• Communications for Statistical Applications and Methods
• /
• v.28 no.6
• /
• pp.627-641
• /
• 2021

An asymmetric least squares estimation method has been employed to estimate linear models for percentile regression. An asymmetric maximum likelihood estimation (AMLE) has been developed for the estimation of Poisson percentile linear models. In this study, we propose generalized nonlinear percentile regression using the AMLE, and the use of the parametric bootstrap method to obtain confidence intervals for the estimates of parameters of interest and smoothing functions of estimates. We consider three conditional distributions of response variables given covariates such as normal, exponential, and Poisson for three mean functions with one linear and two nonlinear models in the simulation studies. The proposed method provides reasonable estimates and confidence interval estimates of parameters, and comparable Monte Carlo asymptotic performance along with the sample size and quantiles. We illustrate applications of the proposed method using real-life data from chemical and radiation epidemiological studies.

• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• pp.479-485
• /
• 2009

When a part of data is unobserved the marginal likelihood of parameters given the observed data often involves analytically intractable high dimensional integral and hence it is hard to find the maximum likelihood estimate of the parameters. Simulated maximum likelihood(SML) method which estimates the marginal likelihood via Monte Carlo importance sampling and optimize the estimated marginal likelihood has been used in many applications. A key issue in SML is to find a good proposal density from which Monte Carlo samples are generated. The optimal proposal density is the conditional density of the unobserved data given the parameters and the observed data, and attempts have been given to find a good approximation to the optimal proposal density. Algorithms which adaptively improve the proposal density have been widely used due to its simplicity and efficiency. In this paper, we describe a fully adaptive algorithm which has been used by some practitioners but has not been well recognized in statistical literature, and evaluate its estimation performance and robustness via a simulation study. The simulation study shows a great improvement in the order of magnitudes in the mean squared error, compared to non-adaptive or partially adaptive SML methods. Also, it is shown that the fully adaptive SML is robust in a sense that it is insensitive to the starting points in the optimization routine.

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.63-73
• /
• 2002

The one of analytic imputation technique involving conditional means was mentioned by Schafer and Schenker(2000). And their derivations are based on asymptotic expansions of point estimator and their associated variance estimator, and the result of imputation can be thought of as first-order approximations to the estimators. Specially in this paper, we are presenting the method of estimating a Binomial proportion with Bayesian approach of imputed conditional means. That is, instead of using maximum likelihood(ML) estimator to estimate a Binomial proportion, in general, we use the Bayesian estimators and will show the result of estimated Imputed conditional means.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.171-180
• /
• 2016

Basel committee suggests using Value-at-Risk (VaR) and expected shortfall (ES) as a measurement for market risk. Various estimation methods of VaR and ES have been studied in the literature. This paper compares semi-parametric methods, such as conditional autoregressive value at risk (CAViaR) and conditional autoregressive expectile (CARE) methods, and a Gaussian quasi-maximum likelihood estimator (QMLE)-based method through back-testing methods. We use unconditional coverage (UC) and conditional coverage (CC) tests for VaR, and a bootstrap test for ES to check the adequacy. A real data analysis is conducted for S&P 500 index and Hyundai Motor Co. stock price index data sets.

• Journal of Preventive Medicine and Public Health
• /
• v.23 no.3 s.31
• /
• pp.247-254
• /
• 1990

