Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Korean Journal of Applied Statistics
Journal Basic Information
Journal DOI :
The Korean Statistical Society
Editor in Chief :
Volume & Issues
Volume 24, Issue 6 - Dec 2011
Volume 24, Issue 5 - Oct 2011
Volume 24, Issue 4 - Aug 2011
Volume 24, Issue 3 - Jun 2011
Volume 24, Issue 2 - Apr 2011
Volume 24, Issue 1 - Feb 2011
Selecting the target year
Test for Theory of Portfolio Diversification
Kim, Tae-Ho ; Won, Youn-Jo ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 1~10
DOI : 10.5351/KJAS.2011.24.1.001
This study investigates the dynamic structure of interdependence on the domestic and related major stock markets by employing a statistical framework. Finance theory predicts potential gains by international portfolio diversification if returns from investment in different national stock markets are not perfectly correlated or not cointegrated. The benefit of international diversification is limited when national stock markets are cointegrated because of the limited amount of independent variation by the presence of common factors. The statistical tests suggest that international diversification appears to be favorable after the period of the comovement of the stock prices caused by 1997 Asian financial crisis. The result reflects the increase in overseas investment and purchase of overseas funds after the early 2000's.
Robust Unit Root Tests for a Panel TAR Model
Shin, Dong-Wan ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 11~23
DOI : 10.5351/KJAS.2011.24.1.011
Robust unit root tests are developed for dynamic panels consisting of TAR processes. The test statistics are all based on diverse combinations of individual t-type tests for significance of TAR coefficients. Limiting null distributions are established. A Monte-Carlo experiment compares the proposed tests. The tests are applied to a panel data set of Canadian unemployment rates which show asymmetric features as well as having outliers.
A Study on the Decision of Sample Size for Panel Survey Design
Yoo, Yang-Sang ; Shin, Key-Il ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 25~34
DOI : 10.5351/KJAS.2011.24.1.025
The transition probability can be used for the estimation of subpopulation total in panel data analysis. In this paper a real data analysis is performed and the sensitivity of the sample size allocated in the subpopulation is examined by small simulation studies.
A Unit Root Test via a Discrete Cosine Transform
Lee, Go-Un ; Yeo, In-Kwon ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 35~43
DOI : 10.5351/KJAS.2011.24.1.035
In this paper, we introduce a unit root test via discrete cosine transform in the AR(1) process. We first investigate the statistical properties of DCT coefficients under the stationary AR(1) process and the random walk process in order to verify the validity of the proposed method. A bootstrapping approach is proposed to induce the distribution of the test statistic under the unit root. We performed simulation studies for comparing the powers of the Dickey-Fuller test and the proposed test.
Smooth Tests for Seasonality
Lee, Geung-Hee ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 45~59
DOI : 10.5351/KJAS.2011.24.1.045
When using X-12-ARIMA for seasonal adjustment, we usually check whether the series has stable seasonality or not via D8 F-tests, Kruskal-Wallis test, and the spectral diagnostics. In this paper, we develop several smooth tests for seasonality based on a Fourier series to improve the spectral diagnostics of X-12-ARIMA. A simulation study is conducted to compare five smooth tests for seasonality and X-12-ARIMA's D8 F-test an Kruskal-Wallis test. The simulation study shows that smooth tests for seasonality performed well compared with D8 F-tests and a Kruskal-Wallis test.
