Time series econometrics is a rapidly evolving field. Particularly, the cointegration revolution has had a substantial impact on applied analysis. Hence, no textbook has managed to cover the full ...range of methods in current use and explain how to proceed in applied domains. This gap in the literature motivates the present volume. The methods are sketched out, reminding the reader of the ideas underlying them and giving sufficient background for empirical work. The treatment can also be used as a textbook for a course on applied time series econometrics. Topics include: unit root and cointegration analysis, structural vector autoregressions, conditional heteroskedasticity and nonlinear and nonparametric time series models. Crucial to empirical work is the software that is available for analysis. New methodology is typically only gradually incorporated into existing software packages. Therefore a flexible Java interface has been created, allowing readers to replicate the applications and conduct their own analyses.
The aim of ITISE 2022 is to create a friendly environment that could lead to the establishment or strengthening of scientific collaborations and exchanges among attendees. Therefore, ITISE 2022 is ...soliciting high-quality original research papers (including significant works-in-progress) on any aspect time series analysis and forecasting, in order to motivating the generation and use of new knowledge, computational techniques and methods on forecasting in a wide range of fields.
Recently, Transformers and MLPs based models have dominated and made significant progress in time series analysis. However, these methods struggle to capture the complete periodic features to model ...the global dependencies of time series. To this end, we provide a new perspective to explore the potential of time series in the frequency domain. Specifically, we propose the DFT-based Amplitude-Phase Decoupling Network (APDNet), which learns the significance changes and periodicity characteristics of time series by decoupling the real and imaginary parts in the complex frequency domain. First, we propose the Fourier Temporal/Variable Interaction Module to model time dependency and dependency multiple variables, respectively. Secondly, we innovatively propose the Dimensional Expanded Feature Embedding Module (DEFEM), which expands time series into a higher-dimensional representation space to preserve more independent features. Finally, through extensive experiments on multiple real-world datasets, our APDNet achieves state-of-the-art performance in various tasks such as long-term and short-term forecasting, anomaly detection, imputation, and classification. Code is available at: https://github.com/CodeJester196/APDNet.
Business-Cycle Anatomy Angeletos, George-Marios; Collard, Fabrice; Dellas, Harris
The American economic review,
10/2020, Volume:
110, Issue:
10
Journal Article
Peer reviewed
Open access
We propose a new strategy for dissecting the macroeconomic time series, provide a template for the business-cycle propagation mechanism that best describes the data, and use its properties to ...appraise models of both the parsimonious and the medium-scale variety. Our findings support the existence of a main business-cycle driver but rule out the following candidates for this role: technology or other shocks that map to TFP movements; news about future productivity; and inflationary demand shocks of the textbook type. Models aimed at accommodating demand- driven cycles without a strict reliance on nominal rigidity appear promising.
Randomised controlled trials (RCTs) are considered the gold standard when evaluating the causal effects of healthcare interventions. When RCTs cannot be used (e.g. ethically difficult), the ...interrupted time series (ITS) design is a possible alternative. ITS is one of the strongest quasi-experimental designs. The aim of this methodological study was to describe how ITS designs were being used, the design characteristics, and reporting in the healthcare setting.
We searched MEDLINE for reports of ITS designs published in 2015 which had a minimum of two data points collected pre-intervention and one post-intervention. There was no restriction on participants, language of study, or type of outcome. Data were summarised using appropriate summary statistics.
One hundred and sixteen studies were included in the study. Interventions evaluated were mainly programs 41 (35%) and policies 32 (28%). Data were usually collected at monthly intervals, 74 (64%). Of the 115 studies that reported an analysis, the most common method was segmented regression (78%), 55% considered autocorrelation, and only seven reported a sample size calculation. Estimation of intervention effects were reported as change in slope (84%) and change in level (70%) and 21% reported long-term change in levels.
This methodological study identified problems in the reporting of design features and results of ITS studies, and highlights the need for future work in the development of formal reporting guidelines and methodological work.
