• Communications for Statistical Applications and Methods
• /
• v.4 no.2
• /
• pp.445-452
• /
• 1997

In this paper, twicing technique for the improvement of asymptotic boundary bias in nonparametric regression is considered. Asymptotic mean squared errors of the nonparametric regression estimators are derived at the boundary region by twicing the Nadaraya-Waston and local linear smoothing. Asymptotic biases of the resulting estimators are of order$h^2$and$h^4$ respectively.

• Journal of the Korean Statistical Society
• /
• v.30 no.1
• /
• pp.77-87
• /
• 2001

Some asymptotic results on the local likelihood density estimator of Copas(1995) are derived when the locally parametric model has several parameters. It turns out that it has the same asymptotic mean squared error as that of Hjort and Jones(1996).

• Journal of the Korean Statistical Society
• /
• v.20 no.2
• /
• pp.118-138
• /
• 1991

Given a random sample of size N(unknown) with density f(x $\theta$), suppose that only n observations which lie outside a region R are recorded. On the basis of n observations, the Bayes estimators of $\theta$ and N are considered and their asymptotic expansions are developed to compare their second order asymptotic properties with those of the maximum likelihood estimators and the Bayes modal estimators. Corrections to bias and median bias of these estimators are made. An example is given to illustrate the results obtained.

• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.527-538
• /
• 2019

This paper considers the issue of obtaining the optimal design in Poisson regression model when the sample size is small. Poisson regression model is widely used for the analysis of count data. Asymptotic theory provides the basis for making inference on the parameters in this model. However, for small size experiments, asymptotic approximations, such as unbiasedness, may not be valid. Therefore, first, we employ the second order expansion of the bias of the maximum likelihood estimator (MLE) and derive the mean square error (MSE) of MLE to measure the quality of an estimator. We then define DM-optimality criterion, which is based on a function of the MSE. This criterion is applied to obtain locally optimal designs for small size experiments. The effect of sample size on the obtained designs are shown. We also obtain locally DM-optimal designs for some special cases of the model.

• Journal of the Korean Statistical Society
• /
• v.25 no.2
• /
• pp.217-233
• /
• 1996

This paper gives a rigorous proof of an asymptotic result about bias and variance for a transformation-based nonparametric regression estimator proposed by Park et al (1995).

• Journal of the Korean Statistical Society
• /
• v.25 no.2
• /
• pp.195-203
• /
• 1996

A bootstrap method is used to correct the apparent downward bias of a naive plug-in bootstrap model selection criterion, which is shown to enjoy a high degree of accuracy. Comparison of bootstrap method with the asymptotic method is made through an illustrative example.

• Communications for Statistical Applications and Methods
• /
• v.31 no.4
• /
• pp.459-466
• /
• 2024

Multivariate regular variation is a popular framework of multivariate extreme value analysis. However, a suitable parametric model needs to be introduced for efficient estimation of its spectral measure. In such a view, elliptical distributions have been employed for deriving such models. On the other hand, the second order behavior of multivariate regular variation has to be specified for investigating the property of the estimator. This paper derives such a behavior by imposing a widely adopted second order regular variation condition on the representation of elliptical distributions. As result, the second order variation for the convergence to spectral measure is characterized by a signed measure with a regular varying index. Moreover, it leads to the asymptotic bias of the estimator. For demonstration, multivariate t-distribution is considered.

• Communications for Statistical Applications and Methods
• /
• v.15 no.5
• /
• pp.709-717
• /
• 2008

The difference of two one-sided kernel estimators is usually used to detect the location of the discontinuity points of regression function. The large absolute value of the statistic imply discontinuity of regression function, so we may use the difference of two one-sided kernel estimators as the test statistic for testing null hypothesis of a smooth regression function. The problem is, however, we only know the asymptotic distribution of the test statistic under $H_0$ and we hardly expect the good performance of test if we rely solely on the asymptotic distribution for determining the critical points. In this paper, we show that if we adjust the bias of test statistic properly, the asymptotic rules hold for even small sample size situation.

• Journal of the Korean Statistical Society
• /
• v.27 no.1
• /
• pp.113-132
• /
• 1998

In this paper, we consider a minimum distance (M.D.) estimation based on kernels for U-statistics. We use Cramer-von Mises type distance function which measures the discrepancy between U-empirical distribution function(d.f.) and modeled d.f. of kernel. In the distance function, we allow various integrating measures, which can be finite, $\sigma$-finite or discrete. Then we derive the asymptotic normality and study the qualitative robustness of M. D. estimates.

• Journal of the Korean Data and Information Science Society
• /
• v.6 no.1
• /
• pp.73-83
• /
• 1995

We construct the approximate bootstrap confidence intervals for reliability (R) when the distributions of strength and stress are both normal. Also we propose percentile, bias correct (BC), bias correct acceleration (BCa), and percentile-t intervals for R. We compare with the accuracy of the proposed bootstrap confidence intervals and classical confidence interval based on asymptotic normal distribution through Monte Carlo simulation. Results indicate that the confidence intervals by bootstrap method work better than classical confidence interval. In particular, confidence intervals by BC and BCa method work well for small sample and/or large value of true reliability.