• Journal of the Korean Statistical Society
• /
• 제30권1호
• /
• pp.99-113
• /
• 2001

This paper deals with the problem of estimating the means in two inverse Gaussian populations with equal but unknown coefficient of variation. The maximum likelihood estimators are derived by solving a cubic equation and their asymptotic variances are presented for comparative purpose. Monte-Carlo simulation is conducted to investigate the efficiency of the estimators relative to the sample means over a wide range of values for the sample size and the coefficient of variation. The effect on this efficiency under the departure from the assumption of common coefficient of variation is also studied.

• Journal of the Korean Data and Information Science Society
• /
• 제15권4호
• /
• pp.981-992
• /
• 2004

In this paper, we develop the noninformative priors for the common scale parameter in the inverse gaussian distributions. We developed the first and second order matching priors. Next we revealed that the second order matching prior satisfies a HPD matching criterion. Also we showed that the second order matching prior matches alternative coverage probabilities up to the second order. It turns out that the one-at-a-time reference prior satisfies a second order matching criterion. Some simulation study is performed.

• Communications for Statistical Applications and Methods
• /
• 제27권1호
• /
• pp.97-108
• /
• 2020

This paper compares several methods for estimating parameters of normal inverse Gaussian distribution. Ordinary maximum likelihood estimation and the method of moment estimation often do not work properly due to restrictions on parameters. We examine the performance of adjusted estimation methods along with the ordinary maximum likelihood estimation and the method of moment estimation by simulation and real data application. We also see the effect of the initial value in estimation methods. The simulation results show that the ordinary maximum likelihood estimator is significantly affected by the initial value; in addition, the adjusted estimators have smaller root mean square error than ordinary estimators as well as less impact on the initial value. With real datasets, we obtain similar results to what we see in simulation studies. Based on the results of simulation and real data application, we suggest using adjusted maximum likelihood estimates with adjusted method of moment estimates as initial values to estimate the parameters of normal inverse Gaussian distribution.

• 응용통계연구
• /
• 제26권1호
• /
• pp.37-47
• /
• 2013

Q-Q 플롯은 자료에 대한 분포적 가정을 평가하기 위해서 사용되는 편리하고 효과적인 그래프 방법이다. Q-Q 플롯은 자료의 분포와 이론적 분포를 비교하기 위한 확률플롯으로 자료에서의 분위수와 이에 대응하는 이론적 분위수를 각각 수직축과 수평축으로 해서 그린 산점도의 형태를 취한다. 본 논문에서는 확률변수 X가 위치모수 ${\mu}$와 척도수 ${\lambda}$를 가지는 역가우스분포를 따르면, 변환된 확률변수 $Y={\mid}\sqrt{\lambda}(X-{\mu})/{\mu}\sqrt{X}{\mid}$는 평균이 0이고 분산이 1인 표준반접정규분포를 하게 되는 분포적 결과를 활용하여 역가우스분포 Q-Q 플롯의 구축방법을 소개한다. 역가우스분포와 다른 분포를 따르는 자료를 대상으로 그린 Q-Q 플롯에서 나타나는 점들의 형태를 알아보고자 모의실험을 수행하고 그 결과를 제시한다. 실제 자료에 대한 사례분석을 통해 제안한 Q-Q 플롯의 유용성을 보인다.

• 응용통계연구
• /
• 제29권4호
• /
• pp.741-752
• /
• 2016

금융자산의 수익률 분포를 잘 설명할 수 있는 것으로 알려진 normal inverse Gaussian(NIG)분포는 모수의 조건에 의해 세 배의 초과첨도가 왜도 제곱의 5배보다 커야 하는데, 만약 관측된 초과첨도와 왜도의 관계가 이를 만족하지 못하거나 두 값이 매우 비슷하다면 모수를 안정적으로 추정하기 어렵게 된다. 이 논문에서 우리는 NIG분포의 모수추정에서 발생하는 이러한 문제점을 살펴보고 모의실험을 통해 이를 보정하는 방법을 찾아보았다. KOSPI, S&P500, FTSE와 HANG SENG의 실제 주가지수 자료에 적용하여 보정의 효과를 비교하고 VaR를 이용한 사후검증으로 보정된 추정방법의 성능을 평가해 보았다. 보정 방법을 이용하였을 때, 모수추정의 문제가 있던 구간을 포함한 모든 구간에서 안정적인 모수추정이 가능하였고 VaR를 통한 사후 검증에서도 분포의 성능이 떨어지지 않음을 확인하였다.

