Application of sand-rubber mixtures to mitigate vibration and ground shock

Chew, Jia Han

doi:10.32657/10220/46628

Cited by 1 publication

(1 citation statement)

References 64 publications

(127 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We should expect such predictability to weaken as trader actions to exploit profit opportunities expunge serial return correlation, with prices adjusting to new equilibrium levels quickly, given that the stock market nowadays is assumed to be highly efficient; hence predictability tends to recede over longer horizons. Intraday horizons are important, however, in the management of trading desk risk (see Chew, 1994). Despite its economic and financial importance, the analysis of stock return predictability for very short forecast horizons is under-represented in the academic literature, although worthy of mention is the study by Clements and Taylor (2003) describing an analysis of interval forecasts for high-frequency data.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Performance of Nonlinear Models for Intraday Stock Returns

Matías

Reboredo

2011

Journal of Forecasting

View full text Add to dashboard Cite

We 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.

show abstract

Section: Introductionmentioning

confidence: 99%