In this article, we consider the problem of detecting multiple changepoints in large datasets. Our focus is on applications where the number of changepoints will increase as we collect more data: for ...example, in genetics as we analyze larger regions of the genome, or in finance as we observe time series over longer periods. We consider the common approach of detecting changepoints through minimizing a cost function over possible numbers and locations of changepoints. This includes several established procedures for detecting changing points, such as penalized likelihood and minimum description length. We introduce a new method for finding the minimum of such cost functions and hence the optimal number and location of changepoints that has a computational cost, which, under mild conditions, is linear in the number of observations. This compares favorably with existing methods for the same problem whose computational cost can be quadratic or even cubic. In simulation studies, we show that our new method can be orders of magnitude faster than these alternative exact methods. We also compare with the binary segmentation algorithm for identifying changepoints, showing that the exactness of our approach can lead to substantial improvements in the accuracy of the inferred segmentation of the data. This article has supplementary materials available online.
An innovations state space modeling framework is introduced for forecasting complex seasonal time series such as those with multiple seasonal periods, high-frequency seasonality, non-integer ...seasonality, and dual-calendar effects. The new framework incorporates Box-Cox transformations, Fourier representations with time varying coefficients, and ARMA error correction. Likelihood evaluation and analytical expressions for point forecasts and interval predictions under the assumption of Gaussian errors are derived, leading to a simple, comprehensive approach to forecasting complex seasonal time series. A key feature of the framework is that it relies on a new method that greatly reduces the computational burden in the maximum likelihood estimation. The modeling framework is useful for a broad range of applications, its versatility being illustrated in three empirical studies. In addition, the proposed trigonometric formulation is presented as a means of decomposing complex seasonal time series, and it is shown that this decomposition leads to the identification and extraction of seasonal components which are otherwise not apparent in the time series plot itself.
We review the results of six forecasting competitions based on the online data science platform Kaggle, which have been largely overlooked by the forecasting community. In contrast to the M ...competitions, the competitions reviewed in this study feature daily and weekly time series with exogenous variables, business hierarchy information, or both. Furthermore, the Kaggle data sets all exhibit higher entropy than the M3 and M4 competitions, and they are intermittent.
In this review, we confirm the conclusion of the M4 competition that ensemble models using cross-learning tend to outperform local time series models and that gradient boosted decision trees and neural networks are strong forecast methods. Moreover, we present insights regarding the use of external information and validation strategies, and discuss the impacts of data characteristics on the choice of statistics or machine learning methods. Based on these insights, we construct nine ex-ante hypotheses for the outcome of the M5 competition to allow empirical validation of our findings.
Time series segmentation, which is also known as multiple‐change‐point detection, is a well‐established problem. However, few solutions have been designed specifically for high dimensional ...situations. Our interest is in segmenting the second‐order structure of a high dimensional time series. In a generic step of a binary segmentation algorithm for multivariate time series, one natural solution is to combine cumulative sum statistics obtained from local periodograms and cross‐periodograms of the components of the input time series. However, the standard ‘maximum’ and ‘average’ methods for doing so often fail in high dimensions when, for example, the change points are sparse across the panel or the cumulative sum statistics are spuriously large. We propose the sparsified binary segmentation algorithm which aggregates the cumulative sum statistics by adding only those that pass a certain threshold. This ‘sparsifying’ step reduces the influence of irrelevant noisy contributions, which is particularly beneficial in high dimensions. To show the consistency of sparsified binary segmentation, we introduce the multivariate locally stationary wavelet model for time series, which is a separate contribution of this work.
Probabilistic forecasting, i.e., estimating a time series’ future probability distribution given its past, is a key enabler for optimizing business processes. In retail businesses, for example, ...probabilistic demand forecasts are crucial for having the right inventory available at the right time and in the right place. This paper proposes DeepAR, a methodology for producing accurate probabilistic forecasts, based on training an autoregressive recurrent neural network model on a large number of related time series. We demonstrate how the application of deep learning techniques to forecasting can overcome many of the challenges that are faced by widely-used classical approaches to the problem. By means of extensive empirical evaluations on several real-world forecasting datasets, we show that our methodology produces more accurate forecasts than other state-of-the-art methods, while requiring minimal manual work.
PDF
