دانلود رایگان مقاله لاتین هموارسازی نمایی از سایت الزویر
عنوان فارسی مقاله:
روش هموارسازی نمایی باگینگ با تجزیه STL و تبدیل جعبه کاکس
عنوان انگلیسی مقاله:
Bagging exponential smoothing methods using STL decomposition and Box–Cox transformation
سال انتشار : 2016
برای دانلود رایگان مقاله هموارسازی نمایی اینجا کلیک نمایید.
بخشی از مقاله انگلیسی:
3. Experimental
study In this section, we describe the forecasting methods, error measures, and statistical tests that were used in the experiments, together with the results obtained for the M3 dataset, separately for yearly, quarterly, and monthly data. 3.1. Compared methods In what follows, we refer to the decomposition approach proposed in this paper, namely the Box–Cox transformation and STL or loess, as Box–Cox and loess-based decomposition (BLD). Bootstrapped versions of the series are generated as was discussed in Section 2, i.e., BLD is followed by the MBB, to generate bootstrapped versions of the series. We use an ensemble size of 100, so that we estimate models on the original time series and on 99 bootstrapped series. We compare our proposed method both to the original ETS method and to several variants, in the spirit of Cordeiro and Neves (2009). Specifically, we consider all possible combinations of using BLD or ETS for decomposition, and the MBB or a sieve bootstrap for bootstrapping the remainder. Here, the sieve bootstrap is implemented as follows: an ARIMA model is fitted to the remainder of the method used for decomposition (BLD or ETS) using the auto.arima function from the forecast package (Hyndman, 2014; Hyndman & Khandakar, 2008), which selects a model automatically using the bias-corrected AIC, with model orders of up to five. Then, a normal bootstrapping procedure is applied to the residuals of thisARIMA model. In particular, the following procedures are employed: ETS The original exponential smoothing method applied to the original series, selecting one model from among all possible models using the biascorrected AIC.
برای دانلود رایگان مقاله هموارسازی نمایی اینجا کلیک نمایید.
کلمات کلیدی:
Bagging exponential smoothing methods using STL ... - Rob J Hyndman https://robjhyndman.com/publications/bagging-ets/ Exponential smoothing is one of the most popular forecasting methods. We present a method for bootstrap aggregation (bagging) of exponential smoothing methods. The bagging uses a Box-Cox transformation followed by an STL decomposition to separate the time series into trend, seasonal part, and remainder. Bagging exponential smoothing methods using STL ... - IDEAS/RePEc https://ideas.repec.org/a/eee/intfor/v32y2016i2p303-312.html by C Bergmeir - 2016 - Cited by 14 - Related articles We present a technique for the bootstrap aggregation (bagging) of exponential smoothing methods, which results in significant improvements in the forecasts. EconPapers: Bagging exponential smoothing methods using STL ... econpapers.repec.org/RePEc:eee:intfor:v:32:y:2016:i:2:p:303-312 by C Bergmeir - 2016 - Cited by 14 - Related articles Apr 6, 2017 - By Christoph Bergmeir, Rob Hyndman and José M. Benítez; Abstract: Exponential smoothing is one of the most popular forecasting methods. Bagging exponential smoothing methods using STL ... - ResearchGate https://www.researchgate.net/.../291421520_Bagging_exponential_smoothing_methods... Bagging exponential smoothing methods using STL decomposition and Box–Cox transformation on ResearchGate, the professional network for scientists. Guest post: On the robustness of bagging exponential smoothing ... kourentzes.com/.../guest-post-on-the-robustness-of-bagging-exponential-smoothing/ Oct 31, 2014 - Using ETS (selecting the most appropriate method from the exponential smoothing family using information criteria) they produce multiple sets ... baggedETS: Forecasting using the bagged ETS method in forecast ... https://rdrr.io › CRAN › forecast › baggedETS Bagging Exponential Smoothing Methods using STL Decomposition and Box-Cox Transformation. International Journal of Forecasting 32, 303-312. Bagging exponential smoothing methods using ... - Monash University monash.edu/.../bagging-exponential-smoothing-methods-using-stl-decomposition-and... Original language, English. Pages (from-to), 303 - 312. Number of pages, 10. Journal, International Journal of Forecasting. Volume, 32. Issue number, 2. DOIs. Bagging exponential smoothing methods using ... - Monash University monash.edu/.../bagging-exponential-smoothing-methods-using-stl.../export.html Bagging exponential smoothing methods using STL decomposition and Box-Cox transformation. International Journal of Forecasting, 32(2), 303 - 312.
