Granger Causality on forward and Reversed Time Series
In this study, the information flow time arrow is investigated for stochastic data defined by vector autoregressive models. The time series are analyzed forward and backward by different Granger causality detection methods. Besides the normal distribution, which is usually required for the validity...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/4/409 |
| _version_ | 1797539470436728832 |
|---|---|
| author | Martina Chvosteková Jozef Jakubík Anna Krakovská |
| author_facet | Martina Chvosteková Jozef Jakubík Anna Krakovská |
| author_sort | Martina Chvosteková |
| collection | DOAJ |
| description | In this study, the information flow time arrow is investigated for stochastic data defined by vector autoregressive models. The time series are analyzed forward and backward by different Granger causality detection methods. Besides the normal distribution, which is usually required for the validity of Granger causality analysis, several other distributions of predictive errors are considered. A clear effect of a change in the order of cause and effect on the time-reversed series of unidirectionally connected variables was detected with standard Granger causality test (GC), when the product of the connection strength and the ratio of the predictive errors of the driver and the recipient was below a certain level, otherwise bidirectional causal connection was detected. On the other hand, opposite causal link was detected unconditionally by the methods based on the time reversal testing, but they were not able to detect correct bidirectional connection. The usefulness of the backward analysis is manifested in cases where falsely detected unidirectional connections can be rejected by applying the result obtained after the time reversal, and in cases of uncorrelated causally independent variables, where the absence of a causal link detected by GC on the original series should be confirmed on the time-reversed series. |
| first_indexed | 2024-03-10T12:46:24Z |
| format | Article |
| id | doaj.art-505b3ff8c41a408ea614ab8429a8ecc7 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T12:46:24Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-505b3ff8c41a408ea614ab8429a8ecc72023-11-21T13:27:19ZengMDPI AGEntropy1099-43002021-03-0123440910.3390/e23040409Granger Causality on forward and Reversed Time SeriesMartina Chvosteková0Jozef Jakubík1Anna Krakovská2Institute of Measurement Science, Slovak Academy of Sciences, 84104 Bratislava, SlovakiaInstitute of Measurement Science, Slovak Academy of Sciences, 84104 Bratislava, SlovakiaInstitute of Measurement Science, Slovak Academy of Sciences, 84104 Bratislava, SlovakiaIn this study, the information flow time arrow is investigated for stochastic data defined by vector autoregressive models. The time series are analyzed forward and backward by different Granger causality detection methods. Besides the normal distribution, which is usually required for the validity of Granger causality analysis, several other distributions of predictive errors are considered. A clear effect of a change in the order of cause and effect on the time-reversed series of unidirectionally connected variables was detected with standard Granger causality test (GC), when the product of the connection strength and the ratio of the predictive errors of the driver and the recipient was below a certain level, otherwise bidirectional causal connection was detected. On the other hand, opposite causal link was detected unconditionally by the methods based on the time reversal testing, but they were not able to detect correct bidirectional connection. The usefulness of the backward analysis is manifested in cases where falsely detected unidirectional connections can be rejected by applying the result obtained after the time reversal, and in cases of uncorrelated causally independent variables, where the absence of a causal link detected by GC on the original series should be confirmed on the time-reversed series.https://www.mdpi.com/1099-4300/23/4/409time reversalGranger causalitypredictive errorendogeneity |
| spellingShingle | Martina Chvosteková Jozef Jakubík Anna Krakovská Granger Causality on forward and Reversed Time Series Entropy time reversal Granger causality predictive error endogeneity |
| title | Granger Causality on forward and Reversed Time Series |
| title_full | Granger Causality on forward and Reversed Time Series |
| title_fullStr | Granger Causality on forward and Reversed Time Series |
| title_full_unstemmed | Granger Causality on forward and Reversed Time Series |
| title_short | Granger Causality on forward and Reversed Time Series |
| title_sort | granger causality on forward and reversed time series |
| topic | time reversal Granger causality predictive error endogeneity |
| url | https://www.mdpi.com/1099-4300/23/4/409 |
| work_keys_str_mv | AT martinachvostekova grangercausalityonforwardandreversedtimeseries AT jozefjakubik grangercausalityonforwardandreversedtimeseries AT annakrakovska grangercausalityonforwardandreversedtimeseries |