Forecasting, Structural Time Series Models and the Kalman Filter

By Andrew Harvey. 1990

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Time-series forecasting with deep learning: a survey (2020, methodology): “While traditional methods have focused on parametric models informed by domain expertise—such as autoregressive (AR) [6], exponential smoothing [7,8] or structural time-series models [9]— modern machine learning methods provide a means to learn temporal dynamics in a purely data-driven manner [10].”
Deep Factors for Forecasting (2019, methodology): “The core of these methods is formed by comparatively simple (often linear) models, which require manual feature engineering and model design by domain experts to achieve good performance (Harvey, 1990).”
Nowcasting GDP in Real Time: A Density Combination Approach (2014, unknown): “We refer to Harvey (1990) for the technical details.”
Effects of Word-of-Mouth versus Traditional Marketing: Findings from an Internet Social Networking Site (2009, methodology): “We estimate this model using Kalman filter recursions (Harvey 1991).”
Non-Gaussian OU based models and some of their uses in financial economics (2000, unknown): “For related ideas, in the context of discrete time log-normal SV models, see Harvey, Ruiz, and Shephard (1994) and Harvey and Shephard (1996) where a linear state space form is constructed for log y n.”
No-Arbitrage Taylor Rules (2007, unknown): “We use a Kalman filter algorithm that includes time-varying exogenous variables in the state equation following Harvey (1989).”
Predicting the present with Bayesian structural time series (2014, methodology): “Our system uses a structural time series model (Harvey, 1989) to capture the trend, seasonal, and similar components of the target series.”
Predictive Regressions: A Present-Value Approach (2010, unknown): “17See also Harvey (1989).”
Mixed Effects Models and Extensions in Ecology with R (2009, methodology): “This is also called intervention analysis (Harvey, 1989; Zuur et al., 2007).”
Risk management based on stochastic volatility (2003, methodology): “Therefore, the simplifying assumption concerns ( , , , ,( ) , , , , , , V l y y V t t s s t T ϕ γ ϕ γ ϑ a K = − ) ∑ 1 1 it is hard to y s ) s =1 –1 γ , ϑ ) Shiryaev, 1995, Theorem VI.7.1, or Harvey, 1989, Section 3.”
Dynamic Factor Models, Factor-Augmented Vector Autoregressions, and Structural Vector Autoregressions in Macroeconomics (2016, methodology): “2 compares the biweight filter to three other filters that could be used to estimate the low-frequency trend: an equal-weighted moving average filter with 40 leads and lags (ie, an 81-quarter centered moving average), the Hodrick and Prescott (1997) filter with the conventional quarterly tuning para”