Search Results

Time Series Analysis

Andrew J. Connolly, Jacob T. VanderPlas, Alexander Gray, Andrew J. Connolly, Jacob T. VanderPlas, and Alexander Gray

in Statistics, Data Mining, and Machine Learning in Astronomy: A Practical Python Guide for the Analysis of Survey Data

This chapter summarizes the fundamental concepts and tools for analyzing time series data. Time series analysis is a branch of applied mathematics developed mostly in the fields of signal processing ... More

This chapter summarizes the fundamental concepts and tools for analyzing time series data. Time series analysis is a branch of applied mathematics developed mostly in the fields of signal processing and statistics. Contributions to this field, from an astronomical perspective, have predominantly focused on unevenly sampled data, low signal-to-noise data, and heteroscedastic errors. The chapter starts with a brief introduction to the main concepts in time series analysis. It then discusses the main tools from the modeling toolkit for time series analysis. Despite being set in the context of time series, many tools and results are readily applicable in other domains, and for this reason the examples presented will not be strictly limited to time-domain data. Armed with the modeling toolkit, the chapter goes on to discuss the analysis of periodic time series, search for temporally localized signals, and concludes with a brief discussion of stochastic processes.Less

Political Methodology: An Overview

John E. Jackson

in A New Handbook of Political Science

Reviews methodological techniques available across the discipline of political science. Econometrics and political science methods include structural equation estimations, time‐series analysis, and ... More

Reviews methodological techniques available across the discipline of political science. Econometrics and political science methods include structural equation estimations, time‐series analysis, and non‐linear models. Alternative approaches analyse public preferences, political institutions, and path dependence political economy modelling. The drawbacks of these methods are examined by questioning their underlying assumptions and examining their consequences. While there is cause for concern, solace lies in the fact that these problems are also faced across other disciplines.Less

Introduction and Overview

Anindya Banerjee, Juan J. Dolado, John W. Galbraith, and David F. Hendry

in Co-integration, Error Correction, and the Econometric Analysis of Non-Stationary Data

Serves as an introductory overview for the rest of the book, and outlines its main aims. As a basis for the following chapters, an overview and clarification of equilibrium relationships in economic ... More

Serves as an introductory overview for the rest of the book, and outlines its main aims. As a basis for the following chapters, an overview and clarification of equilibrium relationships in economic theory is presented. A preliminary discussion of testing for orders of integration and the estimation of long‐run relationships is provided. The chapter summarizes key concepts from time‐series analysis and the theory of stochastic processes and, in particular, the theory of Brownian motion processes. Several empirical examples are offered as illustration of these concepts.Less

John Denis Sargan 1924–1996

David F. Hendry

in Proceedings of the British Academy, Volume 120, Biographical Memoirs of Fellows, II

Denis Sargan was the leading British econometrician of his generation, playing a central role in establishing the technical basis for modern time-series econometric analysis. In a distinguished ... More

Denis Sargan was the leading British econometrician of his generation, playing a central role in establishing the technical basis for modern time-series econometric analysis. In a distinguished career spanning more than forty years as a teacher, researcher, and practitioner, particularly during the period that he was Professor of Econometrics at the LSE, Denis transformed both the role of econometrics in the analysis of macroeconomic time series, and the teaching of econometrics.Less

Time Series Analysis with Two or More Time Series

Youseop Shin

in Time Series Analysis in the Social Sciences: The Fundamentals

Chapter Six explains time series analysis with one or more independent variables. The dependent variable is the monthly violent crime rates and the independent variables are unemployment rates and ... More

Chapter Six explains time series analysis with one or more independent variables. The dependent variable is the monthly violent crime rates and the independent variables are unemployment rates and inflation. This chapter discusses several topics related to the robustness of estimated models, such as how to prewhiten a time series, how to deal with trends and seasonal components, how to deal with autoregressive residuals, and how to discern changes of the dependent variable caused by independent variables from its simple continuity. This chapter also discusses the concepts of co-integration and long-memory effect and related topics such as error correction models and autoregressive distributive lags models.Less

Gallman’s Annual Product Series, 1834–1909

Robert E. Gallman and Paul W. Rhode

in Capital in the Nineteenth Century

The chapter describes and analyses the underlying data in Gallman’s Volume 30 annual national product series. These are our best estimates of nineteenth-century US GNP, NNP, and capital formation and ... More

The chapter describes and analyses the underlying data in Gallman’s Volume 30 annual national product series. These are our best estimates of nineteenth-century US GNP, NNP, and capital formation and underlie much of what we know about America’s economic growth. The series break down national product, measures in current and constant prices, in consumptions and investment components. The chapter discusses the limitations of the Volume 30 series and why Gallman considered his estimates suitable for long-run investigations but not for time-series analysis as annual series.Less