Quadratic GARCH Models: Introduction and Applications
Park, Jin-A ; Choi, Moon-Sun ; Hwan, Sun-Young ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 61~69
DOI : 10.5351/KJAS.2011.24.1.061
In GARCH context, the conditional variance (or volatility) is of a quadratic function of the observation process. Examine standard ARCH/GARCH and their variant models in terms of quadratic formulations and it is interesting to note that most models in GARCH context have contained neither the first order term nor the interaction term. In this paper, we consider three models possessing the first order and/or interaction terms in the formulation of conditional variances, viz., quadratic GARCH, absolute value GARCH and bilinear GARCH processes. These models are investigated with a view to model comparisons and applications to financial time series in Korea
An Empirical Analysis of KOSPI Volatility Using GARCH-ARJI Model
Kim, Woo-Hwan ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 71~81
DOI : 10.5351/KJAS.2011.24.1.071
In this paper, we systematically analyzed the variation of KOSPI returns using a GARCH-ARJI(auto regressive jump intensity) model. This model is possibly to capture time varying volatility as well as time varying conditional jump intensity. Thus, we can decompose return volatility into usual variation explained by the GARCH model and unusual variation that resulted from external news or shocks. We found that the jump intensity implied on KOSPI return series clearly shows time varying. We also found that conditional volatility due to jump is generally smaller than that resulted from usual variation. We also analyzed the effect of 9.11 and the 2008 financial crisis on the volatility of KOSPI returns and conclude that there is strong and persistent impact on the KOSPI from the 2008 financial crisis.
Asset Pricing From Log Stochastic Volatility Model: VKOSPI Index
Oh, Yu-Jin ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 83~92
DOI : 10.5351/KJAS.2011.24.1.083
This paper examines empirically Durham's (2008) asset pricing models to the KOSPI200 index. This model Incorporates the VKOSPI index as a proxy for 1 month integrated volatility. This approach uses option prices to back out implied volatility states with an explicitly speci ed risk-neutral measure and risk premia estimated from the data. The application uses daily observations of the KOSPI200 and VKOSPI indices from January 2, 2003 to September 24, 2010. The empirical results show that non-affine model perform better than affine model.
A Study on the Seasonal Effects of the Tourism Demand Forecasting Models
Kim, Sahm ; Lee, Ju-Hyoung ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 93~102
DOI : 10.5351/KJAS.2011.24.1.093
In this paper, we compared the performance of the several time series models for tourism demand forecasting. We showed that seasonal effects in the data(Japan, China, USA, and Philippines) exist in the tourism data and the forecasting accuracies are compared by the RMSE criterion.
Impact of the Change in Market Conditions on a Test for Market Cointegration
Kim, Tae-Ho ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 103~114
DOI : 10.5351/KJAS.2011.24.1.103
Current series for testing stock market cointegrations tend to be restricted to analyzing the relations between stock market prices and may not be able to understand the whole picture of the variations in the stock market system. The nature of the variations in the stock prices, between the countries that experienced economic crisis and those did not, are different for a certain period of time, and accordingly excluding the potentially important variables in the stock market system causes statistical bias. This study considers domestic foreign exchange markets and financial markets in testing for the cointegrating relations of the stock prices in Korea and major investing countries. The results demonstrate the possibility of specification errors unless those markets are included in the statistical modeling process.
A Comparison Study for Mortality Forecasting Models by Average Life Expectancy
Jeong, Seung-Hwan ; Kim, Kee-Whan ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 115~125
DOI : 10.5351/KJAS.2011.24.1.115
By use of a mortality forecasting model and a life table, forecasting the average life expectancy is an effective way to evaluate the future mortality level. There are differences between the actual values of average life expectancy at present and the forecasted values of average life expectancy in population projection 2006 from Statistics Korea. The reason is that the average life expectancy forecasts did not reflect the increasing speed of the actual ones. The main causes of the problem may be errors from judgment for projection, from choice, or use of a mortality forecasting model. In this paper, we focus on the choice of the mortality forecasting model to inspect this problem. Statistics Korea should take a mortality forecasting model with considerable investigation to proceed population projection 2011 without the errors observed in population projection 2006. We compare the five mortality forecasting models that are the LC(Lee and Carter) model used widely and its variants, and the HP8(Heligman and Pollard 8 parameter) model for handling death probability. We make average life expectancy forecasts by sex using modeling results from 2010 to 2030 and compare with that of the population projection 2006 during the same period. The average life expectancy from all five models are forecasted higher than that of the population projection 2006. Therefore, we show that the new average life expectancy forecasts are relatively suitable to the future mortality level.