짝짓기 방법은 교란변수를 통제하기 가장 좋은 방법으로 알려져 있으나, 모수추정시 그 계산방법이 복잡하고, 포함된 모든 정보를 이용할 수 없다는 단점을 갖고 있다. 그럼에도 불구하고, conditional 모델을 이용한 matched 분석법은 짝지은 자료 분석시 가장 좋은 방법으로 인정되고 있다. 그러나 명확한 confounding 현상을 통제할 목적이 아닌 상태에서 짝지워진 자료를 matched 분석법으로 모수추정하는 경우나, 올바로 짝지워진 자료를 분석법의 편이성 때문에 unmatched 분석을 시도하는 경우, 오히려 estimation bias가 야기될 수 있다. 이러한 estimation bias의 통제능력을 몇 가지 분석방법을 이용하여 비교하고자, 1:2로 대응된 한 환자-대조군 자료를 이용하여 Mantel-Haenszel 분석법, 두가지의 unconditional model을 이용한 다변량분석법의 결과를 conditional model을 이용한 matched 분석법의 결과와 비교하였다. 1. Matched 분석법의 대용방법으로 사용된 세 가지 방법들은 모수추정면에서나 가설검정능력면에서 차이를 서로 보이지 않았다. 2. 짝짓기에 사용된 변수가 분석자료내에서 confounder나 effect modifier로 작용되지 않았음이 명백한 경우에는 이들 세 가지 통제 방법과 matched 분석법간에 차이가 없었다. 3. 짝짓기에 사용된 변수가 분석자료내에서 effect modifier로 작용하지는 않았으나, Confounder로 작용한 것으로 추정되는 경우, unmatched 분석법으로 인해 야기된 estimation bias의 통제능력이 이들 세 가지 대용방안 모두에서 인정되었다. 4. 짝짓기에 사용된 변수가 분석자료내에서 effect modifier로 작용하고 있음을 직접 확인할 수 있는 경우에는, overmatching에 의한 estimation bias를 의심할 수 있었으며, 이들 세 가지 통제방법은 오히려 unmatched 분석 방법에 가까운 모수를 추정하였다.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.263-273
• /
• 2010

Missing values in time series can be treated as unknown parameters and estimated by maximum likelihood or as random variables and predicted by the conditional expectation of the unknown values given the data. The purpose of this study is to impute missing values which are regarded as the maximum likelihood estimator and random variable in incomplete data and to compare with two methods using ARMA and STAR model. For illustration, the Mumps data reported from the national capital region monthly over the years 2001~2009 are used, and estimate precision of missing values and forecast precision of future data are compared with two methods.

• The Korean Journal of Financial Management
• /
• v.26 no.3
• /
• pp.199-226
• /
• 2009

We examine the intertemporal relation between risk and return in the Korean stock market and foreign exchange market based on the two factor ICAPM framework. The standard GARCH model and the GJR(1993) model are employed to estimate conditional variances of the stock returns and foreign exchange rates. The covariance between the rates of stock returns and changes in the exchange rates are estimated by the constant conditional correlation model of Bollerslev(1990) and the dynamic conditional correlation model of Engle(2002). The multivariate GARCH in mean model and quasi-maximum likelihood estimation method, consequently, are applied to investigate riskreturn relation jointly. We find that the estimated coefficient of relative risk aversion is negative and statistically significant in the post-financial crisis sample period in the Korean stock market. We also show that the expected stock returns are negatively related to the dynamic covariance with foreign exchange rates. Both estimated parameters of conditional variance and covariance in the foreign exchange market, however, are not statistically significant. The GJR model is better than the standard GARCH model to estimate the conditional variances. In addition, the dynamic conditional correlation model has higher explanatory power than the constant correlation model. The empirical results of this study suggest following two points to investors and risk managers in hedging and diversifying strategies for their portfolios in the Korean stock market: first, the variability of foreign exchange rates should be considered, and second, time-varying correlation between stock returns and changes in foreign exchange rates supposed to be considered.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.12
• /
• pp.1-11
• /
• 1993

This paper concentrates on models useful for analyzing the error performance of ML(Maximum Likelihood) estimators of a single unknown signal parameter: that is the error intensity model. We first develop the point process representation for the estimation error and the conditional distribution of the estimator as well as the distribution of error candidate point process. Then the error intensity function is defined as the probability dessity of the estimate and the general form of the error intensity function is derived. We then develop several intensity models depending on the way we choose the candidate error locations. For each case, we compute the explicit form of the intensity function and discuss the trade-off among models as well as the extendability to the case of multiple parameter estimation.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.3
• /
• pp.419-425
• /
• 2010

Kernel machine learning is gaining a lot of popularities in analyzing large or high dimensional nonlinear data. We use this technique to estimate a GARCH model for predicting the conditional volatility of stock market returns. GARCH models are usually estimated using maximum likelihood (ML) procedures, assuming that the data are normally distributed. In this paper, we show that GARCH models can be estimated using kernel machine learning and that kernel machine has a higher predicting ability than ML methods and support vector machine, when estimating volatility of financial time series data with fat tail.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.