Linear state space models

J. Durbin and S.J. Koopman

in Time Series Analysis by State Space Methods: Second Edition

This chapter shows how structural time series models can be put into state space form. It puts Box-Jenkins ARIMA models into state space form, thus demonstrating that these models are special cases ... More

This chapter shows how structural time series models can be put into state space form. It puts Box-Jenkins ARIMA models into state space form, thus demonstrating that these models are special cases of state space models. It discusses the history of exponential smoothing and shows how it relates to simple forms of state space and ARIMA models. It considers various aspects of regression with or without time-varying coefficients or autocorrelated errors. It also presents a treatment of dynamic factor analysis. Further topics discussed include simultaneous modelling series from different sources, benchmarking, continuous time models, and spline smoothing in discrete and continuous time.Less

The Impact on Foreign Direct Investment of BITs *

Unctad

in The Effect of Treaties on Foreign Direct Investment: Bilateral Investment Treaties, Double Taxation Treaties, and Investment Flows

This chapter examines whether the conclusion of BITs does indeed contribute to an increase in FDI. Time-series data analysis based on bilateral FDI flows between the BIT signatory countries shows ... More

This chapter examines whether the conclusion of BITs does indeed contribute to an increase in FDI. Time-series data analysis based on bilateral FDI flows between the BIT signatory countries shows that the influence of BITs on FDI is weak, especially in redirecting the share of FDI flowing from or to BIT signatory countries. In other words, following the signing of a BIT, it is more likely than not that the host country will marginally increase its share in the outward FDI of the home country; the same applies to the share of the home country in the FDI inflows of the host country. The effect, however, is usually small. In the cross-country comparison of FDI determinants, the overall conclusion is that BITs appear to play a minor and secondary role in influencing FDI flows.Less

Putting Relative Advantage to the Test: State-Level Republican Growth in the Modern American South

M. V. Hood III, Quentin Kidd, and Irwin L. Morris

in The Rational Southerner: Black Mobilization, Republican Growth, and the Partisan Transformation of the American South

This chapter provides the first extensive empirical assessment of the theory of relative advantage. A panel Granger analysis based on nearly five decades of state-level data demonstrates that black ... More

This chapter provides the first extensive empirical assessment of the theory of relative advantage. A panel Granger analysis based on nearly five decades of state-level data demonstrates that black mobilization influenced Republican growth in each of the Southern states. The chapter also includes results from time series cross-sectional analyses that clearly indicate that black mobilization played a more important role in the growth of Southern Republicanism than regional economic growth, black context, in-migration, or the growth of evangelicalism—all of which are competing explanations for GOP growth in the South. The analysis also demonstrates that the growing viability of Republican substate party organizations played a role in subsequent Republican growth in the electorate.Less

Bayesian dynamic modelling

West Mike

in Bayesian Theory and Applications

This chapter focuses on some key models and ideas in Bayesian time series and forecasting, along with extracts from a few time series analysis and forecasting examples. It discusses specific ... More

This chapter focuses on some key models and ideas in Bayesian time series and forecasting, along with extracts from a few time series analysis and forecasting examples. It discusses specific modelling innovations that relate directly to the goals of addressing analysis of increasingly high-dimensional time series and nonlinear models. These include dynamic graphical and matrix models, dynamic matrix models for stochastic volatility, time-varying sparsity modelling, and nonlinear dynamical systems.Less

Time Series Analysis in the Social Sciences

Youseop Shin

in Time Series Analysis in the Social Sciences: The Fundamentals

This chapter explains how time series analysis has been applied in the social sciences.

Techniques for the Study of Long-Term Dynamics: Analyzing Time Series

Peter A. Henderson

in Southwood's Ecological Methods

The definition of ‘long-term’ requires reference to the generation time and the scale over which environmental variation of interest operates. A long-term (large temporal scale) population study of ... More

The definition of ‘long-term’ requires reference to the generation time and the scale over which environmental variation of interest operates. A long-term (large temporal scale) population study of an annually reproducing insect would be expected to include annual population estimates over at least ten years. An equivalent study of an amoeba, which can reproduce daily, might be completed in a few weeks. However, if the focus of a long-term study is the role of seasonal variation in determining population number, then it is likely that a study will need at least twenty-five years of data, irrespective of the size of the organism and the generation time. This chapter reviews a range of time series analytical techniques and presents R code listings for measuring synchrony and species associations, detecting break-points in time series and measuring community stability. Statistical methods to assess if a species has gone extinct are described. Techniques for detecting density dependence in time series are reviewed. Temporal β‎-diversity is defined as the shift in the identities and/or the abundances of named taxa in a specified assemblage over two or more time points. The measurement of temporal β‎-diversity is discussed. Numerous R code listings are presented.Less

