• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.35 no.3
• /
• pp.216-222
• /
• 2002

Autocorrelation in time series data can affect statistical inference in correlation or regression analyses. To improve a regression model from which the residuals are autocorrelated, Yule-Walker method, nonlinear least squares estimation, maximum likelihood method and 'prewhitening' method have been used to estimate the parameters in a regression equation. This study reviewed on the estimation methods of preventing spurious correlation in the presence of autocorrelation and applied the former three methods, Yule-Walker, nonlinear least squares and maximum likelihood method, to a 20-year real data set. Monte carlo simulation was used to compare the three parameter estimation methods. However, the simulation results showed that the mean squared error distributions from the three methods simulated do not differ significantly.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.26-30
• /
• 2011

최근 기후변화에 따라 강우의 패턴이 변화하고 있다. 강우일수는 줄어드는 반면, 강우강도는 증가하여, 홍수로 인한 많은 피해에 직면하고 있다. 이러한 기상이변은 홍수방어시스템을 위한 수공구조물에도 많은 영향을 미친다. 수공구조물을 설계할 때, 일반적으로 강우 기록들의 통계적 특성이 정상성을 가진다고 가정한다. 하지만 최근의 강우 자료를 분석하면, 시간에 따라 평균, 분산, 왜곡도와 같은 기본 통계량이 변화하는 것을 알 수 있다. 따라서, 수공구조물의 설계를 위한 확률 강우량은 이러한 기후변화에 따른 자료의 특성을 반영할 필요가 있다. 본 연구의 목적은 강우 자료의 비정상성의 특성을 이용하여 확률강우량을 산정하는 것이다. 최근 비정상성 강우빈도해석에 대한 연구가 활발히 진행되고 있는데, 이들 연구는 대부분 목표연도까지 경향성의 기울기가 증가, 또는 일정하다고 가정한다. 하지만, 현재는 경향성이 있지만, 목표연도에는 경향성이 없을 경우도 있고, 또는 경향성이 있어도 그 기울기가 적어지는 경향을 보일 수도 있다. 본 연구에서는 현시점과 목표연도의 시점에 대한 경향성 기울기의 변화를 고려하여 비정상성 강우빈도해석을 수행하였다. 대상지점 선정은 통계적 경향성 검정, Mann-Kendall test를 이용하여 1994년(현재시점)에 경향성이 있다고 판단되는 관측지점을 대상지점으로 선정하였다. 분석 방법은 24시간 임계지속시간의 연최대강우자료를 구축하였다. 자료를 현시점까지 선형회귀식을 이용하여 잔차 계열을 산정하고, Gumbel 분포를 이용하여 확률 잔차를 산정하였다. 확률강우량을 추정하기 위해 추세요소를 산정하였다. 기울기의 증가 혹은 감소 경향을 회귀모형을 이용하여 추세요소를 산정하였고, 잔차의 확률빈도와 추세요소의 합으로 비정상상 확률강우량을 산정하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.548-548
• /
• 2016

수위-유량관계 곡선식은 시계열 수위자료를 유량자료로 변환해줄 수 있는 회귀식으로 측정단면의 형태, 단면 상 하류의 지형요인 등으로 인하여 영향을 고려하기 위하여 기간분할 혹은 구간분할을 수행한다. 구간분할을 위하여 측정단면의 변화를 고려한 관계자의 주관적인 판단이 주요 근거로 이용되고 있다. 따라서 본 연구에서는 기존에 개발된 수위-유량관계 곡선식의 자동구 구간분할방법에 대한 적용성 검토를 수행하였다. 객관화된 분할근거의 제시를 위하여 주관성을 배제하고 관측데이터를 기반으로 수위 증가에 따른 변동계수를 계산하였고, 변동계수가 정규분포를 따르는 것으로 가정 하에 계산된 변동계수가 전 단계에서 계산된 95% 신뢰구간 이내에 존재하지 않는 경우 구간을 분할하였다. 즉, 변동계수를 이용하여 집단 간의 특성을 비교하였으며, 변동 계수의 분포를 이용하여 분할을 위한 기준 값을 제시하였다. 방법론의 추정능력 검토를 위하여 가상의 곡선으로부터 생성된 데이터에 제안된 방법론을 적용하였고, 실제 유역에 적용성 검토를 위하여 금강에 위치한 무주 및 산계교 수위관측소 지점에 적용하였다. 결과적으로 자동으로 분할된 관계곡선식을 사용하여 추정의 정확도를 높일 수 있을 뿐만 아니라 외삽을 하는 경우 역시 그 정확도를 향상할 수 있음을 확인하였다. 마지막으로 실측값을 활용한 수위-유량관계 곡선식의 구축 시 구간 분할 전 후의 잔차데이터에 대하여 Shapiro-wilk 정규성 검정을 수행하였으며, 구간분할 후 잔차가 정규성을 갖게 되는 것으로 나타났다.

