Robust Forecasting of Non-Stationary Time Series
نویسندگان
چکیده
منابع مشابه
Forecasting Non - stationary Economic Time Series
Forecasting macroeconomic time series is notoriously difficult. Previously unannounced changes in policy, natural and man-made disasters, institutional changes, new discoveries, new data definitions and revisions among others cause occasional large forecast errors in the standard constant-parameter models. While much effort has been put into working out the theory of estimation, inference and i...
متن کاملForecasting non-stationary time series by wavelet process modelling
Many time series in the applied sciences display a time-varying second order structure. In this article, we address the problem of how to forecast these non-stationary time series by means of non-decimated wavelets. We first consider a model in which only the variance evolves with time. We define a predictor for this model and show an application to the Dow Jones index. Then, we generalise the ...
متن کاملForecasting Non-Stationary Time Series: From Theory to Algorithms
Generalization bounds for time series prediction and other non-i.i.d. learning scenarios that can be found in the machine learning and statistics literature assume that observations come from a (strictly) stationary distribution. The first bounds for completely non-stationary setting were proved in [6]. In this work we present an extension of these results and derive novel algorithms for foreca...
متن کاملUsing Wavelets and Splines to Forecast Non-Stationary Time Series
This paper deals with a short term forecasting non-stationary time series using wavelets and splines. Wavelets can decompose the series as the sum of two low and high frequency components. Aminghafari and Poggi (2007) proposed to predict high frequency component by wavelets and extrapolate low frequency component by local polynomial fitting. We propose to forecast non-stationary process u...
متن کاملLearning Theory and Algorithms for Forecasting Non-stationary Time Series
We present data-dependent learning bounds for the general scenario of nonstationary non-mixing stochastic processes. Our learning guarantees are expressed in terms of a data-dependent measure of sequential complexity and a discrepancy measure that can be estimated from data under some mild assumptions. We use our learning bounds to devise new algorithms for non-stationary time series forecastin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: SSRN Electronic Journal
سال: 2010
ISSN: 1556-5068
DOI: 10.2139/ssrn.1690494