• 제목/요약/키워드: Statistical power

검색결과 1,626건 처리시간 0.03초

Robust extreme quantile estimation for Pareto-type tails through an exponential regression model

  • Richard Minkah;Tertius de Wet;Abhik Ghosh;Haitham M. Yousof
    • Communications for Statistical Applications and Methods
    • /
    • 제30권6호
    • /
    • pp.531-550
    • /
    • 2023
  • The estimation of extreme quantiles is one of the main objectives of statistics of extremes (which deals with the estimation of rare events). In this paper, a robust estimator of extreme quantile of a heavy-tailed distribution is considered. The estimator is obtained through the minimum density power divergence criterion on an exponential regression model. The proposed estimator was compared with two estimators of extreme quantiles in the literature in a simulation study. The results show that the proposed estimator is stable to the choice of the number of top order statistics and show lesser bias and mean square error compared to the existing extreme quantile estimators. Practical application of the proposed estimator is illustrated with data from the pedochemical and insurance industries.

전력설비의 수명계산을 위한 통계적 분석기법의 활용 및 검증에 대한 연구 (A Study on the Application and Verification of Statistical Techniques for Calculating the Life of Electric Power Facilities)

  • 이온유;김강식;이홍석;조종은;김상봉;박기훈
    • KEPCO Journal on Electric Power and Energy
    • /
    • 제8권1호
    • /
    • pp.9-14
    • /
    • 2022
  • Social infrastructure facilities such as production, transportation, gas and electricity facilities may experience poor performance depending on time, load, temperature, etc. and may require maintenance, repair and management as they are used. In particular, in the case of transformers, the process of managing them for the purpose of preventing them from failing is necessary because a failure can cause enormous social damage. The management of transformers should consider both technical and economic aspects and strategic aspects at the same time. Thus, it applies the Asset Management concept, which is widely used in the financial industry as an advanced method of transformer management techniques worldwide. In this paper, the operation and power outage data were secured for the asset management of the transformer for distribution, and the asset status was analyzed. Analysis of asset status using actual operation and power outage data is essential for assessing the statistical life and failure rate of the facility. Through this paper, the status of transformer assets for arbitrary A group distribution was analyzed, and the end of life and replacement life were calculated.

Power Analysis of Distributions between Nonparametric Tests

  • Chan Keun Park
    • Communications for Statistical Applications and Methods
    • /
    • 제5권2호
    • /
    • pp.417-429
    • /
    • 1998
  • This paper compares powers of the two nonparametric tests under a variety of population distributions through a simulation study. Both tests require that the two underlying populations have the same variance, but this assumption is relaxed in some of the comparisons.

  • PDF

A Study on the Power Comparison between Logistic Regression and Offset Poisson Regression for Binary Data

  • Kim, Dae-Youb;Park, Heung-Sun
    • Communications for Statistical Applications and Methods
    • /
    • 제19권4호
    • /
    • pp.537-546
    • /
    • 2012
  • In this paper, for analyzing binary data, Poisson regression with offset and logistic regression are compared with respect to the power via simulations. Poisson distribution can be used as an approximation of binomial distribution when n is large and p is small; however, we investigate if the same conditions can be held for the power of significant tests between logistic regression and offset poisson regression. The result is that when offset size is large for rare events offset poisson regression has a similar power to logistic regression, but it has an acceptable power even with a moderate prevalence rate. However, with a small offset size (< 10), offset poisson regression should be used with caution for rare events or common events. These results would be good guidelines for users who want to use offset poisson regression models for binary data.

Multiple Comparison for the One-Way ANOVA with the Power Prior

  • Bae, Re-Na;Kang, Yun-Hee;Hong, Min-Young;Kim, Seong-W.
    • Communications for Statistical Applications and Methods
    • /
    • 제15권1호
    • /
    • pp.13-26
    • /
    • 2008
  • Inference on the present data will be more reliable when the data arising from previous similar studies are available. The data arising from previous studies are referred as historical data. The power prior is defined by the likelihood function based on the historical data to the power $a_0$, where $0\;{\le}\;a_0\;{\le}\;1$. The power prior is a useful informative prior for Bayesian inference such as model selection and model comparison. We utilize the historical data to perform multiple comparison in the one-way ANOVA model. We demonstrate our results with some simulated datasets under a simple order restriction between the treatments.

Use of Pseudo-Likelihood Estimation in Taylor's Power Law with Correlated Responses

  • Park, Bum-Hee;Park, Heung-Sun
    • Communications for Statistical Applications and Methods
    • /
    • 제15권6호
    • /
    • pp.993-1002
    • /
    • 2008
  • Correlated responses have been widely analyzed since Liang and Zeger (1986) introduced the famous Generalized Estimating Equations(GEE). However, their variance functions were restricted to known quantifies multiplied by scale parameter. In so many industries and academic/research fields, power-of-the-mean variance function is one of the common variance function. We suggest GEE-type pseudolikelihood estimation based on the power-of-the-mean variance using existing software and investigate it's efficiency for different working correlation matrices.