Application of a Statistical Disclosure Control Techniques Based on Multiplicative Noise
Kim, Young-Won ; Kim, Tae-Yeon ; Ki, Kye-Nam ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 127~136
DOI : 10.5351/KJAS.2011.24.1.127
Multiplicative noise model is the one of popular method for masking continuous variables. In this paper, we propose the transformation on the variable to which random noise was multiplied. An advantage of the masking method using proposed transformation is that the masking data users can obtain the unbiased values of mean and variance of original (unmasked) data. We also consider the data utility and correlation structure of variables when we apply the proposed multiplicative noise scheme. To investigate the properties of the method of masking based on multiplicative noise, a simulation study has been conducted using the 2008 Householder Income and Expenditure Survey data.
Order-Restricted Inference with Linear Rank Statistics in Microarray Data
Kang, Moon-Su ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 137~143
DOI : 10.5351/KJAS.2011.24.1.137
The classification of subjects with unknown distribution in a small sample size often involves order-restricted constraints in multivariate parameter setups. Those problems make the optimality of a conventional likelihood ratio based statistical inferences not feasible. Fortunately, Roy (1953) introduced union-intersection principle(UIP) which provides an alternative avenue. Multivariate linear rank statistics along with that principle, yield a considerably appropriate robust testing procedure. Furthermore, conditionally distribution-free test based upon exact permutation theory is used to generate p-values, even in a small sample. Applications of this method are illustrated in a real microarray data example (Lobenhofer et al., 2002).
A Determining System for the Category of Need in Long-Term Care Insurance System using Decision Tree Model
Han, Eun-Jeong ; Kwak, Min-Jeong ; Kan, Im-Oak ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 145~159
DOI : 10.5351/KJAS.2011.24.1.145
National long-term care insurance started in July, 2008. We try to make up for weak points and develop a long-term care insurance system. Especially, it is important to upgrade the rating model of the category of need for long-term care continually. We improve the rating model using the data after enforcement of the system to reflect the rapidly changing long-term care marketplace. A decision tree model was adpoted to upgrade the rating model that makes it easy to compare with the current system. This model is based on the first assumption that, a person with worse functional conditions needs more long-term care services than others. Second, the volume of long-term care services are de ned as a service time. This study was conducted to reflect the changing circumstances. Rating models have to be continually improved to reflect changing circumstances, like the infrastructure of the system or the characteristics of the insurance beneficiary.
Assessing Average Bioequivalence for 2×2 Crossover Design with Covariates
Jeong, Gyu-Jin ; Park, Sang-Gue ; Kim, Kwan-Yup ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 161~167
DOI : 10.5351/KJAS.2011.24.1.161
The primary variables are often systematically related to other influences apart from drug effect. For instance, there may be relationships to covariates such as health conditions or prognostic factors. When a
crossover experiment for bioequivalence is designed, the statistical adjustment for the influence of covariates should be considered if some covariates influence the drug effect. Statistical inference for assessing average bioequivalence for a
crossover design with covariates is given and an illustrated example is presented with discussion.
Effects of the New Method of Computing Percentage of Victories on 2009~2010 Korea Professional Baseball and Suggestion of Complementary Measures
Kim, Hyuk-Joo ; Lee, Hyun-Jeong ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 169~175
DOI : 10.5351/KJAS.2011.24.1.169
Since 2009, a new method of computing the percentage of victories is being used in the regular league of the Korean professional baseball. This method produced enormous results from the first year of application, and also had an effect on the team standings in 2010. In this paper, we have examined the effects this method had on the Korean professional baseball in 2009 and 2010. We also have discussed what the Korea Baseball Organization need to complement in using this method and suggested complementary measures.
