• 응용통계연구
• /
• 제29권3호
• /
• pp.513-523
• /
• 2016

다중 치우침 모수벡터를 가진 다변량 치우친 정규분포 (MSNMix)를 EM 알고리즘으로 적합하려면 E-step에서 다변량 절단 정규분포의 적률과 확률을 계산해야 하는데 이것은 매우 큰 계산 시간을 요구한다. 그래서 비대칭 자료를 적합하는데 흔히 단순 치우침 모수를 가진 모형을 적용한다. 이 모형은 단변량 처리방식으로 적합하는 것이 가능하기 때문에 처리속도가 매우 빠르다. 그러나 단순 치우침 모수를 적용하는 것은 응용에서 비현실적인 경우가 많다. 본 논문에서는 다중 치우침 모수를 가지는 MSNMix의 근사적 추정법을 제안하는데, 이 방법은 단변량 처리방식이 적용되므로 향상된 처리속도를 보장한다. 그리고 제안된 방법의 실효성을 보이기 위해 몇 가지 실험 결과를 제공한다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2004년도 춘계학술발표회
• /
• pp.319-326
• /
• 2004

Uncertainty is inevitably involved in rock slope engineering since the rock masses are formed by natural process and subsequently the geotechnical characteristics of rock masses cannot be exactly obtained. Therefore the reliability analysis method has been suggested to deal properly with uncertainty. The reliability analysis method can be divided into level I, II and III on the basis of the approach for consideration of random variable and probability density function of reliability function. The level II approach, which is focused in this study, assumes the probability density function of random variables as normal distribution and evaluates the probability of failure with statistical moments such as mean and standard deviation. This method has the advantage that can be used the problem which the Monte Carlo simulation approach cannot be applied since the complete information on the random variables are not available. In this study, the analysis results of level II reliability approach compared with the analysis results of level III approach to verify the appropriateness of the level II approach. In addition, the results are compared with the results of the deterministic analysis.

• 물과 미래
• /
• 제18권1호
• /
• pp.75-83
• /
• 1985

초기연구단계에 있는 ARMA(1, 1) 다계절모형에 의해 계절유량을 발생시키기 위한 모형의 변수결정방법과 유량발생 및 발생유량계열의 통계학적분석을 실시하였으며 타모형과의 비교를 위해 Thomas-Fiering 모형, Matalas AR(1) 다계절모형도 사용하였다. 다계절모형에 의해 발생시킨 계절유량을 연도별로 합산하여 얻은 연유량계열의 통계학적 특성치를 년모의발생모형에 의해 발생시킨 년유량계열의 통계특성치와 비교함으로써 ARMA(1, 1) 다계절모형에 의해 계절 및 년유량자료계열을 한꺼번에 모의발생시킬 수 있는 가능성을 평가하였다.

• Structural Engineering and Mechanics
• /
• 제28권3호
• /
• pp.281-294
• /
• 2008

In this paper, linear elastic isotropic structures under the effects of both stochastic operators and stochastic excitations are studied. The analysis utilizes the spectral stochastic finite elements (SSFEM) with its two main expansions namely; Neumann and Homogeneous Chaos expansions. The random excitation and the random operator fields are assumed to be second order stochastic processes. The formulations are obtained for the system solution of the two dimensional problems of plane strain and plate bending structures under stochastic loading and relevant rigidity using the previously mentioned expansions. Two finite element programs were developed to incorporate such formulations. Two illustrative examples are introduced: the first is a reinforced concrete culvert with stochastic rigidity subjected to a stochastic load where the culvert is modeled as plane strain problem. The second example is a simply supported square reinforced concrete slab subjected to out of plane loading in which the slab flexural rigidity and the applied load are considered stochastic. In each of the two examples, the first two statistical moments of displacement are evaluated using both expansions. The probability density function of the structure response of each problem is obtained using Homogeneous Chaos expansion.

