Forecasting Performance of Nonlinear Models for Intraday Stock Returns

Journal of Forecasting - Tập 31 Số 2 - Trang 172-188 - 2012
J.M. Matías1, Juan C. Reboredo2
1Department of Statistics, University of Vigo, Vigo, Spain
2Department of Economics, University of Santiago de Compostela, Santiago de Compostela, Spain

Tóm tắt

ABSTRACTWe studied the predictability of intraday stock market returns using both linear and nonlinear time series models. For the S&P 500 index we compared simple autoregressive and random walk linear models with a range of nonlinear models, including smooth transition, Markov switching, artificial neural network, nonparametric kernel regression and support vector machine models for horizons of 5, 10, 20, 30 and 60 minutes. The empirical results indicate that nonlinear models outperformed linear models on the basis of both statistical and economic criteria. Specifically, although return serial correlation receded by around 10 minutes, return predictability still persisted for up to 60 minutes according to nonlinear models, even though profitability decreases as time elapses. More flexible nonlinear models such as support vector machines and artificial neural network did not clearly outperform other nonlinear models. Copyright © 2011 John Wiley & Sons, Ltd.

Từ khóa


Tài liệu tham khảo

10.1111/j.1540-6261.2006.01060.x

10.1162/153244302760200704

10.1016/S0304-405X(02)00148-4

10.1080/00036840600592858

10.1109/18.749011

Chew L, 1994, Shock treatment, Risk, 7, 63

10.1016/j.jfineco.2004.06.004

10.1002/jae.703

10.2307/1392185

Fan J, 1996, Local Polynomial Modeling and its Applications

Fine T, 1999, Feedforward Neural Network Methodology

ForeseeF HaganT.1997. Gauss–Newton approximation to Bayesian regularization. InProceedings of the 1997 International Joint Conference on Neural Networks;1930–1935.

Granger C, 1993, Modelling Nonlinear Economic Relationships, 10.1093/oso/9780198773191.001.0001

10.2307/1912559

Hamilton J, 1994, Time Series Analysis, 10.1515/9780691218632

10.1016/0893-6080(90)90005-6

10.1086/296466

10.2307/2331150

10.2307/2965723

10.1109/72.485681

Leitch G, 1991, Economic forecast evaluation: profit versus the conventional error measures, American Economic Review, 81, 580

10.1016/S0893-6080(05)80131-5

10.1080/00036840500428088

10.3905/jpm.2004.442611

10.1080/07350015.2000.10524851

10.1162/neco.1993.5.2.305

10.1111/0022-1082.00246

10.2307/1391822

10.1002/for.3980140602

Schölkopff B, 2002, Learning with Kernels

10.1006/jcom.2002.0642

10.2307/1392186

10.1016/S0169-2070(97)00030-7

Teräsvirta T, 1994, Handbook of Econometrics, 2919

10.1016/j.ijforecast.2007.07.008

10.1162/089976600300015006

Vapnik V, 1998, Statistical Learning Theory

Thông tin
Thông tin xuất bản

Journal of Forecasting

Tập 31 Số 2

172-188

Thông tin tác giả