• Journal of the Korean Statistical Society
• /
• v.30 no.4
• /
• pp.637-644
• /
• 2001

We investigated two kinds of mean square error (MSE) estimator of homogeneous linear estimator (HLE) for the population total under stratified multi-stage sampling. One is studied when the second stage variance component is estimable and the other is found in cafe it is not estimable. The proposed estimators are necessary forms of non-negative unbiased MSE estimators of HLE.

• The Korean Journal of Applied Statistics
• /
• v.6 no.1
• /
• pp.95-103
• /
• 1993

Necessary and sufficient conditions for the equality between the best linear unbiased estimators in two linear models with different covariance matrices, $V_1 and V_2$, say, are derived. Various applications of this discovery are also given. Necessary and sufficient conditions for the equality between the best linear unbiased estimator and the ordinary least squares estimator are discussed related to this topic.

• Wind and Structures
• /
• v.16 no.4
• /
• pp.355-372
• /
• 2013

The Gringorten estimator has been extensively used in extreme value analysis of wind speed records to obtain unbiased estimates of design wind speeds. This paper reviews the derivation of the Gringorten estimator for the mean plotting position of extremes drawn from parents of the exponential type and demonstrates how it eliminates most of the bias caused by the classical Weibull estimator. It is shown that the coefficients in the Gringorten estimator are the asymptotic values for infinite sample sizes, whereas the estimator is most often used for small sample sizes. The principles used by Gringorten are used to derive a new Consistent Linear Unbiased Estimator (CLUE) for the mean plotting positions for the Fisher Tippett Type 1, Exponential and Weibull distributions and for the associated standard deviations. Analytical and Bootstrap methods are used to calibrate the bias error in each of the estimators and to show that the CLUE are accurate to better than 1%.

• Journal of the Korean Statistical Society
• /
• v.7 no.2
• /
• pp.95-98
• /
• 1978

This note deals with the estimations of the variance of a normal distribution $N(\theta,c\theta^2)$ where c, the square of coefficient of variation is assumed to be known. This amounts to the estimation of $\theta^2$. The minimum variance estimator among all unbiased estimators linear in $\bar{x}^2$ and $s^2$ where $\bar{x}$ and $s^2$ are the sample mean and variance, respectively, and the minimum risk estimator in the class of all estimators linear in $\bar{x}^2$ and $s^2$ are obtained. It is shown that the suggested estimators are BAN.

• Journal of the Korean Statistical Society
• /
• v.22 no.1
• /
• pp.1-12
• /
• 1993

An approach to make the information bound sharper in median-unbiased estimation, based on an analogue of the Cramer-Rao inequality developed by Sung et al. (1990), is introduced for continuous densities with a nuisance parameter by considering information quantities contained both in the parametric function of interest and in the nuisance parameter in a linear fashion. This approach is comparable to that of improving the information bound in mean-unbiased estimation for the case of two unknown parameters. Computation of an optimal weight corresponding to the nuisance parameter is also considered.

• Communications for Statistical Applications and Methods
• /
• v.21 no.6
• /
• pp.529-538
• /
• 2014

In this paper, we consider maximum likelihood estimators of normal distribution based on type II censoring. Gupta (1952) and Cohen (1959, 1961) required a table for an auxiliary function to compute since they did not have an explicit form; however, we derive an explicit form for the estimators using a method to approximate the likelihood function. The derived estimators are a special case of Balakrishnan et al. (2003). We compare the estimators with the Gupta's linear estimators through simulation. Gupta's linear estimators are unbiased and easily calculated; subsequently, the proposed estimators have better performance for mean squared errors and variances, although they show bigger biases especially when the ratio of the complete data is small.

• East Asian mathematical journal
• /
• v.5 no.1
• /
• pp.95-110
• /
• 1989

In a general variance component model, nonnegative quadratic estimators of the components of variance are considered which are invariant with respect to mean value translaion and have minimum bias (analogously to estimation theory of mean value parameters). Here the minimum is taken over an appropriate cone of positive semidefinite matrices, after having made a reduction by invariance. Among these estimators, which always exist the one of minimum norm is characterized. This characterization is achieved by systems of necessary and sufficient condition, and by a cone restricted pseudoinverse. In models where the decomposing covariance matrices span a commutative quadratic subspace, a representation of the considered estimator is derived that requires merely to solve an ordinary convex quadratic optimization problem. As an example, we present the two way nested classification random model. An unbiased estimator is derived for the mean squared error of any unbiased or biased estimator that is expressible as a linear combination of independent sums of squares. Further, it is shown that, for the classical balanced variance component models, this estimator is the best invariant unbiased estimator, for the variance of the ANOVA estimator and for the mean squared error of the nonnegative minimum biased estimator. As an example, the balanced two way nested classification model with ramdom effects if considered.

• The Korean Journal of Applied Statistics
• /
• v.15 no.1
• /
• pp.119-128
• /
• 2002

In this paper, we consider the HB estimators of small area means with repeated survey. mao and Yu(1994) considered small area model with repeated survey data and proposed empirical best linear unbiased estimators. We propose a hierachical Bayes version of Rao and Yu by assigning prior distributions for unknown hyperparameters. We illustrate our HB estimator using very popular data in small area problem and then compare the results with the estimator of Census Bureau and other estimators previously proposed.

• Survey Research
• /
• v.11 no.1
• /
• pp.19-41
• /
• 2010

Although it is possible to provide statistically reliable estimators of the entire population parameters based on each independent rolling sample, estimators of the small areas may not have the required statistical efficiency. Thus, in general, small area estimators are calculated based on the combined rolling sample after entire rolling sample survey is finished. In this study, we considered the construction of weights that is necessary in the analysis of the combined rolling sample. Unlike the past studies that provided the empirical results for the corresponding specific rolling sample survey, we considered linear models that depends only on design variables and rolling period and provided the corresponding Best Linear Unbiased Predictor(BLUP). Through a simulation study, we proposed the estimators for the population parameters that are robust to model failure and the BLUP under the assumed model. The results are applied to the 4th Korea National Health and Nutrition Examination Survey.

• Communications for Statistical Applications and Methods
• /
• v.26 no.2
• /
• pp.91-102
• /
• 2019

In this paper, we propose a new estimation method based on a weighted linear regression framework to obtain some estimators for unknown parameters in a two-parameter Rayleigh distribution under a progressive Type-II censoring scheme. We also provide unbiased estimators of the location parameter and scale parameter which have a nuisance parameter, and an estimator based on a pivotal quantity which does not depend on the other parameter. The proposed weighted least square estimator (WLSE) of the location parameter is not dependent on the scale parameter. In addition, the WLSE of the scale parameter is not dependent on the location parameter. The results are compared with the maximum likelihood method and pivot-based estimation method. The assessments and comparisons are done using Monte Carlo simulations and real data analysis. The simulation results show that the estimators ${\hat{\mu}}_u({\hat{\theta}}_p)$ and ${\hat{\theta}}_p({\hat{\mu}}_u)$ are superior to the other estimators in terms of the mean squared error (MSE) and bias.