• Corpus ID: 18050741

Algorithms for Unevenly Spaced Time Series : Moving Averages and Other Rolling Operators

@inproceedings{Eckner2015AlgorithmsFU,
  title={Algorithms for Unevenly Spaced Time Series : Moving Averages and Other Rolling Operators},
  author={Andreas Eckner},
  year={2015}
}
This paper describes algorithms for efficiently calculating certain rolling time series operators for unevenly spaced data. In particular, we show how to calculate simple moving averages (SMAs), exponential moving averages (EMAs), and related operators in linear time with respect to the number of observations in a time series. A web appendix provides an implementation of these algorithms in the programming language C and a package (forthcoming) for the statistical software R. 

Figures from this paper

A Framework for the Analysis of Unevenly Spaced Time Series Data

Methods for analyzing and manipulating unevenly spaced time series without a transformation to equally spaced data are presented to avoid the biases and information loss caused by resampling.

Some Properties of Operators for Unevenly Spaced Time SeriesThis paper previously circulated under the title ``A Framework for the Analysis of Unevenly Spaced Time Series Data.`` Based on feedback from readers I have shortened the paper and narrowed the scope

An unevenly spaced time series is a sequence of observation time and value pairs with strictly increasing observation times. This paper examines some properties of such time series and of their

On Moving Averages, Histograms and Time-DependentRates for Online Measurement

A framework for the definition of MAs is proposed and performance criteria, e.g., the concept of memory, is developed that allow to parameterize different methods in a comparable way to simplify design, parametrization, and evaluation of technical control systems.

Data Abstraction for Visualizing Large Time Series

This work proposes a classification framework that defines essential criteria for selecting an abstraction method with an eye to subsequent visualization and support of users' analysis tasks and provides a summary table that can be easily used for selecting suitable abstraction methods.

On the stability of unevenly spaced samples for interpolation and quadrature

It is shown that perturbed equally spaced grids with small α can be used without numerical woes, and a discrete version of the Kadec-1/4 theorem is proved, which states that the nonuniform discrete Fourier transform associated with perturbed nodes has a bounded condition number independent of h, for any α < 1/4.

A Measure of Similarity of Time Series Containing Missing Data Using the Mahalanobis Distance

An approach where the characteristics of the Mahalanobis Distance are made use to inherently accommodate the missing values while finding the best match between two time series is presented.

Unsupervised Anomaly Detection in Sensor Data used for Predictive Maintenance

This thesis provides a literature overview on unsupervised anomaly detection methods suitable for unevenly spaced time series and introduces two new methods for anomaly detection, which are based on the Pattern Anomaly Value (PAV) algorithm proposed by Chen and Zhan (2008).

A Method for Dissolved Gas Forecasting in Power Transformers Using LS-SVM

This research attempts consolidating industry knowledge on the maintenance of power transformers and time series forecasting techniques into a coherent system for the purpose of predictive maintenance ofPower transformers.

Advanced Analytics and Learning on Temporal Data: 4th ECML PKDD Workshop, AALTD 2019, Würzburg, Germany, September 20, 2019, Revised Selected Papers

This paper proposes an outlier detection algorithm for temperature sensor data from jet engine tests, and applies functional depth with respect to the residuals to rank the samples and identify the outliers.

Household electricity demand forecasting: benchmarking state-of-the-art methods

The results indicate that without further refinement the considered advanced state-of-the-art forecasting methods rarely beat corresponding persistence forecasts, and provide an exploration of promising directions for future research.

References

SHOWING 1-10 OF 16 REFERENCES

A Framework for the Analysis of Unevenly Spaced Time Series Data

Methods for analyzing and manipulating unevenly spaced time series without a transformation to equally spaced data are presented to avoid the biases and information loss caused by resampling.

Operators on Inhomogeneous Time Series

We present a toolbox to compute and extract information from inhomogeneous (i.e. unequally spaced) time series. The toolbox contains a large set of operators, mapping from the space of inhomogeneous

Nonlinear Time Series : Nonparametric and Parametric Methods

Although Nonlinear Time Series is the only part of the title to appear on the spine of this new book by Fan and Yao, the word “nonparametric” in the subtitle really deserves top billing. There are

New Introduction to Multiple Time Series Analysis

This reference work and graduate level textbook considers a wide range of models and methods for analyzing and forecasting multiple time series. The models covered include vector autoregressive,

Time Series: Theory and Methods

This paper presents a meta-modelling framework for estimating the mean and the Autocovariance Function of Stationary Time Series using ARMA Models and State-Space Models and Kalman Recursions.

An Introduc-tion to High-Frequency Finance

Non-linear time series. A dynamical system approach

Non-linear least-squares prediction based on non-linear models and case studies and an introduction to dynamical systems.

Introduction to time series and forecasting

A general approach to Time Series Modelling and ModeLLing with ARMA Processes, which describes the development of a Stationary Process in Terms of Infinitely Many Past Values and the Autocorrelation Function.

Time Series Analysis

  • J. Cryer
  • Computer Science
    Encyclopedia of Big Data
  • 2022
We provide a concise overview of time series analysis in the time and frequency domains, with lots of references for further reading.