Detecting structural breaks in seasonal time series by regularized optimization

Wang, Bing; Sun, Jie; Motter, Adilson E.

doi:10.1201/b16387-524

Cited by 5 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, temporal stationarity assumptions are often violated in real-world applications. It is therefore of critical importance to divide the observed time series data into stationary segments [77], allowing for the inference of causal networks that are time-dependent [45]. Finally, information causality suggests physical causality, but they are not necessarily equivalent [33,53].…”

Section: Discussionmentioning

confidence: 99%

Causal Network Inference by Optimal Causation Entropy

Sun

Taylor²,

Bollt

2015

SIAM J. Appl. Dyn. Syst.

Self Cite

175

193

View full text Add to dashboard Cite

Abstract. The broad abundance of time series data, which is in sharp contrast to limited knowledge of the underlying network dynamic processes that produce such observations, calls for a rigorous and efficient method of causal network inference. Here we develop mathematical theory of causation entropy, an information-theoretic statistic designed for model-free causality inference. For stationary Markov processes, we prove that for a given node in the network, its causal parents forms the minimal set of nodes that maximizes causation entropy, a result we refer to as the optimal causation entropy principle. Furthermore, this principle guides us to develop computational and data efficient algorithms for causal network inference based on a two-step discovery and removal algorithm for time series data for a network-couple dynamical system. Validation in terms of analytical and numerical results for Gaussian processes on large random networks highlight that inference by our algorithm outperforms previous leading methods including conditioned Granger causality and transfer entropy. Interestingly, our numerical results suggest that the number of samples required for accurate inference depends strongly on network characteristics such as the density of links and information diffusion rate and not necessarily on the number of nodes.

show abstract

Section: Discussionmentioning

confidence: 99%

Causal Network Inference by Optimal Causation Entropy

Sun

Taylor²,

Bollt

2015

SIAM J. Appl. Dyn. Syst.

Self Cite

175

193

View full text Add to dashboard Cite

show abstract

“…These are known as structural breaks and are points in time at which statistical patterns change. According to Wang et al (2014), the structural breaks on data series should not be ignored as they highlight those sections of the time horizon…”

Section: Trend Analysismentioning

confidence: 99%

Time series analysis of data for sea surface temperature and upwelling components from the southwest coast of Portugal

Goela

Cordeiro

Danchenko

et al. 2016

Journal of Marine Systems

View full text Add to dashboard Cite

Time series analysis of data for sea surface temperature and upwelling components from the southwest coast of AbstractThis study relates sea surface temperature (SST) to the upwelling conditions off the southwest coast of Portugal using statistical analyses of publically available data.Optimum Interpolation (OI) daily SST data were extracted from the United States (US) National Oceanic and Atmospheric Administration (NOAA) and data for wind speed and direction were from the US National Climatic Data Center. Time series were extracted at a daily frequency for a time horizon of 26 years. Upwelling indices were estimated using westerly (Q x ) and southerly (Q y ) Ekman transport components.In the first part of the study, time series were inspected for trend and seasonality over the whole period. The seasonally adjusted time series revealed an increasing slope for SST (0.15ºC per decade) and decreasing slopes for Q x (-84.01 m 3 .s -1 .km -1 per decade) and Q y (-25.20 m 3 .s -1 .km -1 per decade), over the time horizon. Structural breaks analysis applied to the time series showed that a statistically significant incremental increase in SST was more pronounced during the last decade. Cross-correlation between upwelling indices and SST revealed a time delay of 5 and 2 days between Q x and SST, and between Q y and SST, respectively. A spectral analysis combined with the previous analysis enabled the identification of four oceanographic seasons. Those seasons were later recognised over a restricted time period of 4 years, between 2008 and 2012; when there was an extensive sampling programme for the validation of ocean colour remote sensing imagery. The seasons were defined as: summer, with intense and regular events of upwelling; autumn, indicating relaxation of upwelling conditions; and spring and winter, showing high interannual variability in terms of number and intensity of upwelling events.

show abstract

“…Many studies use weekly (or monthly) data to detect structural breaks to distinguish structural breaks from spikes. For instance, Wang et al (2015) use monthly data from fisheries to detect structural breaks. Harvey and Lange (2018) use weekly prices on several stock markets to analyze volatility.…”

Section: Data and Descriptive Statisticsmentioning

confidence: 99%

Renewable energy regulation and structural breaks: An empirical analysis of Spanish electricity price volatility

2020

View full text Add to dashboard Cite

International experience proves that electricity prices have undergone major changes in volatility since the entry of green technologies. The intermittency of renewable sources is one of the reasons for these changes, as it leads to higher volatility in periods of higher participation by renewables. We argue that the development of the regulatory system promoting renewable electricity also plays a crucial role. We raise a question that deserves attention: could an incentive scheme induce higher share of renewables and lower volatility simultaneously? In this paper, we conduct an empirical analysis with Spanish data. We analyze possible ensuing structural changes in Spanish electricity spot price volatility from January 2002 to December 2017. We identify two structural breaks linked to important measures related to renewable electricity: (i) the abolishment of the feed-in tariff scheme; and (ii) the establishment of a more market-oriented regulation based on investment and operating costs. We conclude that stable regulatory policies reduce volatility even though the presence of renewable sources is greater. Furthermore, market-based policy measures achieve lower volatility, encouraging good integration of intermittent renewable electricity.

show abstract

Detecting structural breaks in seasonal time series by regularized optimization

Cited by 5 publications

References 22 publications

Causal Network Inference by Optimal Causation Entropy

Causal Network Inference by Optimal Causation Entropy

Time series analysis of data for sea surface temperature and upwelling components from the southwest coast of Portugal

Renewable energy regulation and structural breaks: An empirical analysis of Spanish electricity price volatility

Contact Info

Product

Resources

About