A simple and efficient simulation smoother for state space time series analysis

By J. Durbin, S. J. Koopman. 2002

626 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Molecular Biology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/a4e2c06d0982b8320e930f960e999315a0c117b5

How researchers see this paper

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

In Control and Systems Engineering

In Molecular Biology

In Signal Processing

Citations in the corpus

Bayesian Tail Risk Interdependence Using Quantile Regression (2015, methodology): “In fact, the missing value interpolation is obtained by running the efficient recursive Kalman filter and smoothing algorithms and represents a byproduct of the Bayesian inferential procedure (see also Durbin and Koopman (2012) and Harvey (1989) for an extensive treatment of missing values using sta”
The Analysis of Stochastic Volatility in the Presence of Daily Realised Measures (2011, methodology): “The simulation smoothing methods of de Jong and Shephard (1995) and Durbin and Koopman (2002) can carry out the simulation of α(s) from the smoothed density p(α|RM ;ψ), for s = 1, . . . , S.”
Likelihood-based Analysis for Dynamic Factor Models (2008, background): “Sargent and Sims (1977) and Geweke (1977) were the first to propose a dynamic factor model.”
Safety, Liquidity, and the Natural Rate of Interest (2017, background): “Edge et al. (2008), Justiniano and Primiceri (2008), Barsky et al.”
Bayesian Nonparametric Modelling of the Return Distribution with Stochastic Volatility (2011, positive): “Kohn 1994; Frühwirth-Schnatter 1994; Durbin and Koopman 2002) leading to faster mixing than single-state algorithms. A problem with this parametrization is that the returns can take values very close to zero or even in some cases zero, leading the transformed values to be largely negative or undefin”
Time varying VARs with inequality restrictions (2011, methodology): “First, the naive researcher may think that a standard algorithm such as that of Durbin and Koopman (2002) can be used, with the added restriction that, if a drawn t violates the inequality restriction, then it can be immediately discarded and new ts can be drawn until one 3Note, though, that Cogley…”
Stochastic volatility with leverage: Fast and efficient likelihood inference (2007, methodology): “Step 2b, the sampling of hn;mjy n; dn; sn; h is simple and is implemented with the help of the Gaussian simulation smoother (Frühwirth-Schnatter, 1994; Carter and Kohn, 1994; de Jong and Shephard, 1995; Durbin and Koopman, 2002).”
Modeling frailty-correlated defaults using many macroeconomic covariates (2011, methodology): “The Gaussian importance density g(θ|y) is chosen for convenience and since it is possible to generate a large number of draws θm from it in a computationally efficient manner using the simulation smoothing algorithms of de Jong and Shephard (1995) and Durbin and Koopman (2002).”
Time Varying Dimension Models (2012, positive): “Carter and Kohn, 1994 or Durbin and Koopman, 2002) could be used. All our models have stochastic volatility and to draw the volatilities and all related parameters we use the algorithm of Section 3 of Kim, Shephard and Chib (1998). The remaining parameters are the error variances in the state equati”
The Stochastic Volatility in Mean Model With Time-Varying Parameters: An Application to Inflation Modeling (2017, methodology): “Hence, a draw from p(γ |y,x,h,Ω) can be obtained either by conventional Kalman filter-based algorithms (e.g., Carter and Kohn, 1994; Durbin and Koopman, 2002) or the more efficient precision sampler (Chan and Jeliazkov, 2009; McCausland, Miller, and Pelletier, 2011); we adopt the latter approach and”
Conditional Forecasts and Scenario Analysis with Vector Autoregressions for Large Cross-Sections (2015, methodology): “ṽ (j) l,t|Ω, l ̸∈ I can be obtained from Zl,t − (C̃ t )l·S̃ (j) t|Ω or, alternatively, a disturbance smoother (see de Jong and Shephard, 1995; Durbin and Koopman, 2002) can be used and the states can be derived indirectly from the disturbances.”
The Multi-State Latent Factor Intensity Model for Credit Rating Transitions (2008, methodology): “Therefore, the simulation smoothing algorithms of de Jong and Shephard (1995) or Durbin and Koopman (2002) can be used to generate conditional samples for ν, denoted as νm for m = 1, . . . ,M .”
Multivariate stochastic volatility (2009, methodology): “–S ample{αt} n=1|θ, {ht} n=1 ,Y n using a simulation smoother for a linear Gaussian state-space model; see de Jong and Shephard (1995) and Durbin and Koopman (2002) .”