• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• pp.989-995
• /
• 2009

Basu et al. (1998) proposed the minimum divergence estimating method which is free from using the painful kernel density estimator. Their proposed class of density power divergences is indexed by a single parameter $\alpha$ which controls the trade-off between robustness and efficiency. In this article, (1) we introduce a new large class the minimum squared distance which includes from the minimum Hellinger distance to the minimum $L_2$ distance. We also show that under certain conditions both the minimum density power divergence estimator(MDPDE) and the minimum squared distance estimator(MSDE) are asymptotically equivalent and (2) in finite samples the MDPDE performs better than the MSDE in general but there are some cases where the MSDE performs better than the MDPDE when estimating a location parameter or a proportion of mixed distributions.

• Journal of the Korean Statistical Society
• /
• v.14 no.1
• /
• pp.7-17
• /
• 1985

Data set generated by teh bivariate dichotomous choice made by individuals often occurs in practice. This paper presents general model of how such data set is generated as well as methods of estimation. The M.L.E. is examined and found to be computationally burdensome. A simpler estimator, the bivariate dichotomous two-stage estimator, is suggested as an alternative. The two-stage estimator is found to be as efficient as the M.L.E.

• The Korean Journal of Applied Statistics
• /
• v.7 no.2
• /
• pp.173-182
• /
• 1994

By applying slope estimator under the arbitrary error distributions proposed by Han(1993), if we define regression quantiles to give upper and lower trimming part and blocks of data, we show the proposed slope estimator has asymptotically efficient slope estimator when the number of regression quantiles to from blocks of data goes to sufficiently large.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.859-866
• /
• 2001

The problem of wavelet density estimation is studied when the sample observations are contaminated with random noise. In this paper a linear wavelet estimator based on Meyer-type wavelets is shown to be L$_1$ strongly consistent for f(x) with bounded support when Fourier transform of random noise has polynomial descent or exponential descent.

• Communications for Statistical Applications and Methods
• /
• v.15 no.5
• /
• pp.753-764
• /
• 2008

The $L_1$ regularized estimator in quantile problems conduct parameter estimation and model selection simultaneously and have been shown to enjoy nice performance. However, $L_1$ regularized estimator has a drawback: when there are several highly correlated variables, it tends to pick only a few of them. To make up for it, the proposed method adopts doubly regularized framework with the mixture of $L_1$ and $L_2$ norms. As a result, the proposed method can select significant variables and encourage the highly correlated variables to be selected together. One of the most appealing features of the new algorithm is to construct the entire solution path of doubly regularized quantile estimator. From simulations and real data analysis, we investigate its performance.

• Communications for Statistical Applications and Methods
• /
• v.3 no.3
• /
• pp.271-282
• /
• 1996

this paper deal with the estimation of the power spectral density function of time series. A kernel estimator which is based on local average is defined and the rates of convergence of the pointwise, $$L_2$-norm; and; $L{\infty}$-norm associated with the estimator are investigated by restricting as to kernels with suitable assumptions. Under appropriate regularity conditions, it is shown that the optimal rate of convergence for 0$N^{-r}$ both in the pointwiseand $$L_2$-norm, while; $N^{r-1}(logN)^{-r}$is the optimal rate in the $L{\infty}-norm$. Some examples are given to illustrate the application of main results.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.733-739
• /
• 2011

The linear absolute shrinkage and selection operator(Lasso) method improves the low prediction accuracy and poor interpretation of the ordinary least squares(OLS) estimate through the use of $L_1$ regularization on the regression coefficients. However, the Lasso is not robust to outliers, because the Lasso method minimizes the sum of squared residual errors. Even though the least absolute deviation(LAD) estimator is an alternative to the OLS estimate, it is sensitive to leverage points. We propose a robust Lasso estimator that is not sensitive to outliers, heavy-tailed errors or leverage points.

• Communications for Statistical Applications and Methods
• /
• v.3 no.2
• /
• pp.299-307
• /
• 1996

This article is concerned with the algorithms for the least median of squares estimator. An algorithm based on the $L{\infty}$ .inf.-estimation procedure is proposed in an attempt to improve the optimality of the estimate. And it is shown that the proposed algorithm yields more optimal estimate than the traditional resampling algorithms. The proposed algorithm employs a linear scaling transformation at each iteration of the$L{\infty}$-algorithm to deal with its computational inefficiency problem.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.18 no.6
• /
• pp.587-592
• /
• 2013

In this paper, the performance improvement of the sensorless control of IPMSM employing the active flux concept by the improved current estimator is presented. The accuracy of the current estimator used in a previous report is degraded when the motor parameters are not known exactly. A simple current estimator derived from estimated flux is proposed to improve the position estimation performance. In order to show the usefulness of the proposed estimation method, the simulation results using Matlab/Simulink and the experiment results are presented.

• Communications for Statistical Applications and Methods
• /
• v.12 no.1
• /
• pp.169-179
• /
• 2005

In this study, we investigate the effects of the weight function in the bounded influence regression quantile (BIRQ) estimator for the AR(l) model with additive outliers. In order to down-weight the outliers of X -axis, the Mallows' (1973) weight function has been commonly used in the BIRQ estimator. However, in our Monte Carlo study, the BIRQ estimator using the Tukey's bisquare weight function shows less MSE and bias than that of using the Mallows' weight function or Huber's weight function. Thus, the use of the Tukey's weight function is recommended in the BIRQ estimator for our model.