000			02135nam a2200217Ia 4500
005			20260630101259.0
008			260630s9999||||xx |||||||||||||| ||und||
020			_a9781482225006
082			_a519.55 PEL _223
100			_aPelagatti, Matteo M.
245		0	_aTime Series Modelling with Unobserved Components _c/ Matteo M. Pelagatti.
250			_aFirst edition.
260			_aBoca Raton, Florida _b: Chapman & Hall/CRC Press _c, 2015.
300			_axv, 275 p. _b: illustrations, tables _c; 24 cm.
520			_aTime Series Modelling with Unobserved Components provides a comprehensive introduction to the Unobserved Components Model (UCM) approach for analysing and forecasting time series data. Written by Matteo M. Pelagatti, the book bridges statistical theory and practical application, making advanced state-space modelling techniques accessible to students, researchers, economists, and data analysts. The book begins with the fundamentals of statistical prediction and classical time series concepts, including stationarity, ARIMA models, and forecasting principles. It then develops the UCM framework by explaining how observed time series can be decomposed into underlying components such as trend, seasonal variation, cyclical movements, and irregular fluctuations. The text introduces the state-space representation of these models and explains estimation using the Kalman filter and smoothing algorithms. The later chapters focus on practical modelling strategies, intervention analysis, regression with time-varying coefficients, missing observations, outlier detection, and real-world applications such as business cycle analysis and economic forecasting. The author also reviews statistical software packages that support UCM estimation, enabling readers to implement these techniques in practice. The book is especially valuable for postgraduate students and professionals in statistics, econometrics, finance, economics, engineering, and data science.
650			_aForecasting.
650			_aMathematical statistics.
650			_aState-space methods.
650			_aTime-series analysis.
942			_cVC OFFICE
999			_c69895 _d69895