• 아태비즈니스연구
• /
• 제13권2호
• /
• pp.23-37
• /
• 2022

Purpose - The purpose of this paper is to analyze the dynamic factors of the daily FX implied volatility based on the fractional integration methods focusing on long memory feature and structural changes. Design/methodology/approach - This paper uses the daily FX implied volatility data of the EUR-USD and the JPY-USD exchange rates. For the fractional integration analysis, this paper first applies the basic ARFIMA-FIGARCH model and the Local Whittle method to explore the long memory feature in the implied volatility series. Then, this paper employs the Adaptive-ARFIMA-Adaptive-FIGARCH model with a flexible Fourier form to allow for the structural changes with the long memory feature in the implied volatility series. Findings - This paper finds statistical evidence of the long memory feature in the first two moments of the implied volatility series. And, this paper shows that the structural changes appear to be an important factor and that neglecting the structural changes may lead to an upward bias in the long memory feature of the implied volatility series. Research implications or Originality - The implied volatility has widely been believed to be the market's best forecast regarding the future volatility in FX markets, and modeling the evolution of the implied volatility is quite important as it has clear implications for the behavior of the exchange rates in FX markets. The Adaptive-ARFIMA-Adaptive-FIGARCH model could be an excellent description for the FX implied volatility series

• Journal of Electrical Engineering and Technology
• /
• 제12권4호
• /
• pp.1641-1648
• /
• 2017

Many researchers had examined the validity of using the high-to-low ratio between two fixed frequency band amplitudes (H/L-FFB) from the surface electromyography of a face and body as the first spectral index to assess muscle fatigue. Despite these studies, the disadvantage of this index is the lack of a criterion for choosing the optimal border frequency. We tested the potential of using the high-to-low ratio between two signal spectral moments (H/L-SSM), without fixed border frequencies, to evaluate muscle fatigue and predict endurance time ($T_{end}$), which was determined when the subject was exhausted and could no longer follow the fixed contraction cycle. Ten healthy participants performed five sets of voluntary isotonic contractions until they could only produce 10% and 20% of their maximum voluntary contraction (MVC). The $T_{end}$ values for all participants were $138{\pm}35s$ at 10% MVC and $69{\pm}20s$ at 20% MVC. Changes in conventional spectral indices, such as the mean power frequency (MPF), Dimitrov spectral index (DSI), H/L-FFB, and H/L-SSM, were extracted from surface EMG signals and were monitored using the initial slope computed every 10% of $T_{end}$ as a statistical indicator and compared as a predictor of $T_{end}$. Significant correlations were found between $T_{end}$ and the initial H/L-SSM slope as computed over 30% of $T_{end}$. In conclusion, initial H/L-SSM slope can be used to describe changes in the spectral content of surface EMG signals and can be employed as a good predictor of $T_{end}$ compared to that of conventional spectral indices.

• 한국지구과학회지
• /
• 제33권1호
• /
• pp.39-48
• /
• 2012

본 연구에서는 부산지방기상청 장기 강수량 자료(1973-2007)를 이용하여 부산지역 확률강수량 및 이에 따른 재현 기간을 산정하였다. 확률강수량 산정에 있어서 확률가중모멘트법을 이용하여 매개변수를 추정하였고, $x^2$ 및 PPCC 검정을 통해 적합성분석을 실시하였다. 분석결과 최적의 확률분포형으로 GLO 모형을 채택하였다. 또한 AWS 자료를 이용하여 부산지역 확률강수량 분포도를 작성하였다. 6시간 지속강수량에 있어서 245.2 mm의 강수량이 100년 마다 발생할 수 있으며, 280.6 mm가 200년에 한번 정도 나타날 수 있다. 확률강수량 분포도 결과 1시간 지속강수일 경우 동래구에서 높은 값을 가지며, 3시간 지속강수는 부산연안 전반에 걸쳐 높게 나타나고 있다. 6시간 지속강수량일 경우는 부산진과 양산일대에서 높은 값을 나타내며 12시간 지속강수의 경우 남동연안지역과 웅상 일대에서 높은 값을 보이는 특징이 나타났다.

• 한국방재안전학회논문집
• /
• 제13권1호
• /
• pp.1-11
• /
• 2020

수문 통계 분야에서 관측된 자료를 대표할 수 있는 확률분포 모형을 추정하는 일은 매우 중요한 문제이다. 이를 위해 표본 자료로부터 추정되는 확률분포 모형과 가정된 이론적 확률분포 모형의 일치 정도를 통해 적합도 검정을 수행한다. 확률 도시 상관계수 검정(PPCC)은 적합도 검정 방법 중 하나로 적용 방법이 간편하면서도 높은 기각력을 가지고 있다. 본 연구에서는 L-모멘트 법 기반의 generalized extreme value(GEV) 분포 모형을 위한 PPCC의 검정 통계량을 유도하고 이를 다변량 비선형 형태의 회귀식으로 제시하였다. 새롭게 제시된 방법의 기각력을 검토하고자 기존의 적합도 검정 방법들과 모의실험을 수행하였으며 그 결과 본 연구에서 제시된 PPCC-A 검정 방법이 기존의 PPCC 검정을 비롯한 다른 적합도 검정 방법보다 우수한 기각력을 보이는 것으로 나타났다. 이를 통해 표본 자료를 좀 더 정확하게 대표할 수 있는 확률분포 모형을 구축하는 데 도움이 될 것으로 기대된다.

