Weighted Linear Recurrent Forecasting in Singular Spectrum Analysis
被引:2
|
作者:
论文数: 引用数:
h-index:
机构:
Kalantari, Mahdi
[1
]
Hassani, Hossein
论文数: 0引用数: 0
h-index: 0
机构:
Univ Tehran, Res Inst Energy Management & Planning, Tehran, IranPayame Noor Univ, Dept Stat, Tehran 193954697, Iran
Hassani, Hossein
[2
]
Silva, Emmanuel Sirimal
论文数: 0引用数: 0
h-index: 0
机构:
Fash Univ Arts London, London Coll, Fash Business Sch, Ctr Fash Business & Innovat Res, London WC1V 7EY, EnglandPayame Noor Univ, Dept Stat, Tehran 193954697, Iran
Silva, Emmanuel Sirimal
[3
]
机构:
[1] Payame Noor Univ, Dept Stat, Tehran 193954697, Iran
[2] Univ Tehran, Res Inst Energy Management & Planning, Tehran, Iran
[3] Fash Univ Arts London, London Coll, Fash Business Sch, Ctr Fash Business & Innovat Res, London WC1V 7EY, England
Time series;
forecasting;
singular spectrum analysis;
recurrent forecasting;
DIAGNOSIS;
D O I:
10.1142/S0219477520500108
中图分类号:
O1 [数学];
学科分类号:
0701 ;
070101 ;
摘要:
Singular Spectrum Analysis (SSA) is an increasingly popular time series filtering and forecasting technique. Owing to its widespread applications in a variety of fields, there is a growing interest towards improving its forecasting capabilities. As such, this paper takes into consideration the Recurrent forecasting approach in SSA (SSA-R) and presents a new mechanism for improving the accuracy of forecasts attainable via this method. The proposed Recurrent SSA-R approach is referred to as Weighted SSA-R (W:SSA-R), and we propose using a weighting algorithm for weigthing the coefficients of the Linear Recurrent Relation (LRR). The performance of forecasts from the W:SSA-R approach are compared with forecasts from the established SSA-R approach. We exploit real data and various simulated time series for the comparison, so as to provide the reader with more conclusive findings. Our results confirm that the W:SSA-R approach can provide comparatively more accurate forecasts and is indeed a viable solution for improving forecasts by SSA.
机构:
Bournemouth Univ, Business Sch, Stat Res Ctr, 89 Holdenhurst Rd, Bournemouth BH8 8EB, Dorset, EnglandBournemouth Univ, Business Sch, Stat Res Ctr, 89 Holdenhurst Rd, Bournemouth BH8 8EB, Dorset, England
机构:
Univ Fed Bahia, Dept Stat, Salvador, BA, Brazil
Univ Tampere, Ctr Appl Stat & Data Analyt, Fac Nat Sci, Tampere, FinlandBu Ali Sina Univ, Dept Stat, POB 6517838695, Hamadan, Iran
机构:
Univ Arts London, London Coll Fash, Fash Business Sch, 272 High Holborn, London WC1V 7EY, EnglandBournemouth Univ, Sch Business, Bournemouth, Dorset, England
机构:
St Petersburg State Univ, Fac Math & Mech, Dept Stat Modelling, St Petersburg 198504, RussiaSt Petersburg State Univ, Fac Math & Mech, Dept Stat Modelling, St Petersburg 198504, Russia
Golyandina, Nina
Korobeynikov, Anton
论文数: 0引用数: 0
h-index: 0
机构:
St Petersburg State Univ, Fac Math & Mech, Dept Stat Modelling, St Petersburg 198504, RussiaSt Petersburg State Univ, Fac Math & Mech, Dept Stat Modelling, St Petersburg 198504, Russia