This article presents a method for training Dynamic Factor Graphs (DFG) with continuous latent state variables. A DFG includes factors modeling joint probabilities between hidden and observed variables, and factors modeling dynamical constraints on hidden variables. The DFG assigns a scalar energy to each configuration of hidden and observed variables. A gradient-based inference procedure finds...

Time series problems involve analysis of periodic functions for predicting the future. A flexible regression method should be able to dynamically select the appropriate model to fit the available data. In this paper, we present a function approximation scheme that can be used for modeling periodic functions using a series of orthogonal polynomials, named Chebychev polynomials. In our approach, ...

We consider situations in which a significant proportion of observations in a time series are zero, but the remaining observations are positive and measured on a continuous scale. We propose a new dynamic model in which the conditional distribution of the observations is constructed by shifting a distribution for non-zero observations to the left and censoring negative values. The key to genera...

The subject of this paper is autoregressive (AR) modeling of a stationary, Gaussian discrete time process, based on a finite sequence of observations. The process is assumed to admit an AR(∞) representation with exponentially decaying coefficients. We adopt the nonparametric minimax framework and study how well the process can be approximated by a finiteorder AR model. A lower bound on the accu...

Demand forecasting is crucial to electricity providers because their ability to produce energy exceeds their ability to store it. Excess demand can cause “brown outs,” while excess supply ends in waste. In an industry worth over $1 trillion in the U.S. alone [1], almost 9% of GDP [2], even marginal improvements can have a huge impact. Any plan toward energy efficiency should include enhanced ut...

We express the classic ARMA time-series model as a directed graphical model. In doing so, we find that the deterministic relationships in the model make it effectively impossible to use the EM algorithm for learning model parameters. To remedy this problem, we replace the deterministic relationships with Gaussian distributions having a small variance, yielding the stochastic ARMA (σARMA) model....

We consider modeling procedures for multiple time series which aim to address the challenge of providing both a good representation of the structure, and an efficient parameterization. We first review a method, applied to vector autoregressions of low order, which uses conditional independence graphs to identify a sparse structural autoregressive representation. We show by an example how this m...

Even after realignment there is residual movement-related variance present in fMRI time-series, causing loss of sensitivity and, potentially, also specificity. One cause is the differential deformation of the sampling matrix, by field inhomogeneities, at different object positions, i.e., a movement-by-inhomogeneity interaction. This has been addressed previously by using empirical field measure...

This paper argues that time-series econometrics provides valuable tools and opens exciting research opportunities to marketing researchers. It allows marketing researchers to advance traditional modeling and estimation approaches by incorporating dynamic processes to answer new important research questions. The authors discuss the challenges facing time-series modelers in marketing, provide an ...