• 유통과학연구
• /
• 제13권5호
• /
• pp.53-60
• /
• 2015

Purpose - The purpose of this paper is to shed light on the importance of the slope and curvature of the volatility curve implied in option prices in the KOSPI 200 options index. A number of studies examine the implied volatility curve, however, these usually focus on cross-sectional characteristics such as the volatility smile. Contrary to previous studies, we focus on time-series characteristics; we investigate correlation dynamics among slope, curvature, and level of the implied volatility curve to capture market information embodied therein. Our study may provide useful implications for investors to utilize current market expectations in managing portfolios dynamically and efficiently. Research design, data, and methodology - For our empirical purpose, we gathered daily KOSPI200 index option prices executed at 2:50 pm in the Korean Exchange distribution market during the period of January 2, 2004 and January 31, 2012. In order to measure slope and curvature of the volatility curve, we use approximated delta distance; the slope is defined as the difference of implied volatilities between 15 delta call options and 15 delta put options; the curvature is defined as the difference between out-of-the-money (OTM) options and at-the-money (ATM) options. We use generalized method of moments (GMM) and the seemingly unrelated regression (SUR) method to verify correlations among level, slope, and curvature of the implied volatility curve with statistical support. Results - We find that slope as well as curvature is positively correlated with volatility level, implying that put option prices increase in a downward market. Further, we find that curvature and slope are positively correlated; however, the relation is weakened at deep moneyness. The results lead us to examine whether slope decreases monotonically as the delta increases, and it is verified with statistical significance that the deeper the moneyness, the lower the slope. It enables us to infer that when volatility surges above a certain level due to any tail risk, investors would rather take long positions in OTM call options, expecting market recovery in the near future. Conclusions - Our results are the evidence of the investor's increasing hedging demand for put options when downside market risks are expected. Adding to this, the slope and curvature of the volatility curve may provide important information regarding the timing of market recovery from a nosedive. For financial product distributors, using the dynamic relation among the three key indicators of the implied volatility curve might be helpful in enhancing profit and gaining trust and loyalty. However, it should be noted that our implications are limited since we do not provide rigorous evidence for the predictability power of volatility curves. Meaning, we need to verify whether the slope and curvature of the volatility curve have statistical significance in predicting the market trough. As one of the verifications, for instance, the performance of trading strategy based on information of slope and curvature could be tested. We reserve this for the future research.

• 터널과지하공간
• /
• 제33권5호
• /
• pp.414-424
• /
• 2023

본 연구에서는 픽커터의 다양한 형상변수들과 그에 따른 절삭 가능 암반 조건들에 대한 총 326개의 정보를 수집하고 데이터베이스를 구축하였다. 이와 같이 구축한 데이터베이스를 대상으로 통계분석을 실시한 결과, 픽커터의 형상을 정의하는 변수들 사이에는 유의미한 양(+)의 상관관계가 존재하는 것으로 나타났다. 특히, 픽커터의 길이 관련 변수들과 텅스텐 카바이드 삽입재의 형상 변수들 사이의 상관관계가 높게 나타났다. 픽커터 샤프트의 직경도 삽입재의 형상변수들과 밀접한 상관관계를 나타내었다. 반면, 네 가지 조건으로 정의한 암반 조건에 대한 변수와 픽커터의 형상 변수들 사이에는 뚜렷한 상관관계를 확인하기 어려웠다. 이는 암반의 불확실성으로 인해 픽커터의 적용 대상을 수치가 아닌 적용 가능 범위로 제시했기 때문인 것으로 사료된다. 단, 암반이 강해질수록 픽커터 형상변수들의 평균값이 증가하는 경향을 나타내었다. 그러나 픽커터의 길이 관련 변수들은 암반이 강해질수록 오히려 작아지는 것으로 나타났는데, 이는 경암반에서 길이가 긴 픽커터를 사용할 때 발생할 수 있는 모멘트의 발생을 줄이기 위한 방안으로 사료된다.