Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Communications for Statistical Applications and Methods
Journal Basic Information
Journal DOI :
The Korean Statistical Society
Editor in Chief :
Volume & Issues
Volume 17, Issue 6 - Nov 2010
Volume 17, Issue 5 - Sep 2010
Volume 17, Issue 4 - Jul 2010
Volume 17, Issue 3 - May 2010
Volume 17, Issue 2 - Mar 2010
Volume 17, Issue 1 - Jan 2010
Selecting the target year
Cost Ratios for Cost and ROC Curves
Hong, Chong-Sun ; Yoo, Hyun-Sang ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 755~765
DOI : 10.5351/CKSS.2010.17.6.755
For classification problems on mixture distribution, a threshold based on cost functions is optimal from the viewpoint of a minimum expected cost. Assuming that there is no cost information, we propose cost ratios in the expected cost corresponding to thresholds where the total accuracy and the true rate are maximized to explain the relation of these cost ratios minimizing the expected cost. Other cost ratios are also proposed by comparing the normalized expected costs when classification accuracy is maximized. The values of these cost ratios are located between two cost ratios for the expected costs based on classification accuracies, and converge to that of the minimum expected cost. This work suggests two cost ratios: one is minimized by the expected cost and the normalized expected cost, and the other in the expected cost and the normalized expected cost functions that are maximized classification accuracies. We discuss their compatibility based on the relation of these cost ratios.
Passenger Car Demand and Polarized Economic Development in Korea
Kim, Hyun-Chul ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 767~777
DOI : 10.5351/CKSS.2010.17.6.767
This paper investigates the relationship between the passenger car demand and business activities in the OECD. The positively linear relationships changed suddenly since 1990 and the reason was thought to be the polarized economic development of USA and Japan. The cases of other countries supports this conclusion. According to the conclusion, we modeled and estimated the car demand function of Korea.
Deciding Relative Importance of Factors in Evaluating Public Trust of Soccer Commentators Using Fuzzy AHP
You, Kang-Won ; Choi, Kyoung-Ho ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 779~789
DOI : 10.5351/CKSS.2010.17.6.779
Sport commentators play an increasingly influential role in commercial sports broadcasting. Public trust is regarded as one of the most significant qualifications for sport commentators and this study used a Fuzzy AHP method in deciding the relative importance of professionalism, reliability, dynamic, and narrative skill. Based on the results, we conducted an evaluation of the public trust for the four SBS sport commentators for the 2010 South-Africa World Cup. The conclusion showed that professionalism and narrative skill were regarded as the most important factors for sport commentators to gain public trust. Among the four commentators evaluated, commentator # 1 got highest score overall, the soccer expert group highly appreciated commentator # 2, and the non-expert group highly appreciated commentator # 3.
The Decision of Critical Population Size for Releasing Micro Data Files
NamKung, Pyong ; So, Joung-Hyun ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 791~801
DOI : 10.5351/CKSS.2010.17.6.791
This study reviews the concept of disclosure, disclosure risks, and uniqueness. The number of uniqueness in the population is of great importance in evaluating the disclosure risk of micro data files. We approach this problem by considering some basic superpopulation models including the Multinomial-Dirichlet model, the Poisson- Gamma model of Bethlehem et al. (1990) and Takemura (1997), and the Modified Multinomial-Dirichlet model. We decided the critical population size of each superpopulation model for four different superpopulation models.
Robust Singular Value Decomposition BaLsed on Weighted Least Absolute Deviation Regression
Jung, Kang-Mo ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 803~810
DOI : 10.5351/CKSS.2010.17.6.803
The singular value decomposition of a rectangular matrix is a basic tool to understand the structure of the data and particularly the relationship between row and column factors. However, conventional singular value decomposition used the least squares method and is not robust to outliers. We propose a simple robust singular value decomposition algorithm based on the weighted least absolute deviation which is not sensitive to leverage points. Its implementation is easy and the computation time is reasonably low. Numerical results give the data structure and the outlying information.
Truncation Parameter Selection in Binary Choice Models
Kim, Kwang-Rae ; Cho, Kyu-Dong ; Koo, Ja-Yong ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 811~827
DOI : 10.5351/CKSS.2010.17.6.811
This paper deals with a density estimation method in binary choice models that can be regarded as a statistical inverse problem. We use an orthogonal basis to estimate density function and consider the choice of an appropriate truncation parameter to reflect the model complexity and the prediction accuracy. We propose a data-dependent rule to choose the truncation parameter in the context of binary choice models. A numerical simulation is provided to illustrate the performance of the proposed method.
Effects of Overdispersion on Testing for Serial Dependence in the Time Series of Counts Data
Kim, Hee-Young ; Park, You-Sung ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 829~843
DOI : 10.5351/CKSS.2010.17.6.829
To test for the serial dependence in time series of counts data, Jung and Tremayne (2003) evaluated the size and power of several tests under the class of INARMA models based on binomial thinning operations for Poisson marginal distributions. The overdispersion phenomenon(i.e., a variance greater than the expectation) is common in the real world. Overdispersed count data can be modeled by using alternative thinning operations such as random coefficient thinning, iterated thinning, and quasi-binomial thinning. Such thinning operations can lead to time series models of counts with negative binomial or generalized Poisson marginal distributions. This paper examines whether the test statistics used by Jung and Tremayne (2003) on serial dependence in time series of counts data are affected by overdispersion.
