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 25, Issue 6 - Dec 2012
Volume 25, Issue 5 - Oct 2012
Volume 25, Issue 4 - Aug 2012
Volume 25, Issue 3 - Jun 2012
Volume 25, Issue 2 - Apr 2012
Volume 25, Issue 1 - Feb 2012
Selecting the target year
Study on Assumptions for Fractional Ages in Life Insurance
Lee, Soo-Bin ; Cha, Ji-Hwan ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 1~13
DOI : 10.5351/KJAS.2012.25.1.001
An assumption for fractional ages should be made to obtain the net premium of the whole life insurance payable at the moment of death based on the life table. Most existing studies adopt the assumption of the uniform distribution(UDD) for the fractional ages. However, as seasonal changes may frequently lead to the deaths of elderly people, it is questionable whether the assumption of the uniform distribution is the most appropriate one for the entire age intervals. In this article, based on a real mortality data set, the appropriateness of UDD assumption for the entire age intervals is examined. And then we propose a more suitable model for fractional ages. We analyze the effect of UDD assumption through the net premium and the corresponding risk when the true distribution for the fractional ages is not uniform.
Market Microstructure Noise and Optimal Sampling Frequencies for the Realized Variances of Stock Prices of Four Leading Korean Companies
Oh, Rosy ; Shin, Dong-Wan ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 15~27
DOI : 10.5351/KJAS.2012.25.1.015
We have studied the realized variance(RV) of intra-day returns and market microstructure noise based on high-frequency stock transaction data for the four largest companies in terms of market capitalization in the KOSPI. First, non-negligible biases are observed for the RV and for the bias-corrected realized variance(
) which is constructed by adjusting RV for the first order autocorrelation in intra-day returns. Bias is more obvious for the RV and the
when intra-day returns are sampled more frequently than every 2 minutes. Transaction Time Sampling(TTS) is shown to be better than Calendar Time Sampling(CTS) in terms of biases of the RV and the
for the 4 companies. The analysis reveals that market microstructure noise is temporally dependent. Second, by using the Noise-to-Signal Ratio(NSR), we estimate sampling frequencies that are optimal in terms of the Mean Square Errors(MSE) of the RV and the
. The optimal sampling frequencies are around 200 for RV and is around 5000 for the
for all the four stock prices. For the 6 hour transaction period of the Korean stock trading, these correspond to about 2 minutes and 6 seconds.
GARCH Model with Conditional Return Distribution of Unbounded Johnson
Jung, Seung-Hyun ; Oh, Jung-Jun ; Kim, Sung-Gon ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 29~43
DOI : 10.5351/KJAS.2012.25.1.029
Financial data such as stock index returns and exchange rates have the properties of heavy tail and asymmetry compared to normal distribution. When we estimate VaR using the GARCH model (with the conditional return distribution of normal) it shows the tendency of the lower estimation and clustering in the losses over the estimated VaR. In this paper, we argue that this problem can be resolved through the adaptation of the unbounded Johnson distribution as that of the condition return. We also compare this model with the GARCH with the conditional return distribution of normal and student-t. Using the losses exceed the ex-ante VaR, estimates, we check the validity of the GARCH models through the failure proportion test and the clustering test. We nd that the GARCH model with conditional return distribution of unbounded Johnson provides an appropriate estimation of the VaR and does not occur the clustering of violations.
Estimations for Unemployment Rate Variations in Business Coincident and Lagging Framework
Kim, Tae-Ho ; Jung, Jae-Hwa ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 45~54
DOI : 10.5351/KJAS.2012.25.1.045
Published employment statistics do not provide enough information about the relationship of unemployment and economic and business conditions. This study investigates long-run equilibrium relations and short-run adjustment process of unemployment and discouraged unemployment with major price variables in the business coincident and lagging framework. Speed of adjustment from short-run disequilibrium to long-run equilibrium is found to be relatively faster for discouraged unemployment that appears more responsive to changes in most of explanatory variables. Discouraged unemployment is found to reflect reality and suggested to be a more meaningful statistical index.