Time Series Analysis as an Impact Analysis Method

Youseop Shin

in Time Series Analysis in the Social Sciences: The Fundamentals

Chapter Seven explains interrupted time series analysis. This chapter includes the impact analysis of the Three-Strikes-Out law with October 1994 (when Public Law 103-322 was enacted) as the ... More

Chapter Seven explains interrupted time series analysis. This chapter includes the impact analysis of the Three-Strikes-Out law with October 1994 (when Public Law 103-322 was enacted) as the intervention point.Less

Measuring Macroeconomic Exposure: The Case of Volvo Cars 1

Lars Oxelheim and Clas Wihlborg

in Corporate Decision-Making with Macroeconomic Uncertainty: Performance and Risk Management

Volvo cars exposure have been measured for this chapter by means of time series regression analysis. The required data include quarterly actual cash flow figures for a substantial number of years, ... More

Volvo cars exposure have been measured for this chapter by means of time series regression analysis. The required data include quarterly actual cash flow figures for a substantial number of years, macroeconomic data, as well as proxies for industry- or firm-specific conditions. Issues of implementation are emphasized here and the interpretation of coefficients is discussed from the perspective of risk management. The coefficients for commercial cash flow exposures can easily be translated into financial positions that would provide hedges against macroeconomic exposures. The coefficients can also be helpful in decisions with respect to pricing strategy that affect exposures. Finally, the use of the coefficients for ex post analysis of what hedging has achieved and for performance filtering is illustrated.Less

Illustrations of the use of the linear model

J. Durbin and S.J. Koopman

in Time Series Analysis by State Space Methods: Second Edition

This chapter discusses examples which show how the use of the linear model works in practice. The first example is an analysis of road accident data to estimate the reduction in car drivers killed ... More

This chapter discusses examples which show how the use of the linear model works in practice. The first example is an analysis of road accident data to estimate the reduction in car drivers killed and seriously injured in the UK due to the introduction of a seat belt law. The second example considers a bivariate model which includes data on numbers of front seat passengers killed and seriously injured and on numbers of rear seat passengers killed and seriously injured. The third example shows how state space methods can be applied to Box-Jenkins ARMA models employed to model series of users logged onto the Internet. The fourth example considers the state space solution to the spline smoothing of motorcycle acceleration data. The fifth example provides a dynamic factor analysis based on the linear Gaussian model for the term structure of interest rates paid on US Treasury securities.Less

Implement, Document, and Maintain

Kai R. Larsen and Daniel S. Becker

in Automated Machine Learning for Business

This section covers the final section of the machine learning life cycle. Consider these the most important steps of the entire process. This is the point at which we have the greatest potential to ... More

This section covers the final section of the machine learning life cycle. Consider these the most important steps of the entire process. This is the point at which we have the greatest potential to help our organization reap the benefits of machine learning. In traditional information systems development, 60–80% of the cost of a system comes during the maintenance phase, so these steps are important. This section covers how to deploy a machine learning model, as well as documenting and maintaining this model. A chapter covers the seven types of target leakage followed by time-aware validation and time-series analysis.Less

Phylogenetic Position of the Giant Panda: Historical Consensus through Supertree Analysis

Emonds Olaf R. P. Bininda

in Giant Pandas: Biology and Conservation

This chapter comprehensively outlines a vast amount of historical data on the giant panda and on Ailurus with a view to producing a consensus on their phylogenetic affinities. It reports that ... More

This chapter comprehensively outlines a vast amount of historical data on the giant panda and on Ailurus with a view to producing a consensus on their phylogenetic affinities. It reports that supertree analysis suggests affinities with the Procyonidae. The chapter surveys the systematic literature from the description of Ailuropoda by David to the present in order to explore the affinities of both panda species through time. It also uses a sliding-window approach to time-series analysis in order to view changes in phylogenetic opinion over time. All statements of phylogenetic affinity strongly place Ailuropoda and Ailurus within separate carnivore families. The chapter refrains from making any taxonomic conclusions, even for Ailuropoda, for which the phylogenetic position seems reasonably secure. The taxonomic assessments are subjective and can frequently obscure or even misrepresent phylogenetic information. Moreover, a brief report on pylogenetic placement of the giant panda based on molecular data is presented.Less