of uncertainty built from survey data are analyzed in the context of models for forecasting and asset pricing, and improved estimation methods are...

We model a regression density flexibly so that at each value of the covariates the density is a mixture of normals with the means, variances and mixture probabilities of the components changing smoothly as a function of the covariates. The model extends existing models in two important ways....

We introduce SMARTboost (boosting of symmetric smooth additive regression trees), a machine learning model capable of fitting complex functions in high dimensions, yet designed for good performance in small n and low signal-to-noise environments, and on data generated by the most common...