Research Topic · Peer-Reviewed

Time Series Analysis

Time series analysis is the body of statistical and computational methods for studying data observed sequentially over time, with the aim of characterising temporal structure and forecasting future values. Its defining feature is that observations are ordered and typically correlated, so analysis explicitly models d…

Curated from this journal's research 📚 5 peer-reviewed articles cited Cited 107× across the literature 🔖 ISSN 2643-2811 🗓 Reviewed June 2026

Overview

Time series analysis is the body of statistical and computational methods for studying data observed sequentially over time, with the aim of characterising temporal structure and forecasting future values. Its defining feature is that observations are ordered and typically correlated, so analysis explicitly models dependence between successive points rather than treating them as independent. Standard tasks include decomposing a series into trend, seasonal, cyclical, and irregular components, testing for stationarity, and quantifying autocorrelation. A central modelling framework is the autoregressive integrated moving average family, including seasonal ARIMA models, which represent a series in terms of its own past values, past errors, and differencing to achieve stationarity; related approaches include exponential smoothing, dynamic harmonic regression with Fourier terms, and state-space and machine-learning models. These methods are applied to forecasting and surveillance across economics, environmental monitoring, and especially epidemiology, where they have been used to model and predict the progression of disease outbreaks and to inform prevention and control. Beyond prediction, time series analysis supports anomaly detection, intervention assessment, and the study of underlying dynamics in physiological, ecological, and remotely sensed measurements. Effective application depends on appropriate preprocessing, model identification and diagnostics, validation on held-out data, and quantification of forecast uncertainty, making it a core analytical tool in model-based and data-driven research.

Research published in this journal

5 peer-reviewed articles, ranked by relevance. Each links to its DOI.

How this research is being cited

The 5 articles above have been cited 107 times in the scholarly literature. Citation data via OpenAlex and Crossref, updated Jun 2026.

A sample of recent works citing this journal's research on Time Series Analysis, linking to each citing work.

Editorial oversight

Curated from peer-reviewed research published in Model Based Research (ISSN 2643-2811).

Journal editorial board
Yoshiaki Kikuchi · Japan Yung-Yao Chen · Taiwan Yang Chen · United States

This page summarises published research for orientation; it is not medical or professional advice.