Parametric statistics

About: Parametric statistics is a research topic. Over the lifetime, 39200 publications have been published within this topic receiving 765761 citations.

Robust Sliding Mode Control for Robot Manipulators

Abstract: In the face of large-scale parametric uncertainties, the single-model (SM)-based sliding mode control (SMC) approach demands high gains for the observer, controller, and adaptation to achieve satisfactory tracking performance. The main practical problem of having high-gain-based design is that it amplifies the input and output disturbance as well as excites hidden unmodeled dynamics, causing poor tracking performance. In this paper, a multiple model/control-based SMC technique is proposed to reduce the level of parametric uncertainty to reduce observer-controller gains. To this end, we split uniformly the compact set of unknown parameters into a finite number of smaller compact subsets. Then, we design a candidate SMC corresponding to each of these smaller subsets. The derivative of the Lyapunov function candidate is used as a resetting criterion to identify a candidate model that approximates closely the plant at each instant of time. The key idea is to allow the parameter estimate of conventional adaptive sliding mode control design to be reset into a model that best estimates the plant among a finite set of candidate models. The proposed method is evaluated on a 2-DOF robot manipulator to demonstrate the effectiveness of the theoretical development.

On the Transfer of Parametric Values in L2 Development

Abstract: White (e.g., 1990/1991; 1992a) argued that grammatical representations in second-language development can be understood in terms of parametric values that are transferred from the learner's native language. Schwartz (1993a; 1993b) and Schwartz and Sprouse (1994) push this view of transfer to its logical limit: The initial state of L2 acquisition is determined in its entirety by the parametric values of the native language. This article presents early-stage learner data that are not compatible with this strong view of parametric transfer. An alternative proposal is made, a weak transfer view in which lexical and functional projections transfer, and the headedness of those projections transfers, but morphology-driven values of features like the strength of agreement do not transfer. This idea is checked against learner data and is also evaluated for the extent to which it follows in a principled fashion from linguistic theory.

A Bayesian approach to nonlinear inversion

Abstract: Powerful methods are now available for solving linear parametric inverse problems. However, many inverse problems which arise in geohysics are nonlinear. Fortunately, it is possible to treat most of these with the air of linear perturbation theory and liner inversion. But a convenient method is needed for assessing the importance of nonlinearity in these quasi-linear problems. The present paper provides such a method. Matsu'ura and Jackson (1984) have presented a simple algorithm for evaluating the asymptotic covariance matrix fo estimation errors. In the present investigation, aspects of linear inversion are discussed, taking into account linear parametric inverse problems, nonuniqueness, prior information, confidence limits, conditional and marginal statistics, the relative importance of the prior and observational data, and standardized variables. Attention is also given to nonlinear inversion, and the application of the considered approaches to a number of examples.