• 한국수학교육학회지시리즈B:순수및응용수학
• /
• 제28권4호
• /
• pp.281-296
• /
• 2021

In this paper, we suggest a representation for an inverse transform of the generalized Fourier-Feynman transform on the function space C_a,b[0, T]. The function space C_a,b[0, T] is induced by the generalized Brownian motion process with mean function a(t) and variance function b(t). To do this, we study the generalized Fourier-Feynman transform associated with the Gaussian process Ƶ_k of exponential-type functionals. We then establish that a composition of the Ƶ_k-generalized Fourier-Feynman transforms acts like an inverse generalized Fourier-Feynman transform.

• Communications for Statistical Applications and Methods
• /
• 제19권6호
• /
• pp.837-847
• /
• 2012

Inverse Gaussian distribution is widely used in applications to analyze and model right-skewed data. To assess the appropriateness of the distribution prior to data analysis, Mudholkar and Tian (2002) proposed an entropy-based test of fit. The test is based on the entropy power fraction(EPF) index suggested by Gokhale (1983). The simulation results report that the power of the entropy-based test is superior compared to other goodness-of-fit tests; however, this observation is based on the small-scale simulation results on the standard exponential, Weibull W(1; 2) and lognormal LN(0:5; 1) distributions. A large-scale simulation should be performed against various alternative distributions to evaluate the power of the entropy-based test; however, the use of a theoretical method is more effective to investigate the powers. In this paper, utilizing the information discrimination(ID) index defined by Ehsan et al. (1995) as a mathematical tool, we scrutinize the power of the entropy-based test. The selected alternative distributions are the gamma, Weibull and lognormal distributions, which are widely used in data analysis as an alternative to inverse Gaussian distribution. The study results are provided and an illustrative example is analyzed.

• Communications for Statistical Applications and Methods
• /
• 제15권5호
• /
• pp.655-666
• /
• 2008

Small sample likelihood based inference for the shape parameter of the inverse Gaussian distribution is the purpose of this paper. When shape parameter is of interest, the signed log-likelihood ratio statistic and the modified signed log-likelihood ratio statistic are derived. Hsieh (1990) gave a statistical inference for the shape parameter based on an exact method. Throughout simulation, we will compare the statistical properties of the proposed statistics to the statistic given by Hsieh (1990) in term of confidence interval and power of test. We also discuss a real data example.

• Journal of the Korean Data and Information Science Society
• /
• 제19권3호
• /
• pp.995-1006
• /
• 2008

This article deals with the one-sided hypothesis testing problem in inverse Gaussian distribution. We propose Bayesian hypothesis testing procedures for the one-sided hypotheses of the shape parameter under the noninformative prior. The noninformative prior is usually improper which yields a calibration problem that makes the Bayes factor to be defined up to a multiplicative constant. So we propose the objective Bayesian hypothesis testing procedures based on the fractional Bayes factor, the median intrinsic Bayes factor and the encompassing intrinsic Bayes factor under the reference prior. Simulation study and a real data example are provided.

• Journal of the Korean Data and Information Science Society
• /
• 제26권1호
• /
• pp.243-253
• /
• 2015

In this paper, we develop the noninformative priors for the common shape parameter of several inverse Gaussian distributions. Specially, we want to develop noninformative priors which satisfy certain objective criterion. The probability matching priors and reference priors of the common shape parameter will be developed. It turns out that the second order matching prior does not exist. The reference priors satisfy the first order matching criterion, but Jeffrey's prior is not the first order matching prior. We showed that the proposed reference prior matches the target coverage probabilities in a frequentist sense through simulation study, and an example based on real data is given.