A Flexible Mixed-Frequency Vector Autoregression with a Steady-State Prior

Ankargren, Sebastian; Unosson, Måns; Yang, Yukai

doi:10.1515/jtse-2018-0034

Cited by 10 publications

(8 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the VAR (1) form is more convenient for analytical derivations and allows more compact statements. This is explained also, graphically, Figure (8,9), since the maximum lag for VAR (1) is 11. This means that 11-th order VAR refers to a VAR model which includes lags for the last 11 time periods.…”

Section: Stationarity Process Of Time Series Datamentioning

confidence: 60%

“…Eraker et al [7] formulated a Bayesian VAR based on this idea and Schorfheide and Song [6] proceeded with a Gibbs sampling approach based on simulation smoothing and forward-filtering, backward-smoothing along the lines of Carter and Kohn [8] . Ankargren et al [9] developed a steady-state mixedfrequency VAR model for a real-time US dataset. This paper is organized as following: Section 2 presents some algorithms and packages that are used in this paper.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting EGX30 index time series using vector autoregressive models VARS

El-Sayed¹

2021

Int. J. Stat. Appl. Math.

View full text Add to dashboard Cite

Time series analysis is considered one of the most important analysis processes at the present time, especially if it is a multivariate analysis. This analysis helps the decision maker in making his future decision based on the behavior of a phenomenon in the past. This is done for many economic, financial, engineering, medical, and other important fields. So we were keen in this article to address a multivariate time series using the vector autoregressive models analysis of the practical time series This analysis is also used in the process of forecasting the future of multiple time series. Three packages from the R program, are used for numerical analysis these data, that are "vars", "MTS(VAR)", and "forecast" packages. For these data ARIMA (0,1,0) model is the best model for non-stationary time series, but the best model is ARIMA(0,0,0) with zero mean for stationary time series. VAR(1) model is better than VAR(2) model for analyzing the data. Also, VAR(1) model is better than VAR(2) model for identifying the Lags order. Comparing between VAR(p) and VARS(p), we found that the VAR(p) model order is better than the VARS(p) model order for identifying lag order. The significance predictor time series is Institutional investor, the other predictors are non-significance. No serial correlation in error terms. The Institutional investor and Trade values time series are useful for forecasting other time series. Only the Exchange rate time series has instantaneous causality between it and other time series. Finally, A five forecasts values of all stationary time series, using VARS(1) models, are predicted.

show abstract

Section: Stationarity Process Of Time Series Datamentioning

confidence: 60%

Section: Introductionmentioning

confidence: 99%

Forecasting EGX30 index time series using vector autoregressive models VARS

El-Sayed¹

2021

Int. J. Stat. Appl. Math.

View full text Add to dashboard Cite

show abstract

“…The merits of the mixed-frequency VARs in nowcasting and forecasting have been demonstrated by e.g. Schorfheide and Song (2015); Eraker et al (2015); Ankargren et al (2018); Götz and Hauzenberger (2018). These papers frame the problem as a latent variable problem, where the low-frequency series have an underlying, high-frequency series which we do not observe.…”

Section: Introductionmentioning

confidence: 76%

“…To model data observed at mixed frequencies we follow Schorfheide and Song (2015); Ankargren et al (2018); Götz and Hauzenberger (2018) and deal with the problem by postulating a VAR model at the high frequency. That is, we start with the VAR(p) given by…”

Section: Mixed-frequency Varsmentioning

confidence: 99%

Simulation smoothing for nowcasting with large mixed-frequency VARs

Ankargren¹,

Jonéus²

2019

Preprint

Self Cite

View full text Add to dashboard Cite

There is currently an increasing interest in large vector autoregressive (VAR) models. VARs are popular tools for macroeconomic forecasting and use of larger models has been demonstrated to often improve the forecasting ability compared to more traditional small-scale models. Mixed-frequency VARs deal with data sampled at different frequencies while remaining within the realms of VARs. Estimation of mixed-frequency VARs makes use of simulation smoothing, but using the standard procedure these models quickly become prohibitive in nowcasting situations as the size of the model grows.We propose two algorithms that alleviate the computational efficiency of the simulation smoothing algorithm. Our preferred choice is an adaptive algorithm, which augments the state vector as necessary to sample also monthly variables that are missing at the end of the sample. For large VARs, we find considerable improvements in speed using our adaptive algorithm. The algorithm therefore provides a crucial building block for bringing the mixed-frequency VARs to the high-dimensional regime.

show abstract

“…Following Schorfheide and Song (2015), Sebastian et al (2020), and Ankargren and Yang (2019), BVARM's state-space form transition equation, which is the companion form of the VAR(p) process, and the measurement equation are shown as, respectively:…”

Section: Bayesian Vector Ar Modelmentioning

confidence: 99%

Big data financial transactions and GDP nowcasting: The case of Turkey

Barlas,

Mert,

Isa

et al. 2023

Journal of Forecasting

View full text Add to dashboard Cite

We use aggregated information from individual‐to‐firm and firm‐to‐firm transactions from the Garanti BBVA Bank to simulate domestic private demand and estimate aggregate consumption and investment for Turkey's quarterly national accounts in real time. We show that these big data variables successfully nowcast official consumption and investment flows. To further validate the usefulness of these indicators, we include both indicators among others which are generally used in gross domestic product (GDP) nowcasting and evaluate their contribution to nowcasting power of Turkish GDP by combining both linear and nonlinear models. The results are successful and confirm the usefulness of consumption and investment banking transactions for nowcasting purposes. These big data are valuable, especially at the beginning of the nowcasting process, when the traditional hard data are scarce. Accordingly, this information is especially relevant for countries with longer statistical release lags, such as emerging markets.

show abstract

A Flexible Mixed-Frequency Vector Autoregression with a Steady-State Prior

Cited by 10 publications

References 59 publications

Forecasting EGX30 index time series using vector autoregressive models VARS

Forecasting EGX30 index time series using vector autoregressive models VARS

Simulation smoothing for nowcasting with large mixed-frequency VARs

Big data financial transactions and GDP nowcasting: The case of Turkey

Contact Info

Product

Resources

About