A Study of Option Pricing Using Variance Gamma Process
Lee, Hyun-Eui ; Song, Seong-Joo ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 55~66
DOI : 10.5351/KJAS.2012.25.1.055
Option pricing models using L
evy processes are suggested as an alternative to the Black-Scholes model since empirical studies showed that the Black-Sholes model could not reflect the movement of underlying assets. In this paper, we investigate whether the Variance Gamma model can reflect the movement of underlying assets in the Korean stock market better than the Black-Scholes model. For this purpose, we estimate parameters and perform likelihood ratio tests using KOSPI 200 data based on the density for the log return and the option pricing formula proposed in Madan et al. (1998). We also calculate some statistics to compare the models and examine if the volatility smile is corrected through regression analysis. The results show that the option price estimated under the Variance Gamma process is closer to the market price than the Black-Scholes price; however, the Variance Gamma model still cannot solve the volatility smile phenomenon.
Factor Analysis of Customer Loyalty in Car Insurance Using Generalized Additive Partial Linear Model
Ki, Seung-Do ; Kang, Kee-Hoon ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 67~79
DOI : 10.5351/KJAS.2012.25.1.067
The car insurance market in Korea has already entered (or is in the process of entry) a mature market that is characterized by increased competition by market participants. Participants are expected to compete more intensively in order to survive. Together with a slowdown in market growth the goal of non-life insurers' marketing strategies is to enhance existing customer loyalty because it is easier to raise their loyalty via customer satisfaction than to attract new customers in a stagnant market. In this article, we investigate what factors affect customer loyalty, and suggest some specific ways to establish and implement marketing strategies. We use a generalized additive partial linear model in order to find some significant factors.
The Ruin Probability in a Risk Model with Injections
Go, Han-Na ; Choi, Seung-Kyoung ; Lee, Eui-Yong ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 81~87
DOI : 10.5351/KJAS.2012.25.1.081
A continuous time risk model is considered, where the premium rate is constant and the claims form a compound Poisson process. We assume that an injection is made, which is an immediate increase of the surplus up to level u > 0 (initial level), when the level of the surplus goes below
< u). We derive the formula of the ruin probability of the surplus by establishing an integro-differential equation and show that an explicit formula for the ruin probability can be obtained when the amounts of claims independently follow an exponential distribution.
Investigation on Granger Causality between Economic Growth and Demand for Electricity in Korea: Using Quarterly Data
Baek, Moon-Young ; Kim, Woo-Hwan ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 89~99
DOI : 10.5351/KJAS.2012.25.1.089
This study investigates the Granger-causality between economic growth and demand for electricity in Korea, using two quarterly time-series data (real GDP and electricity consumption) for 1970:Q1 through 2009:Q4. We apply Hsiao's sequential procedure to identify a vector autoregressive model to a decision of the optimal lags in the vector error-correction model because the two time-series data contain unit roots respectively and they are cointegrated. According to the empirical results in this study, we find that Hsiao's approach to the Granger-causality indicates a bidirectional causal relation between economic growth and demand for electricity in Korea. Following the Granger and Engle's approach, we also find the statistical evidence on (1) short-run bidirectional causality between real GDP and electricity consumption, (2) bidirectional strong causality between them, and (3) long-run unidirectional causality running from demand for electricity to economic growth. Our results show an inconsistency with the existing studies on Korea's case; however, the results appear to provide more meaningful policy implications for the Korean economy and its strategy of sustainable growth.
Estimation of Car Insurance Loss Ratio Using the Peaks over Threshold Method
Kim, S.Y. ; Song, J. ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 101~114
DOI : 10.5351/KJAS.2012.25.1.101
In car insurance, the loss ratio is the ratio of total losses paid out in claims divided by the total earned premiums. In order to minimize the loss to the insurance company, estimating extreme quantiles of loss ratio distribution is necessary because the loss ratio has essential prot and loss information. Like other types of insurance related datasets, the distribution of the loss ratio has heavy-tailed distribution. The Peaks over Threshold(POT) and the Hill estimator are commonly used to estimate extreme quantiles for heavy-tailed distribution. This article compares and analyzes the performances of various kinds of parameter estimating methods by using a simulation and the real loss ratio of car insurance data. In addition, we estimate extreme quantiles using the Hill estimator. As a result, the simulation and the loss ratio data applications demonstrate that the POT method estimates quantiles more accurately than the Hill estimation method in most cases. Moreover, MLE, Zhang, NLS-2 methods show the best performances among the methods of the GPD parameters estimation.