Hyper-Parameter in Hidden Markov Random Field
Lim, Jo-Han ; Yu, Dong-Hyeon ; Pyu, Kyung-Suk ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 177~183
DOI : 10.5351/KJAS.2011.24.1.177
Hidden Markov random eld(HMRF) is one of the most common model for image segmentation which is an important preprocessing in many imaging devices. The HMRF has unknown hyper-parameters on Markov random field to be estimated in segmenting testing images. However, in practice, due to computational complexity, it is often assumed to be a fixed constant. In this paper, we numerically show that the segmentation results very depending on the fixed hyper-parameter, and, if the parameter is misspecified, they further depend on the choice of the class-labelling algorithm. In contrast, the HMRF with estimated hyper-parameter provides consistent segmentation results regardless of the choice of class labelling and the estimation method. Thus, we recommend practitioners estimate the hyper-parameter even though it is computationally complex.
AROC Curve and Optimal Threshold
Hong, Chong-Sun ; Lee, Hee-Jung ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 185~191
DOI : 10.5351/KJAS.2011.24.1.185
In the credit evaluation study with the assumption of mixture distributions, the ROC curve is a useful method to explore the discriminatory power of default and non-default borrowers. The AROC curve is an adjusted ROC curve that can be identified with the corresponding score and is mathematically analyzed in this work. We obtain patterns of this curve by applying normal distributions. Moreover, the relationship between the AROC curve and many classification accuracy statistics are explored to find the optimal threshold. In the case of equivalent variances of two distributions, we obtain that the local minimum of the AROC curve is estimated at the optimal threshold to maximize certain classification accuracies.
Statistical Analysis of Private Education Expenses in Korea
Oh, Man-Suk ; Kim, Jin-Hee ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 193~206
DOI : 10.5351/KJAS.2011.24.1.193
Due to the great impact of private education expenses on many areas including economics and politics, reducing private education expenses is one of the key issues in Korea. In this paper, we analyze the data from a survey on private education expenses, conducted by Statistics, Korea, in 2008. We study the effect of some demographic variables on two dependent variables, the expenses for out-of-school private education (Private) and the expenses for after-school programs (Afterschool), by using a multiple linear regression model. The analysis results show that 'residential area' and 'school level' variables have a significant effect on the two dependent variables. 'Private' increases in the order of small town, middle town, or metropolitan city, and Seoul, by about 7%. On the other hand, 'Afterschool' are about the same for all areas except for the small town. In terms of the effect of 'school level', 'Private' for high school students is about 17% larger than all other students including professional high school students. This shows a strong correlation between university admission and private education, in Korea. 'Afterschool' is larger for high school and elementary school students and decreases in the order of professional school students and middle school students. It seems that after-school programs are alternatives to expensive private education programs for elementary school students, and that high school students are attracted to after-school programs to get a good GPA, which is important for university admissions.
Bootstrap Estimation for GEE Models
Park, Chong-Sun ; Jeon, Yong-Moon ;
Korean Journal of Applied Statistics, volume 24, issue 1, 2011, Pages 207~216
DOI : 10.5351/KJAS.2011.24.1.207
Bootstrap is a resampling technique to find an estimate of parameters or to evaluate the estimate. This technique has been used in estimating parameters in linear model(LM) and generalized linear model(GLM). In this paper, we explore the possibility of applying Bootstrapping Residuals, Pairs, and an Estimating Equation that are most widely used in LM and GLM to the generalized estimating equation(GEE) algorithm for modelling repeatedly measured regression data sets. We compared three bootstrapping methods with coefficient and standard error estimates of GEE models from one simulated and one real data set. Overall, the estimates obtained from bootstrap methods are quite comparable, except that estimates from bootstrapping pairs are somewhat different from others. We conjecture that the strange behavior of estimates from bootstrapping pairs comes from the inconsistency of those estimates. However, we need a more thorough simulation study to generalize it since those results are coming from only two small data sets.