Accuracy Measures of Empirical Bayes Estimator for Mean Rates
Jeong, Kwang-Mo ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 845~852
DOI : 10.5351/CKSS.2010.17.6.845
The outcomes of counts commonly occur in the area of disease mapping for mortality rates or disease rates. A Poisson distribution is usually assumed as a model of disease rates in conjunction with a gamma prior. The small area typically refers to a small geographical area or demographic group for which very little information is available from the sample surveys. Under this situation the model-based estimation is very popular, in which the auxiliary variables from various administrative sources are used. The empirical Bayes estimator under Poissongamma model has been considered with its accuracy measures. An accuracy measure using a bootstrap samples adjust the underestimation incurred by the posterior variance as an estimator of true mean squared error. We explain the suggested method through a practical dataset of hitters in baseball games. We also perform a Monte Carlo study to compare the accuracy measures of mean squared error.
A Study on the Improvement of Sampling Rate of Performance Test in Public Survey
Kim, Kyu-Seong ; Lee, Young-Min ; Jung, Byung-Chul ; Choi, Yoon-Soo ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 853~863
DOI : 10.5351/CKSS.2010.17.6.853
The performance test in a public survey is conducted by a sample survey and the sampling rate of the performance test is a very important factor in the test process. Since the current sampling rate was decided empirically at an earlier time, it has been criticized for two points: the first is that it has a lack of a theoretical background on the decision for the sampling rate and the second is that the sampling rate should be improved in accordance with current test situations. In this paper, we review the present state of performance tests in public surveys in Korea and study the relationship between the rate of the performance test and fitness probability, number of tests, and the success rate in order to create a theoretical background to improve the test rate. In addition, we discuss relationship between the test rate and cost in the performance test.
Preventive Maintenance Model after Minimal Repair Warranty
Jung, Ki-Mun ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 865~877
DOI : 10.5351/CKSS.2010.17.6.865
This paper considers the periodic preventive maintenance model for a repairable system following warranty expiration. We consider three types of warranty policies: free repair warranty, pro-rata repair warranty, and combination repair warranty. Under these preventive maintenance models, we derive the expressions for the expected cycle length, the total expected cost, and the expected cost rate per unit time. In addition, we explain the optimal preventive maintenance period and the optimal preventive maintenance number by minimizing the expected cost rate per unit time. Finally, the optimal periodic preventive maintenance policy is given for a Weibull distribution case.
System of Culture Satellite Account
Kim, Ji-Young ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 879~889
DOI : 10.5351/CKSS.2010.17.6.879
In this paper I summarize the compiling method of culture satellite account which has been recommended by international statistic organizations, and I suggest the required statistics which is need to compile Korean culture satellite account. Culture satellite account is recommended to be composed of five modules and each module has to has its specific function respectively. The first module is macro-information module, the second module is quantity/volume output module, the third module is characterization module, the fourth module is targeted analysis/analytical module, and the fifth module is documentation module. Each module is recommended to contain cultural demand and supply statistics of respective module from the first module to the fourth module.
Evaluation of Software Task Processing Based on Markovian Imperfect Debugging Model and Its Release Policy
Kim, U-Jung ; Lee, Chong-Hyung ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 891~898
DOI : 10.5351/CKSS.2010.17.6.891
In real software development fields, software is unified by several modules that are developed before the software testing period. For the evaluation of software task processing performance, this paper considers the software imperfect debugging model that is proposed by Lee and Park (2003) and presents the measures of a unified software, such as the completion probability of a task which is completed in a time interval and the expected number of the completed tasks. In addition, we suggest a software release policy that satisfies the required level of the expected perfect debugging, completion probability, and availability.
Non-Response Imputation for Panel Data
Pak, Gi-Deok ; Shin, Key-Il ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 899~907
DOI : 10.5351/CKSS.2010.17.6.899
Several non-response imputation methods are suggested, however, mainly cross-sectional imputations are studied and applied to this analysis. A simple and common imputation method for panel data is the cross-wave regression imputation or carry-over imputation as a special case of cross-wave regression imputation. This study suggests a multiple imputation method combined time series analysis and cross-sectional multiple imputation method. We compare this method and the cross-wave regression imputation method using MSE, MAE, and Bias. The 2008 monthly labor survey data is used for this study.
Selection of a Predictive Coverage Growth Function
Park, Joong-Yang ; Lee, Gye-Min ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 909~916
DOI : 10.5351/CKSS.2010.17.6.909
A trend in software reliability engineering is to take into account the coverage growth behavior during testing. A coverage growth function that represents the coverage growth behavior is an essential factor in software reliability models. When multiple competitive coverage growth functions are available, there is a need for a criterion to select the best coverage growth functions. This paper proposes a selection criterion based on the prediction error. The conditional coverage growth function is introduced for predicting future coverage growth. Then the sum of the squares of the prediction error is defined and used for selecting the best coverage growth function.
A Study on the Relationship between Physique, Physical Fitness and Basic Skill Factors of Tennis Players in the Korea Tennis Association Using the Generalized Canonical Correlation Biplot and Procrustes Analysis
Choi, Tae-Hoon ; Choi, Yong-Seok ;
Communications for Statistical Applications and Methods, volume 17, issue 6, 2010, Pages 917~925
DOI : 10.5351/CKSS.2010.17.6.917
The canonical correlation biplot is a 2-dimensional plot for graphically investigating the relationship between two sets of variables and the relationship between observations and variables in the canonical correlation analysis. Recently, Choi and Choi (2008) suggested a method for investigating the relationship between skill and competition score factors of KLPGA players using this biplot. Choi et al. (2010) used this biplot to analyze the player characteristic factors and competitive factors of tennis Grand Slam competition. Moreover, Huh (1999) provided a generalized canonical correlation analysis and biplot for more than three sets of variables. A Procrustes analysis is a useful tool for comparing shapes between configurations. This study will provide a method to investigate the relationship between physique, physical fitness and basic skill factors of tennis players in the Korea Tennis Association using a generalized canonical correlation biplot and Procrustes analysis.