Change Point Detection Using Penalized Multidegree Splines

We consider a function estimation method with change point detection using truncated power spline basis and elastic-net-type L1-norm penalty. The L1-norm penalty controls the jump detection and smoothness depending on the value of the parameter. In terms of the proposed estimators, we introduce two computational algorithms for the Lagrangian dual problem (coordinate descent algorithm) and constrained convex optimization problem (an algorithm based on quadratic programming). Subsequently, we investigate the relationship between the two algorithms and compare them. Using both simulation and real data analysis, numerical studies are conducted to validate the performance of the proposed method.

Realized Multi-Power Variation Process for Jump Detection in the Nigerian All Share Index

In this paper, we studied the particular cases of higher-order realized multipower variation process, their asymptotic properties comprising the probability limits and limit distributions were highlighted. The respective asymptotic variances of the limit distributions were obtained and jump detection models were developed from the asymptotic results. The models were obtained from the particular cases of the higher-order of the realized multipower variation process, in a class of continuous stochastic volatility semimartingale process. These are extensions of the method of jump detection by Barndorff-Nielsen and Shephard (2006), for large discrete data. An Empirical Application of the models to the Nigerian All Share Index (NASI) data shows that the models are robust to jumps and suggest that stochastic models with added jump components will give a better representation of the NASI price process.

A New Approach to Detection of Changes in Multidimensional Patterns

In the paper we develop an algorithm based on the Parzen kernel estimate for detection of sudden changes in 3-dimensional shapes which happen along the edge curves. Such problems commonly arise in various areas of computer vision, e.g., in edge detection, bioinformatics and processing of satellite imagery. In many engineering problems abrupt change detection may help in fault protection e.g. the jump detection in functions describing the static and dynamic properties of the objects in mechanical systems. We developed an algorithm for detecting abrupt changes which is nonparametric in nature and utilizes Parzen regression estimates of multivariate functions and their derivatives. In tests we apply this method, particularly but not exclusively, to the functions of two variables.

Pre-treating GNSS time series using a recurrent neural network to improve the automated detection of jump discontinuities

<p>Ground motion monitoring is one of the main goals in the geoscientist community and at the time it is mainly performed by analyzing time series of data. Our capability of describing the most significant features characterizing the time evolution of a point-position is affected by the presence of undetected discontinuities in the time series. One of the most critical aspects in the automated time series analysis, which is quite necessary since the amount of data is increasing more and more, is still the detection of discontinuities and in particular the definition of their epoch. A number of algorithms have already been developed and proposed to the community in the last years, following different statistical approaches and different hypotheses on the coordinates behavior. In this work, we have chosen to analyze GNSS time series and to use an already published algorithm (STARS) for jump detection as a benchmark to test our approach, consisting of pre-treating the time series to be analyzed using a neural network. In particular, we chose a Long Short Term Memory (LSTM) neural network belonging to the class of the Recurrent Neural Networks (RNNs), ad hoc modified for the GNSS time series analysis. We focused both on the training algorithm and the testing one. The latter has been the object of a parametric test to find out the number of predicted data that mostly emphasize our capability of detecting jump discontinuities. Results will be presented considering several GNSS time series of daily positions. Finally, a discussion on the possible integration of machine learning approaches and classical deterministic approaches will be done.</p>

The Impact of Forecasting Jumps on Forecasting Electricity Prices

The paper is devoted to forecasting hourly day-ahead electricity prices from the perspective of the existence of jumps. We compare the results of different jump detection techniques and identify common features of electricity price jumps. We apply the jump-diffusion model with a double exponential distribution of jump sizes and explanatory variables. In order to improve the accuracy of electricity price forecasts, we take into account the time-varying intensity of price jump occurrences. We forecast moments of jump occurrences depending on several factors, including seasonality and weather conditions, by means of the generalised ordered logit model. The study is conducted on the basis of data from the Nord Pool power market. The empirical results indicate that the model with the time-varying intensity of jumps and a mechanism of jump prediction is useful in forecasting electricity prices for peak hours, i.e., including the probabilities of downward, no or upward jump occurrences into the model improves the forecasts of electricity prices.

Change Detection within Remotely Sensed Satellite Image Time Series via Spectral Analysis

Jump or break detection within a non-stationary time series is a crucial and challenging problem in a broad range of applications including environmental monitoring. Remotely sensed time series are not only non-stationary and unequally spaced (irregularly sampled) but also noisy due to atmospheric effects, such as clouds, haze, and smoke. To address this challenge, a robust method of jump detection is proposed based on the Anti-Leakage Least-Squares Spectral Analysis (ALLSSA) along with an appropriate temporal segmentation. This method, namely, Jumps Upon Spectrum and Trend (JUST), can simultaneously search for trends and statistically significant spectral components of each time series segment to identify the potential jumps by considering appropriate weights associated with the time series. JUST is successfully applied to simulated vegetation time series with varying jump location and magnitude, the number of observations, seasonal component, and noises. Using a collection of simulated and real-world vegetation time series in southeastern Australia, it is shown that JUST performs better than Breaks For Additive Seasonal and Trend (BFAST) in identifying jumps within the trend component of time series with various types. Furthermore, JUST is applied to Landsat 8 composites for a forested region in California, U.S., to show its potential in characterizing spatial and temporal changes in a forested landscape. Therefore, JUST is recommended as a robust and alternative change detection method which can consider the observational uncertainties and does not require any interpolations and/or gap fillings.

Intraday Jumps, Liquidity, and U.S. Macroeconomic News: Evidence from Exchange Traded Funds

This paper uses two highly liquid S&P 500 and gold exchange-traded funds (ETFs) to evaluate the impact of liquidity and macroeconomic news surprises on the frequency of observing intraday jumps. It explicitly addresses market microstructure noise-induced biases in realized estimators used in jump detection tests and applies non-parametric intraday jump detection tests. The results show a significant increase in trading costs and elevated levels of information asymmetry before observing jumps. Depth, resiliency, and trading activity are associated with the frequency of observing intraday jumps and cojumps. The ability of liquidity variables to predict intraday jumps persists after controlling for news surprises. Results show that intraday jump realizations affect the price discovery of ETFs.