The Bandwidth from the Density Power Divergence

  • Pak, Ro Jin
    • Communications for Statistical Applications and Methods
    • /
    • 제21권5호
    • /
    • pp.435-444
    • /
    • 2014
  • The most widely used optimal bandwidth is known to minimize the mean integrated squared error(MISE) of a kernel density estimator from a true density. In this article proposes, we propose a bandwidth which asymptotically minimizes the mean integrated density power divergence(MIDPD) between a true density and a corresponding kernel density estimator. An approximated form of the mean integrated density power divergence is derived and a bandwidth is obtained as a product of minimization based on the approximated form. The resulting bandwidth resembles the optimal bandwidth by Parzen (1962), but it reflects the nature of a model density more than the existing optimal bandwidths. We have one more choice of an optimal bandwidth with a firm theoretical background; in addition, an empirical study we show that the bandwidth from the mean integrated density power divergence can produce a density estimator fitting a sample better than the bandwidth from the mean integrated squared error.

실험계획법을 이용한 대구경용 코발트 박막의 스퍼터 조건 최적화 (Optimizing the Cobalt Deposition Condition using the Experiment Design)

  • 정성희;송오성
    • 한국자기학회지
    • /
    • 제12권6호
    • /
    • pp.224-230
    • /
    • 2002
  • 직경 200mm의 실리콘 기판에 균일한 코발트 금속박막을 증착하는 DC-스퍼터 장비에서 공정변수는 증착온도, 증착압력, DC power로 하고 종속변수(response)는 면저항, 면저항 균일도로 하는 '||'&'||'quot;통계적 실험방법'||'&'||'quot;을 채택한 실험을 수행하여 Co 박막의 공정 특성에 대해 다음과 같은 결과를 얻었다 '||'&'||'quot;통계적 실험방법'||'&'||'quot;을 이용한 Co박막의 공정 특성을 조사하는 본 실험에서 면저항과 면저항 균일도는 0.05 이하의 significance수치. 낮은 RMS error, 0.91 이상의 R-sq수치로부터 실험의 우수한 신뢰성을 확인하였다. 면저항에 대한 공정변수의 영향성은 증착온도가 -1.83$\Omega$/$\square$의 감소효과, 증착압럭이 1.17$\Omega$/$\square$의 증가 효과. DC power가 -0.65$\Omega$/$\square$의 감소 효과로 실험 구간에서 일정한 경향의 영향성을 보였으며, 면저항 균일도에서는 증착온도에 의해 $25^{\circ}C$~147$^{\circ}C$에서 -4.04%의 감소로 증착온도에 가장 민감함을 확인하였다. Co 박막의 최적 증착 조건은 증착온도 $25^{\circ}C$, 증착압력 12mTorr, DC power 1500 W로 예상되었다.

고차 전력 분석에 대한 통계적 수식의 일반화 (Statistical Analysis of High-Order Power Analysis)

  • 김민수;김희석;홍석희
    • 정보보호학회논문지
    • /
    • 제21권4호
    • /
    • pp.27-37
    • /
    • 2011
  • d차의 고차 전력 분석은 d차 마스킹 기법에 의해 안전하게 방어할 수 있다. 하지만 이러한 고차의 마스킹 기법의 적용은 차수가 높아질수록 암호 시스템의 성능을 현저히 떨어뜨린다. 기존의 고차 전력 분석에 대한 통계적 접근은 이차 전력 분석에 대해서만 이루어져 있다. 하지만 이는 암호 설계자가 삼차 이상의 마스킹 적용 시 특별한 안전성의 기준이 없음을 의미하며 이러한 기준의 부재는 무의미하게 높은 차수의 마스킹 기법 적용으로 인해 암호 시스템의 성능을 상당히 저하시킬 수 있다. 본 논문에서는 이러한 기준을 마련하고자 고차 전력 분석에 대한 통계적 수치를 일반화하였다. 즉, 고차 전력 분석을 수행했을 때 연산되는 상관계수의 값을 일반화 시켰으며 이는 향후 마스킹 기법 사용 시 적용해야할 차수를 선택하기 위한 좋은 지표가 될 것이다.

Statistical Approach for Derivation of Quantitative Acceptance Criteria for Radioactive Wastes to Near Surface Disposal Facility

  • Park Jin Beak;Park Joo Wan;Lee Eun Yong;Kim Chang Lak
    • Nuclear Engineering and Technology
    • /
    • 제35권5호
    • /
    • pp.387-398
    • /
    • 2003
  • For reference human intrusion scenarios constructed in previous study, a probabilistic safety assessment to derive the radionuclide concentration limits for the low- and intermediate- level radioactive waste disposal facility is conducted. Statistical approach by the Latin Hypercube Sampling method is introduced and new assumptions about the disposal facility system are examined and discussed. In our previous study of deterministic approach, the post construction scenarios appeared as most limiting scenario to derive the radionuclide concentration limits. Whereas, in this statistical approach, the post drilling and the post construction scenarios are mutually competing for the scenario selection according to which radionuclides are more important in safety assessment context. Introduction of new assumption shows that the post drilling scenario can play an important role as the limiting scenario instead of the post-construction scenario. When we compare the concentration limits between the previous and this study, concentrations of radionuclides such as Nb-94, Cs-137 and alpha-emitting radionuclides show elevated values than the case of the previous study. Remaining radionuclides such as Sr-90, Tc-99 I-129, Ni-59 and Ni-63 show lower values than the case of the previous study.