Statistical Analysis of Bivariate Current Status Data with Informative Censoring Using Frailty Effects
Kim, Yang-Jin ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 115~123
DOI : 10.5351/KJAS.2012.25.1.115
In animal tumorigenicity data, tumor onsets occur at several sites and onset times cannot be exactly observed. Instead, the existence of tumors is examined only at death time or sacrifice time of the animal. Such an incomplete data structure makes it difficult to investigate the effect of treatment on tumor onset times; in addition, such dependence should be considered when censoring due to death is related with tumor onset. A bivariate frailty effect is incorporated to model bivariate tumor onsets and to connect death with tumor. For the inference of parameters, EM algorithm is applied and a real NTP(National Toxicology Program) dataset is analyzed as an illustrative example.
Statistical Consideration of the Development of Biosimilar Products
Kang, Seung-Ho ; Nam, Ju-Sun ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 125~138
DOI : 10.5351/KJAS.2012.25.1.125
Recent assessments of the biosimilarity of biologic products have received considerable global attention. A clinical trial should be conducted to assess the biosimilarity of a biosimilar product and a innovator biological product. In this paper we will describe several methods for the implementation of clinical trials and statistical analysis, a real international case and related international guidelines.
Model Validation Methods of Population Pharmacokinetic Models
Lee, Eun-Kyung ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 139~152
DOI : 10.5351/KJAS.2012.25.1.139
The result of the analysis of a population pharmacokinetic model can directly influence the decision of the dose level applied to the targeted patients. Therefore the validation procedure of the final model is very important in this area. This paper reviews the validation methods of population pharmacokinetic models from a statistical viewpoint. In addition, the whole procedure of the analysis of population pharmacokinetics, from the base model to the final model (that includes various validation procedures for the final model) is tested with real clinical data.
A Case Study of Mixed-Mode Design Incorporated Mobile RDD into Telephone RDD
Lee, Kay-O ; Jang, Duk-Hyun ; Hong, Young-Taek ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 153~162
DOI : 10.5351/KJAS.2012.25.1.153
We proposed a mixed-mode design with a landline survey and mobile survey as the solution for the problems of election opinion polls by the original telephone survey method, mostly with limited population coverage for young people not living at home and with lower efficiency in selecting valid voters. We numerically verified the applicability of the proposed dual frame survey by analyzing the preliminary opinion poll results of the Seoul mayor by-election of October 26 2011. This research achieved the result that relative standard errors were similar between a mobile RDD sample and landline RDD sample though the variance was bigger in the former. Though the combination of mobile RDD and landline RDD is not found to improve the forecast accuracy, it still is expected to have higher reliability for election polls by expanding the population coverage and compensating the weakness of each survey method.
Estimation and Sensitivity Analysis on the Effect of Job Training for Non-Regular Employees
Lee, Sang-Jun ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 163~181
DOI : 10.5351/KJAS.2012.25.1.163
This paper studies the effect of job training for non-regular employees in the Korea labor market. Using an economically active population data set of statistics Korea, we apply a non-parametric matching and sensitivity analysis method to measure the effect of the training for non-regular employees and to look for the impact of an unobservable variable or confounding factor in regards to the selection effect and outcome effect. In the our empirical results, we conclude that the effect of the training for non-regular employees has a better employment effect for getting a regular job rather than a wage effect; in addition, the impact of unobservable variables or confounding factors do not exercise a statistically strong influence on the baseline ATT.
