This paper proposes a model averaging method based on Kullback-Leibler distance under a homoscedastic normal error term. The resulting model average estimator is proved to be asymptotically optimal. When combining least squares estimators, the model average estimator is shown to have the same large sample properties as the Mallows model average (MMA) estimator developed by Hansen (2007). We sho...

This paper reports preliminary results of data-driven modeling of segmental (phoneme) duration for Hindi. Classification and Regression Tree (CART) based datadriven duration modeling for segmental duration prediction is presented. A number of features are considered and their usefulness and relative contribution for segmental duration prediction is assessed. Objective evaluation of the duration...

Robust regression tools are commonly used to develop regression-type ratio estimators with traditional measures of location whenever data contaminated outliers. Recently, the researchers extended this idea and developed through robust minimum covariance determinant (MCD) estimation. In study, quantile MCD-based is utilized a class mean proposed. The squared errors (MSEs) proposed also obtained....

This paper considers estimation of the intercept and slope vector parameters of the simple multivariate linear regression model with Student-t errors in the presence of uncertain prior information on the value of the unknown slope vector. The unrestricted, restricted, preliminary test, shrinkage, and positive-rule shrinkage estimators are defined together with the expressions for the bias, quad...

In this study, the average surface roughness values obtained when turning AISI 4140 grade tempered steel with a hardness of 51 HRC, were modeled using fuzzy logic, artificial neural networks (ANN) and multi-regression equations. Input variables consisted of cutting speed (V), feed rate (f) and depth of cut (a) while output variable was surface roughness (Ra). Fuzzy logic and ANN models were dev...

This paper considers estimation of the slope parameter of the linear regression model with Student-t errors in the presence of uncertain prior information on the value of the unknown slope. Incorporating uncertain non-sample prior information with the sample data the unrestricted, restricted, preliminary test, and shrinkage estimators are defined. The performances of the estimators are compared...

This paper proposes a double-talk-robust echo canceller using a smoothed-coefficient filter (SCF). The SCF’s tap coefficients are obtained by smoothing those of a pilot adaptive filter (PAF) for better accuracy and stability. The smoothing time constant is controlled by comparing mean squared high-pass errors of the SCF and the PAF. The high-pass filters enable precise control of the SCF by eli...

Undocumented changepoints (inhomogeneities) are ubiquitous features of climatic time series. Level shifts in time series caused by changepoints confound many inference problems and are very important data features. Tests for undocumented changepoints from models that have independent and identically distributed errors are by now well understood. However, most climate series exhibit serial autoc...

We outline the construction of robust, static designs for nonlinear regression models. The designs are robust in that they afford protection from increases in the mean squared error resulting from misspecifications of the model fitted by the experimenter. This robustness is obtained through a combination of minimax and Bayesian procedures. We first maximize (over a neighborhood of the fitted re...

This paper proposes some improved exponential type estimators of finite population mean under simple random sampling and double sampling. Expressions for biases and mean squared errors of the proposed estimators are derived up to the first order of approximation. Theoretical and numerical comparisons are made to investigate the performances of the estimators. The proposed estimators always perf...