• The Korean Journal of Applied Statistics
• /
• v.24 no.1
• /
• pp.103-114
• /
• 2011

Current series for testing stock market cointegrations tend to be restricted to analyzing the relations between stock market prices and may not be able to understand the whole picture of the variations in the stock market system. The nature of the variations in the stock prices, between the countries that experienced economic crisis and those did not, are different for a certain period of time, and accordingly excluding the potentially important variables in the stock market system causes statistical bias. This study considers domestic foreign exchange markets and financial markets in testing for the cointegrating relations of the stock prices in Korea and major investing countries. The results demonstrate the possibility of specification errors unless those markets are included in the statistical modeling process.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.31 no.4
• /
• pp.326-339
• /
• 1995

In this paper, the validity of the numerical model of fishes' behavior presented in our earlier paper was examined by the whiteness test on the residual of numerical model and by the comparison between experiment and simulation on several indexes represented by fishes' swimming characteristics. The validity of the numerical model was proved statistically by means of the whiteness test of the residual. The similarity was confirmed by comparison between experiment and simulation for the swimming trajectory of fishes, the mean distance of individual from wall, the mean swimming speed and the mean distance between the nearest individuals. These results suggest that the behavior of fishes according to the flow speed in three-dimensional space can be estimated partially by the numerical model presented in our earlier paper. However, a long-term approach to improve the modeling technique on the behavior of fishes may be needed before applying the numerical model presented in our earlier paper to real fishing ground.

• Journal of Korea Port Economic Association
• /
• v.34 no.4
• /
• pp.181-190
• /
• 2018

The goal of this study is empirically to investigate the asymmetric relationship between two variables using the dry cargo freight rates and raw material price data from January 2012 to May 2018. First, we estimate the asymmetry of macroeconomic indicators of commodity prices by using a two - step threshold cointegration test. Second, the asymmetric relation test of the trade balance of existing commodity price changes is tested by bypassing to the high frequency dry cargo freight rate index. As a result of the estimation, in contrast to the existing linear analysis, each boundary value for the lower limit and the upper limit has different asymmetry. This implies that the period of fluctuation of the sudden residual that causes irregular rate of return fluctuations does not establish a long term equilibrium relationship between the raw material price and the dry cargo freight rate. Therefore, in order to consider the sudden price change in the analysis, it is necessary to include the band of inaction that controls the irregular volatility, which is consistent with the asymmetry hypothesis.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.141-150
• /
• 2015

Graphical paradigms for assessing the adequacy of models in logistic regression are discussed. The residual plot has been widely used as a graphical tool for evaluating the adequacy of the model. However, this approach works well only for linear models with constant variance, and the alternative approach, the marginal model plot, has its defects as well. We suggest a Chi-residual plot that overcomes the potential shortcomings of the marginal model plot.

• Journal of Korea Water Resources Association
• /
• v.37 no.7
• /
• pp.581-587
• /
• 2004

An experimental watershed was selected and sustainable yield was evaluated. The study area(3.89$\textrm{km}^2$) was located in Kyungpook Sangju Yangchon-dong. The visual MODFLOW was verified by comparing the observed and estimated groundwater table. The analysis of the observed and estimated groundwater table from 19 March 2003 to 18 March 2004 showed that the average error was 0.0009m, the error sum of squares 7.245$m^2$, absolute mean error 0.094 m, root mean square error 0.141m, and the model efficiency was 92%. The normal, 10- and 30- year drought frequency years were selected and sustainable yield was evaluated in these periods. Ratios of sustainable yield to the annual infiltration were 14.5% for the normal year(1992), 15.1% for the 10-year(1994), and 15.2% for the 30-year drought frequency year(1982). The results of this study can be used as a basic information for groundwater development and management planning considering regional characteristics.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.15 no.2
• /
• pp.156-162
• /
• 2012

Outlier detection and treatment process is highly required as the first step for the statistical analysis of the monitoring data having many outliers frequently occurred in the coastal environmental monitoring projects. In this study, the outlier detection method using the approximate and detail (or residual) components of the (raw) data is suggested. The approximate and detail components of the data can be separated by the diverse filtering and smoothing methods. The decomposition of the data is carried out by the harmonic analysis and local regression curve, respectively. Then, the Grubbs' test and modified z-score method widely used to detect outliers in the data are applied to the detail components of the water temperature data. The new data set is reconstructed after removed the outliers detected by these methods. It can be shown that the suggested process is successfully applied to the outlier detection of the coastal water temperature monitoring data provided by the Real-time Information System for Aquaculture Environment, National Fisheries Research and Development Institute (NFRDI).

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.2
• /
• pp.171-177
• /
• 2012

In this paper, we proposed a algorithm and an operation boundary for fault detection of a onboard GNSS receiver. After aircraft exchange corrections computed by an aircraft receiver, a faulty aircraft receiver is detected by checking consistency of correction. For this purpose, PRC residual is used as the test statistic for fault detection of the onboard GNSS receiver. And operation boundaries are set by using DGPS position error increase with respect to the distance from a reference station. If the fault detection is performed by using aircraft only in operation boundary, the more accurate fault detection can be possible.