• Communications for Statistical Applications and Methods
• /
• v.22 no.5
• /
• pp.507-518
• /
• 2015

It is not easy to select a linear mixed model since the main interest for model building could be different and the number of parameters in the model could not be clearly defined. In this paper, performance of conditional Akaike Information Criteria and its bias-corrected version are compared with marginal Bayesian and Akaike Information Criteria through a simulation study. The results from the simulation study indicate that bias-corrected conditional Akaike Information Criteria shows promising performance when candidate models exclude large models containing the true model, but bias-corrected one prefers over-parametrized models more intensively when a set of candidate models increases. Marginal Bayesian and Akaike Information Criteria also have some difficulty to select the true model when the design for random effects is nested.

• Communications for Statistical Applications and Methods
• /
• v.6 no.1
• /
• pp.1-10
• /
• 1999

When the component proportions in mixture experiments are restricted by lower and upper bounds multicollinearity appears all too frequently. The ridge regression can be used to stabilize the coefficient estimates in the fitted model. I propose a graphical method for evaluating the mixture component effects of ridge regression estimator with respect to the prediction variance and the prediction bias.

• Communications for Statistical Applications and Methods
• /
• v.2 no.2
• /
• pp.243-248
• /
• 1995

The problem of optimal design for a nonparametric regression with binary data is considered. The aim of the statistical analysis is the estimation of a quantal response surface in two dimensions. Bias, variance and IMSE of kernel estimates are derived. The optimal design density with respect to asymptotic IMSE is constructed.

• The Korean Journal of Applied Statistics
• /
• v.25 no.4
• /
• pp.681-695
• /
• 2012

In this paper, a family of estimators for the finite population variance investigated by Srivastava and Jhajj (1980) is studied under two different situations of random non-response considered by Tracy and Osahan (1994). Asymptotic expressions for the biases and mean squared errors of members of the proposed family are obtained; in addition, an asymptotic optimum estimator(AOE) is also identified. Estimators suggested by Singh and Joarder (1998) are shown to be members of the proposed family. A correction to the Singh and Joarder (1998) results is also presented.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.165-181
• /
• 2010

This paper presents some chain ratio-type estimators for estimating finite population variance using two auxiliary variables in two phase sampling set up. The expressions for biases and mean squared errors of the suggested c1asses of estimators are given. Asymptotic optimum estimators(AOE's) in each class are identified with their approximate mean squared error formulae. The theoretical and empirical properties of the suggested classes of estimators are investigated. In the simulation study, we took a real dataset related to pulmonary disease available on the CD with the book by Rosner, (2005).

• Communications for Statistical Applications and Methods
• /
• v.17 no.4
• /
• pp.599-609
• /
• 2010

Many of financial data are explained via diffusion models in modern financial research. Various types of estimation methods of diffusion processes were suggested by many authors. In this paper, we tested the properties of the NLL estimation method, suggested by Shoji and Ozaki (1998), of diffusion processes in the view of the bias and variance of the estimators and applied the method to estimate the model parameters for the U.S. fedral funds rate data and Korean inter-bank exchange rate data. By simulation study we showed that the NLL method provides relatively good estimators, in the meaning that the estimator has less bias than the Euler method, while keeping the variance similar level. We also provide the NLL estimates of U.S fedral funds rate data and Korean inter-bank exchange rate data.

• 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).

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.361-362
• /
• 2006

Magnetic Flux Leakage (MFL) inspection is a general non-destructive testing (NDT) method to detect the corrosion of natural gas pipelines. Currently, it is subjectively analyzed by trained analysts. In spite of investing much time and human resources, the inspection results may be different according to the analysts' expertise. So, many gas suppliers are keenly interested in the automation of the interpretation process. This paper presents a Gaussian variance filtering method of MFL signals, which is taken from MFL pigging of underground pipelines. In the proposed algorithm the original MFL signals are filtered by multiple Gaussians with different variance. Experimental results show that this approach does not need to align bias and to use explicit noise reduction algorithm.

• The Korean Journal of Applied Statistics
• /
• v.7 no.1
• /
• pp.149-158
• /
• 1994

Nonparametric regression technique using kernel estimator is an attractive alternative that has received some attention, recently. The kernel estimate depends on two quantities which have to be provided by the user : the kernel function and the bandwidth. However, the more difficult problem is how to find an appropriate bandwidth which controls the amount of smoothing (see Silverman, 1986). Thus, in practical situation, it is certainly desirable to determine an appropriate bandwidth in some automatic fashion. Thus, the problem is to find a data-driven or adaptive (i.e., depending only on the data and then directly computable in practice) bandwidth that performs reasonably well relative to the best theoretical bandwidth. In this paper, we introduce a relation between bias and variance of mean square error. Thus, we present a simple and effective algorithm for selecting local bandwidths in kernel regression.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.6
• /
• pp.982-989
• /
• 2010

This paper shows accuracy comparison results of reliability estimation methods for one-shot systems such as ammunitions. Quantal-response data, following a binomial distribution at each sampling time, characterizes lifetimes of one-shot systems. Various quantal-response data of different sample sizes are simulated using lifetime data randomly sampled from assumed weibull distributions with different shape parameters but the identical scale parameter in this paper. Then, reliability estimation methods in open literature are applied to the simulated quantal-response data to estimate true reliability over time. Rankings in estimation accuracy for different sample sizes are determined using t-test of SSE. Furthermore, MSE at each time, including both bias and variance of estimated reliability metrics for each method are analyzed to investigate how much both bias and variance contribute the SSE. From the MSE analysis, MSE provides reliability estimation trend for each method. Parametric estimation method provides more accurate reliability estimation results than the other methods for most of sample sizes.