Search

This article is concerned with the asymptotic theory of estimates of unknown parameters in autoregressive quantile processes. We assume random errors form a strictly stationary ϕ -mixing sequences. In view of the approach of argmins and blocking argument, we prove the parameter estimators satisfy the functional moderate deviation principle (MDP). Further, we give the law of the iterated logarithm under some standard conditions. Based on the contraction principle, the moderate deviation principles of L-estimators on the autoregression quantile (ARQ) and autoregression rank scores (ARRS's) are also discussed. This method can be extended to a fair range of different statistical estimation problems. [ABSTRACT FROM AUTHOR]

Two innovative acceleration-layer configuration amendment (CA) schemes are proposed to achieve the CA of constrained redundant robot arms. Specifically, by applying the Zhang neurodynamics equivalency (ZNE) method, an acceleration-layer CA performance indicator is derived theoretically. To obtain a unified-layer inequality constraint by transforming from angle-layer and velocity-layer constraints to acceleration-layer constraints, five theorems and three corollaries are theoretically derived and rigorously proved. Then, together with the unified acceleration-layer bound constraint, an enhanced acceleration-layer CA scheme specially considering three-layer time-variant physical limits is proposed, and a simplified acceleration-layer CA scheme considering three-layer time-invariant physical limits is also proposed. The proposed CA schemes are finally formulated in the form of standard quadratic programming and are solved by a projection neurodynamics solver. Moreover, comparative simulative experiments based on a four-link planar arm and a UR3 spatial arm are performed to verify the efficacy and superiority of the proposed CA schemes. At last, physical experiments are conducted on a real Kinova Jaco2 arm to substantiate the practicability of the proposed CA schemes. [ABSTRACT FROM AUTHOR]

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.techfore.2004.08.004 Byline: Mingzhi Mao, E.C. Chirwa Keywords: Motor vehicle; Fatality; Risk forecasting; Grey model; Crashworthiness; Accident Abstract: A mathematical model known as grey model GM(1, 1) has been herewith employed successfully in the estimation of vehicle fatality risk. Its application to the UK and US data sets yields exact predictions that are of high repeatability with characteristics depicting high reliability and efficiency. Another advantage is that these results are obtained without using any assumptions. In the analysis, the model normally deals directly with original data and searches the intrinsic regularity of data. The forecasting accuracy is related to the sample number n in grey model, and the accuracies for smoothed fatality risk predictions are higher than those for short-term predictions. The total time-dependent trends for these cases show very small variability between the real and prediction values, hence showing the theory to be working. For rollover cases, US data sets show that the risk of occupants to experience fatal injuries is decreasing and the fluctuating amplitude is declining. The theory predicted this trend and showed the time-dependent curves for data set and prediction to be in-phase. Another interesting observation that has come from the study is that UK and US experience similar phases in the time-dependent trend of motor vehicle fatality risk despite the different perception of safety between the USA and UK, especially when it comes to occupant usages of restraint systems. Author Affiliation: Bolton Automotive and Aerospace Research Group, Department of Engineering & Safety, Bolton Institute, Bolton BL3 5AB, UK Article History: Received 15 June 2004; Revised 13 August 2004; Accepted 14 August 2004

This paper exploits the random assignment rule embedded in Chinese education system to investigate the external effect of better-educated parents in a class on students' academic outcomes. Using a representative sample of Chinese middle school students, our estimation results show that a higher share of classmates with college-educated parents helps improve test scores of the students in the class. We further show that such external effect may arise from positive interactions between parents. [ABSTRACT FROM AUTHOR]