• Communications for Statistical Applications and Methods
• /
• v.28 no.5
• /
• pp.537-551
• /
• 2021

We conducted a study on a regression spline estimator with a few pre-specified auxiliary variables. For the implementation of the proposed estimators, we adapted a coordinate descent algorithm. This was implemented by considering a structure of the sum of the residuals squared objective function determined by the B-spline and the auxiliary coefficients. We also considered an efficient stepwise knot selection algorithm based on the Bayesian information criterion. This was to adaptively select smoothly functioning estimator data. Numerical studies using both simulated and real data sets were conducted to illustrate the proposed method's performance. An R software package psav is available.

• The Korean Journal of Applied Statistics
• /
• v.23 no.4
• /
• pp.651-668
• /
• 2010

Various estimators of two risk measures of a specific financial portfolio, Value-at-Risk and Expected Shortfall, are compared for each case of 1-day and 10-day horizons. We use the Korea Composite Stock Price Index data of 20-year period including the year 2008 of the global financial crisis. Indexes of five foreign stock markets are also used for the empirical comparison study. The estimator considering both the heavy tail of loss distribution and the conditional heteroscedasticity of time series is of main concern, while other standard and new estimators are considered too. We investigate which estimator is best for the Korean stock market and which one shows the best overall performance.

• Journal of the Korean Mathematical Society
• /
• v.38 no.3
• /
• pp.523-559
• /
• 2001

To predict the fate of groundwater contaminants, accurate spatially continuous information is needed. Because most field sampling of groundwater contaminants are not conducted spatially continuous manner, a special estimation technique is required to interpolate/extrapolate concentration distributions at unmeasured locations. A practical three-dimensional estimations method for in situ groundwater contaminant concentrations is introduced. It consistas of two general steps: estimation of macroscopic transport process and kriging. Using field data and nonlinear optimization techniques, the macroscopic behavior of the contaminant plume is estimated. A spatial distribution of residuals is obtained by subtracting the macroscopic transport portion from field data, then kriging is applied to estimate residuals at unsampled locations. To reduce outlier effects on obtaining correlations between residual data which are needed for determining variougram models, the R(sub)p-estimator is introduced. The proposed estimation method is applied to a field data set.

• Communications for Statistical Applications and Methods
• /
• v.6 no.1
• /
• pp.275-283
• /
• 1999

In order to estimate a parameter $(\alpha,\beta^r), r\epsilonN$, in a distribution belonging to a location-scale family we usually use best invariant estimator (BIE) and best unbiased estimator (BUE). But in some conditions Ryu (1996) showed that BIE is better than BUE. In this paper we calculate risks of BIE and BUE in a normal and an exponential distribution respectively and calculate a percentage risk improvement exponential distribution respectively and calculate a percentage risk improvement (PRI). We find the sample size n which make no significant differences between BIE and BUE in a normal distribution. And we show that BIE is always significantly better than BUE in an exponential distribution. Also simulation in a normal distribution is given to convince us of our result.

• International Journal of Reliability and Applications
• /
• v.14 no.2
• /
• pp.97-105
• /
• 2013

A stress-strength model is formulated for a multi-component system consisting of k identical components. The k components of the system with random strengths ($X_1$, $X_2$, ${\ldots}$, $X_k$) are subjected to one of the r random stresses ($X_{k+1}$, $X_{k+2}$, ${\ldots}$, $X_{k+r}$). The estimation of system reliability based on maximum likelihood estimates (MLEs) and Bayes estimators in k component system are obtained when the system is either parallel or series with the assumption that strengths and stresses follow exponential distribution. A simulation study is conducted to compare MLE and Bayes estimator through the mean squared errors of the estimators.

