• The Korean Journal of Applied Statistics
• /
• v.25 no.1
• /
• pp.101-114
• /
• 2012

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.

• Journal of Microbiology and Biotechnology
• /
• v.12 no.3
• /
• pp.449-456
• /
• 2002

The objective of this study was to optimize medium composition of initial pH, tryptone, glucose, yeast extract, and mineral mixture for production of bacteriocin by Lactobacillus acidophilus ATCC 4356, using response surface methodology. A response surface approach including new statistical and plotting methods was employed for design and analysis of the experiment. An interiorly augmented central composite design was used as an experimental design. A normal-distribution log-link generalized linear model based on a subset fourth-order polynomial ($R^2$=0.94, Mean Error Deviance=0.0065) was used as an analysis model. This model was statistically superior to the full second-order polynomial-based generalized linear model ($R^2$=0.80, Mean Error Deviance=0.0140). Nonlinear programming determined the optimum composition of the medium as initial pH 6.35, typtone $1.21\%$, glucose $0.9\%$, yeast extract $0.65\%$, and mineral mixture $1.17\%$. A validation experiment confirmed that the optimized medium was comparable to the MRS medium in bacteriocin production, having the advantage of economy and practicality.

• 한국데이터정보과학회:학술대회논문집
• /
• 2002.06a
• /
• pp.9-15
• /
• 2002

This paper presents the seasonal forecasting of the occurrence of tropical cyclone (TC) over Western North Pacific (WNP) using the generalized linear model (GLM) and dynamic linear model (DLM) based on 51-year-data (1951-2001) in TC season (June to November). The numbers of TC and TY are predictands and 16 indices (the E1 Nino/Southern Oscillation, the synoptic factors over East asia and WNP) are considered as potential predictors. With 30-year moving windowing, the estimation and prediction of TC and TY are performed using GLM. If GLM forecasts have some systematic error like a bias, DLM is applied to remove the systematic error in order to improve the accuracy of prediction.

• Communications for Statistical Applications and Methods
• /
• v.25 no.5
• /
• pp.453-470
• /
• 2018

We study how to distinguish the parameters of the sparse autoregressive (AR) process from zero using a non-convex penalized estimation. A class of non-convex penalties are considered that include the smoothly clipped absolute deviation and minimax concave penalties as special examples. We prove that the penalized estimators achieve some standard theoretical properties such as weak and strong oracle properties which have been proved in sparse linear regression framework. The results hold when the maximal order of the AR process increases to infinity and the minimal size of true non-zero parameters decreases toward zero as the sample size increases. Further, we construct a practical method to select tuning parameters using generalized information criterion, of which the minimizer asymptotically recovers the best theoretical non-penalized estimator of the sparse AR process. Simulation studies are given to confirm the theoretical results.

• The Korean Journal of Applied Statistics
• /
• v.5 no.2
• /
• pp.181-192
• /
• 1992

We consider the estimation of the regression surface in generalized linear models based on tensor-product B-splines in a data-dependent way. Our approach is to use maximum likelihood method to estimate the regression function by a function from a space of tensor-product B-splines that have a finite number of knots and are linear in the tails. The knots are placed at selected order statistics of each coordinate of the sample data. The number of knots is determined by minimizing a variant of AIC. A numerical example is used to illustrate the performance of the tensor spline estimates.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1A
• /
• pp.34-42
• /
• 2000

In this paper, the closed form expression for the average bit error probability(BER) is derived for diversity reception using an L-branch maximal ratio combining(MRC) system which has same fading index and different fading index. Also, the BER to have same average power and Nakagami m-distribution for a generalized selection combining(SC) is derived, whereby the signal with the largest amplitude is selected from the original diversity branches in the channel, the order statistics is applied. Especially, when L is 1 in a selective diversity, the derived expression leads to that of DPSK in which SC is not applied in Nakagami fading. Changing the diversity branch L and fading index m, we compare the performance of MRC and SC.

• The Korean Journal of Applied Statistics
• /
• v.28 no.1
• /
• pp.115-122
• /
• 2015

This article is concerned with count time series taking values in non-negative integers. Along with the first order mean of the count time series, conditional variance (volatility) has recently been paid attention to and therefore various integer-valued GARCH(generalized autoregressive conditional heteroscedasticity) models have been suggested in the last decade. We introduce diverse integer-valued GARCH(INGARCH, for short) processes to count time series and a real data application is illustrated as a case study. In addition, zero inflated INGARCH models are discussed to accommodate zero-inflated count time series.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.5
• /
• pp.1009-1019
• /
• 2009

In this research, various characteristics of South Korea's design flood have been examined by deriving appropriate design flood, using data obtained from careful observation of actual floods occurring in selected main watersheds of the nation. 19 watersheds were selected for research in Korea. The various characteristics of annual rainfall were analyzed by using a moving average method. The frequency analysis was decided to be performed on the annual maximum flood of succeeding one year as a reference year. For the 19 watersheds, tests of basic statistics, independent, homogeneity, and outlier were calculated per period of annual maximum flood series. By performing a test using the LH-moment ratio diagram and the Kolmogorov-Smirnov (K-S) test, among applied distributions of Gumbel (GUM), Generalized Extreme Value (GEV), Generalized Logistic (GLO) and Generalized Pareto (GPA) distribution was found to be adequate compared with other probability distributions. Parameters of GEV distribution were estimated by L, L1, L2, L3 and L4-moment method based on the change in the order of probability weighted moments. Design floods per watershed and the periods of annual maximum flood series were derived by GEV distribution. According to the result of the analysis performed by using variation rate used in this research, it has been concluded that the time for changing the design conditions to ensure the proper hydraulic structure that considers recent climate changes of the nation brought about by global warming should be around the year 2002.

• The Korean Journal of Applied Statistics
• /
• v.11 no.1
• /
• pp.97-111
• /
• 1998

This paper suggests a Bayesian method for testing first-order markov correlation among linear regression disturbances. As a Bayesian test criterion, Bayes factor is derived in the form of generalized Savage-Dickey density ratio that is easily estimated by means of posterior simulation via Gibbs sampling scheme. Performance of the Bayesian test is evaluated and examined based upon a Monte Carlo experiment and an empirical data analysis. Efficiency of the posterior simulation is also examined.

• The Korean Journal of Applied Statistics
• /
• v.6 no.2
• /
• pp.329-339
• /
• 1993

Kernel regression is a nonparametric regression technique which requires only differentiability of the true function. If one wants to use the kernel regression technique to produce smooth estimates of a curve over a finite interval, one can realize that there exist distinct boundary problems that detract from the global performance of the estimator. This paper develops a kernel to handle boundary problem. In order to develop the boundary kernel, a generalized jacknife method by Gray and Schucany (1972) is adapted. Also, it will be shown that the boundary kernel has the same order of convergence rate as non-boundary.