Metropolis-Hastings Expectation Maximization Algorithm for Incomplete Data
Cheon, Soo-Young ; Lee, Hee-Chan ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 183~196
DOI : 10.5351/KJAS.2012.25.1.183
The inference for incomplete data such as missing data, truncated distribution and censored data is a phenomenon that occurs frequently in statistics. To solve this problem, Expectation Maximization(EM), Monte Carlo Expectation Maximization(MCEM) and Stochastic Expectation Maximization(SEM) algorithm have been used for a long time; however, they generally assume known distributions. In this paper, we propose the Metropolis-Hastings Expectation Maximization(MHEM) algorithm for unknown distributions. The performance of our proposed algorithm has been investigated on simulated and real dataset, KOSPI 200.
Pointwise Estimation of Density of Heteroscedastistic Response in Regression
Hyun, Ji-Hoon ; Kim, Si-Won ; Lee, Sung-Dong ; Byun, Wook-Jae ; Son, Mi-Kyoung ; Kim, Choong-Rak ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 197~203
DOI : 10.5351/KJAS.2012.25.1.197
In fitting a regression model, we often encounter data sets which do not follow Gaussian distribution and/or do not have equal variance. In this case estimation of the conditional density of a response variable at a given design point is hardly solved by a standard least squares method. To solve this problem, we propose a simple method to estimate the distribution of the fitted vales under heteroscedasticity using the idea of quantile regression and the histogram techniques. Application of this method to a real data sets is given.
Robust Response Transformation Using Outlier Detection in Regression Model
Seo, Han-Son ; Lee, Ga-Yoen ; Yoon, Min ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 205~213
DOI : 10.5351/KJAS.2012.25.1.205
Transforming response variable is a general tool to adapt data to a linear regression model. However, it is well known that response transformations in linear regression are very sensitive to one or a few outliers. Many methods have been suggested to develop transformations that will not be influenced by potential outliers. Recently Cheng (2005) suggested to using a trimmed likelihood estimator based on the idea of the least trimmed squares estimator(LTS). However, the method requires presetting the number of outliers and needs many computations. A new method is proposed, that can solve the problems addressed and improve the robustness of the estimates. The method uses a stepwise procedure, suggested by Hadi and Simonoff (1993), to detect outliers that determine response transformations.
3-Level Response Surface Design by Using Expanded Spherical Experimental Region
Kim, Ha-Yan ; Lee, Woo-Sun ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 215~223
DOI : 10.5351/KJAS.2012.25.1.215
Response surface methodology(RSM) is a very useful statistical techniques for improving and optimizing the product process. By this reason, RSM has been utilized extensively in the industrial world, particularly in the circumstances where several product variables potentially influence some quality characteristic of the product. In order to estimate the optimal condition of product variables, an experiment is being conducted defining appropriate experimental region. However, this experimental region can vary with the experimental circumstances and choice of a researcher. Response surface designs can be classified, according to the shape of the experimental region, into spherical and cuboidal. In the spherical case, the design is either rotatable or very near-rotatable. The central composite design(CCD)s widely used in RSM is an example of 5-level and spherical design. The cuboidal CCDs(CCDs with
) is appropriate when an experimental region is cuboidal but this design dose not satisfy the rotatability as it is not spherical. Practically, a 3-level spherical design is often required in the industrial world where various level of experiments are not available. Box-Behnken design(BBD)s are a most popular 3-level spherical designs for fitting second-order response surfaces and satisfy the rotatability but the experimental region does not vary with the number of variables. The new experimental design with expanded experimental region can be considered if the predicting response at the extremes are interested. This paper proposes a new 3-level spherical RSM which are constructed to expand the experimental region together with number of product variables.
Generalization of Quantification for PLS Correlation
Yi, Seong-Keun ; Huh, Myung-Hoe ;
Korean Journal of Applied Statistics, volume 25, issue 1, 2012, Pages 225~237
DOI : 10.5351/KJAS.2012.25.1.225
This study proposes a quantification algorithm for a PLS method with several sets of variables. We called the quantification method for PLS with more than 2 sets of data a generalization. The basis of the quantification for PLS method is singular value decomposition. To derive the form of singular value decomposition in the data with more than 2 sets more easily, we used the constraint,
, for instance, in the case of 3 data sets. However, to prove that there is no difference, we showed it by the use of 2 data sets case because it is very complicate to prove with 3 data sets. The keys of the study are how to form the singular value decomposition and how to get the coordinates for the plots of variables and observations.