• Communications for Statistical Applications and Methods
• /
• v.24 no.5
• /
• pp.519-531
• /
• 2017

We consider goodness-of-fit test statistics for Weibull distributions when data are randomly censored and the parameters are unknown. Koziol and Green (Biometrika, 63, 465-474, 1976) proposed the $Cram\acute{e}r$-von Mises statistic's randomly censored version for a simple hypothesis based on the Kaplan-Meier product limit of the distribution function. We apply their idea to the other statistics based on the empirical distribution function such as the Kolmogorov-Smirnov and Liao and Shimokawa (Journal of Statistical Computation and Simulation, 64, 23-48, 1999) statistics. The latter is a hybrid of the Kolmogorov-Smirnov, $Cram\acute{e}r$-von Mises, and Anderson-Darling statistics. These statistics as well as the Koziol-Green statistic are considered as test statistics for randomly censored Weibull distributions with estimated parameters. The null distributions depend on the estimation method since the test statistics are not distribution free when the parameters are estimated. Maximum likelihood estimation and the graphical plotting method with the least squares are considered for parameter estimation. A simulation study enables the Liao-Shimokawa statistic to show a relatively high power in many alternatives; however, the null distribution heavily depends on the parameter estimation. Meanwhile, the Koziol-Green statistic provides moderate power and the null distribution does not significantly change upon the parameter estimation.

• Communications for Statistical Applications and Methods
• /
• v.26 no.5
• /
• pp.431-443
• /
• 2019

Goodness-of-fit techniques are an important topic in statistical analysis. Censored data occur frequently in survival experiments; therefore, many studies are conducted when data are censored. In this paper we mainly consider test statistics based on the empirical distribution function (EDF) to test normal distributions with unknown location and scale parameters when data are randomly censored. The most famous EDF test statistic is the Kolmogorov-Smirnov; in addition, the quadratic statistics such as the $Cram{\acute{e}}r-von$ Mises and the Anderson-Darling statistic are well known. The $Cram{\acute{e}}r-von$ Mises statistic is generalized to randomly censored cases by Koziol and Green (Biometrika, 63, 465-474, 1976). In this paper, we generalize the Anderson-Darling statistic to randomly censored data using the Kaplan-Meier estimator as it was done by Koziol and Green. A simulation study is conducted under a particular censorship model proposed by Koziol and Green. Through a simulation study, the generalized Anderson-Darling statistic shows the best power against almost all alternatives considered among the three EDF statistics we take into account.

• Journal of Korean Society for Quality Management
• /
• v.24 no.3
• /
• pp.19-30
• /
• 1996

We treat problems of estimating reliability R(t) = P[Y(t) ＞ X(t)] in the time dependent strength-stress model in which a unit of stress X(t) is subjected to environmental strength Y(t) at time t. In this paper we introduce a special model of R(t) with fixed strength and unaccumulated stress case, and propose a Mann-Whitney-Wilcoxon type estimator of R(t).

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.1
• /
• pp.76-86
• /
• 2020

Technology growth curve methodology is commonly used in technology forecasting. A technology growth curve represents the paths of product performance in relation to time or investment in R&D. It is a useful tool to compare the technological performances between Korea and advanced nations and to describe the inflection points, the limit of improvement of a technology and their technology innovation strategies, etc. However, the curve fitting to a set of survey data often leads to model mis-specification, biased parameter estimation and incorrect result since data through survey with experts frequently contain outlier in process of curve fitting due to the subjective response characteristics. This paper propose a method to eliminate of outlier from a technology growth curve using M-estimator. The experimental results prove the overall improvement in technology growth curves by several pilot tests using real-data in Defense Science and Technology Survey reports.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.17 no.3
• /
• pp.139-170
• /
• 2013

We extend a p-hierarchical decomposition of the second degree finite element space of N$\acute{e}$d$\acute{e}$lec for tetrahedral meshes in three dimensions given in [1] to meshes with hexahedral elements, and derive p-hierarchical decompositions of the second degree finite element space of Raviart-Thomas in two dimensions for triangular and quadrilateral meshes. After having proved stability of these subspace decompositions and requiring certain saturation assumptions to hold, we construct a local a posteriori error estimator for fem and bem coupling of a time-harmonic electromagnetic eddy current problem in $\mathbb{R}^3$. We perform some numerical tests to underline reliability and efficiency of the estimator and test its usefulness in an adaptive refinement scheme.