High-dimensional conditionally Gaussian state space models with missing data
From MaRDI portal
Publication:6175545
Abstract: We develop an efficient sampling approach for handling complex missing data patterns and a large number of missing observations in conditionally Gaussian state space models. Two important examples are dynamic factor models with unbalanced datasets and large Bayesian VARs with variables in multiple frequencies. A key insight underlying the proposed approach is that the joint distribution of the missing data conditional on the observed data is Gaussian. Moreover, the inverse covariance or precision matrix of this conditional distribution is sparse, and this special structure can be exploited to substantially speed up computations. We illustrate the methodology using two empirical applications. The first application combines quarterly, monthly and weekly data using a large Bayesian VAR to produce weekly GDP estimates. In the second application, we extract latent factors from unbalanced datasets involving over a hundred monthly variables via a dynamic factor model with stochastic volatility.
Cites work
- A note on implementing the Durbin and Koopman simulation smoother
- A simple and efficient simulation smoother for state space time series analysis
- Bayesian analysis of moving average stochastic volatility models: modeling in-mean effects and leverage for financial time series
- Bayesian estimation of sparse dynamic factor models with order-independent and ex-post mode identification
- Comparing stochastic volatility specifications for large Bayesian VARs
- Corrigendum to ``Large Bayesian vector autoregressions with stochastic volatility and non-conjugate priors
- Determining the Number of Factors in Approximate Factor Models
- Dividend suspensions and cash flows during the Covid-19 pandemic: a dynamic econometric model
- Efficient simulation and integrated likelihood estimation in state space models
- Fast sampling of Gaussian Markov random fields
- Fast simulation of hyperplane-truncated multivariate normal distributions
- Forecasting and conditional projection using realistic prior distributions
- Gaussian Markov Random Fields
- Inference in Semiparametric Dynamic Models for Binary Longitudinal Data
- Large Bayesian VARMAs
- Large Bayesian vector autoregressions with stochastic volatility and non-conjugate priors
- Matrix Completion, Counterfactuals, and Factor Analysis of Missing Data
- Moving average stochastic volatility models with application to inflation forecast
- On Gibbs sampling for state space models
- Real-time density forecasts from Bayesian vector autoregressions with stochastic volatility
- Reconciling output gaps: unobserved components model and Hodrick-Prescott filter
- Simulation smoothing for state-space models: a computational efficiency analysis
- Sparse Bayesian time-varying covariance estimation in many dimensions
- Statistical analysis with missing data
- Time Varying Structural Vector Autoregressions and Monetary Policy
Cited in
(4)- Bayesian mixed-frequency quantile vector autoregression: eliciting tail risks of monthly US GDP
- Precision-based sampling for state space models that have no measurement error
- Advances in nowcasting economic activity: the role of heterogeneous dynamics and fat tails
- Large Bayesian SVARs with linear restrictions
This page was built for publication: High-dimensional conditionally Gaussian state space models with missing data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6175545)
