A comprehensive causality test based on the singular spectrum analysis

Hassani, Hossein; Zhigljavsky, Anatoly; Patterson, Kerry; Soofi, Abdol S.

doi:10.1093/acprof:oso/9780199574131.003.0018

Cited by 24 publications

(26 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latter has been applied to test for nonlinear causality between energy and output (Chiou-Wei et al, 2008) but is not applicable to non-stationary data and has several other shortcomings (Hassani et al, 2010). Chiou-Wei et al (2008) difference their data in order to apply the test, but this throws away the information on the long-run relationship between the variables.…”

Section: Granger Causality Testingmentioning

confidence: 99%

“…Chiou-Wei et al (2008) difference their data in order to apply the test, but this throws away the information on the long-run relationship between the variables. Hassani et al (2010) present a method based on singular spectrum analysis that they claim can cope with non-stationary series. Another kernel-based approach is developed by Sun (2008).…”

Section: Granger Causality Testingmentioning

confidence: 99%

See 1 more Smart Citation

Causality between energy and output in the long-run

Stern

Enflo

2013

Energy Economics

View full text Add to dashboard Cite

Abstract:Though there is a very large literature examining whether energy use Granger causes economic output or vice versa this literature is fairly inconclusive. Almost all existing studies use relatively short time series or panels with a relatively small time dimension. Additionally, many recent papers continue to use what seem to be misspecified models. We apply Granger causality and cointegration techniques to a Swedish time series data set on energy and economic growth spanning 150 years to test whether increases in energy use and energy quality have driven economic growth. We show that these techniques are very sensitive to variable definition, choice of additional variables in the model, and sample periods. All of the following appear to make a finding that energy causes growth more likely: using multivariate models, defining variables to better reflect their theoretical definition, using larger samples, and including appropriate structural breaks. However, it is also possible that the relationship between energy and growth has changed over time and that results from recent smaller samples reflect this. Energy prices have a significant causal impact on both energy use and output.

show abstract

Section: Granger Causality Testingmentioning

confidence: 99%

Section: Granger Causality Testingmentioning

confidence: 99%

Causality between energy and output in the long-run

Stern

Enflo

2013

Energy Economics

View full text Add to dashboard Cite

show abstract

“…Generally, in the standard or basic SSA, almost all of the current studies suggested the window length should be larger but not greater than half of the time series length to achieve better separately of trend and residual. This means that if the length of the time series is , then the window length for the lagged vectors in time series embedding is about 2 ≤ ≤ /2 [13,25,26,31,36]. As the window length is an integer, thus there are many satisfied values of as the tuning parameter that can be used to cover the time series embedding.…”

Section: Related Workmentioning

confidence: 99%

“…Given a one-dimensional time series data = ( 1 , 2 , … , ) with 1 ≤ ≤ of length . Let = ( , +1 , … , + −1 ) is a sub-series vector of with 1 < < , 1 ≤ ≤ , and = − + 1 [25,31]. The window length is an integer between 1 and .…”

Section: Time Series Embeddingmentioning

confidence: 99%

See 1 more Smart Citation

Stock Price Forecasting Using Univariate Singular Spectral Analysis through Hadamard Transform

Syukur¹,

Marjuni²

2020

IJIES

View full text Add to dashboard Cite

The stock price prediction or forecasting is one of the important information in the stock market. Investors need stock price information before buying shares, while shareholders need stock price information for selling shares. There are many stock price prediction techniques have been proposed in the time series analysis. One of the simplest and powerful techniques is singular spectrum analysis, which works on the time series decomposition that is constructed using sub-series or window of the initial time series. However, choosing the exact window length is not easy because it depends on the time series characteristics. In this paper, the Hadamard transform of time series is proposed as an alternative technique to choose the window length in time series embedding. Technically, the length of the window for time series embedding is determined directly based on the size of the Hadamard spectrum. The experimental results show that the proposed method not only facilitates the determination of window length in time series embedding but can also improve the performance of the standard singular spectrum analysis method. The error rates of the proposed and the baseline methods (the standard singular spectrum analysis and the standard singular spectrum analysis with minimum description length) are 0.0088, 0.0194, and 0.1441, respectively.

show abstract

Forecasting UK Industrial Production with Multivariate Singular Spectrum Analysis

Hassani

Heravi

Zhigljavsky

2012

Journal of Forecasting

Self Cite

View full text Add to dashboard Cite

In recent years the singular spectrum analysis (SSA) technique has been further developed and applied to many practical problems. The aim of this research is to extend and apply the SSA method, using the UK Industrial Production series. The performance of the SSA and multivariate SSA (MSSA) techniques was assessed by applying it to eight series measuring the monthly seasonally unadjusted industrial production for the main sectors of the UK economy. The results are compared with those obtained using the autoregressive integrated moving average and vector autoregressive models.We also develop the concept of causal relationship between two time series based on the SSA techniques. We introduce several criteria which characterize this causality. The criteria and tests are based on the forecasting accuracy and predictability of the direction of change. The proposed tests are then applied and examined using the UK industrial production series. Copyright © 2012 John Wiley & Sons, Ltd.

show abstract

A comprehensive causality test based on the singular spectrum analysis

Cited by 24 publications

References 35 publications

Causality between energy and output in the long-run

Causality between energy and output in the long-run

Stock Price Forecasting Using Univariate Singular Spectral Analysis through Hadamard Transform

Forecasting UK Industrial Production with Multivariate Singular Spectrum Analysis

Contact Info

Product

Resources

About