• 응용통계연구
• /
• 제33권5호
• /
• pp.527-540
• /
• 2020

이상치에 대한 적절한 선별과 배제없이 모든 데이터를 종합적으로 분석하게 되는 경우 데이터 분석을 통해 얻은 결과의 신뢰성과 해석의 일반성에 치명적인 위협을 받을 수 있다. 따라서 데이터의 분석 과정에서 이러한 이상치를 판별하고, 이상치가 통계량, 통계적 모형에 어떠한 영향을 주는 지에 대한 분석은 매우 중요한 일이라 할 수 있다. Hampel이 영향함수를 활용하여 이상치를 판별할 수 있는 방법을 소개한 이후, 이상치를 판별하기 위한 방법론으로 영향함수가 폭넓게 활용되어 왔다. 영향함수에는 경험적 영향함수와 표본영향함수가 있으며, 경험적 영향함수를 활용해 표본영향함수를 근사 추론하여 하나의 관측값이 제거되었을 때 통계량에 미치는 영향을 예측하는 방법론이 주로 활용되었다. 본 연구에서는 표본평균, 표본분산, 표본표준편차의 표본영향함수 유도를 통해 경험적 영향함수와 표본영향함수의 차이를 살펴 본다. 또한 경험적 영향함수로 표본영향함수를 근사하는 과정에서 발생하는 오차를 줄이기 위해 경험적 영향함수의 보정으로 표본영향함수를 근사 추론하는 방법을 제안하고, 모의실험을 통해 제안한 추론 방법의 타당성을 확인한다.

• 한국토양비료학회지
• /
• 제17권3호
• /
• pp.212-217
• /
• 1984

지질순계학적(地質純計學的) 개념(槪念)인 지역변수(地域變數) 이론(理論)을 적용(適用)하여 $2{\times}3$ Grid형태(形態)로 표본추출(標本抽出)된 중동사양토(中東砂壤土)와 화동미사질식양토(華東微砂質埴壤土)의 입경분포(粒徑分布)에 대한 공간(空間) 종속성(從屬性)의 구조분석(構造分析) 및 그 해석(解析)과 이것에 의하여 설정(設定)된 Variogram에 기본(基本)을 둔 최량(最良)의 선형불편추정치(線型不編推定置)(BLUE)인 Kriging을 위한 최적(最適)의 표본추출수(標本抽出數)와 그 거리(距離)를 결정(決定)하였으며, 아울러 순수(純粹) Nugget 효과(效果)를 나타내는 특성(特性)의 표본(標本)크기를 결정(決定)하고자 수행(遂行)하였다. (1) 화동토양(華東土壤)은 선형(線型) 그리고 중동토양(中東土壤)은 곡면형(曲面型)의 Variogram을 설정(設定)하였다. (2) 화동토양(華東土壤)은 Nugget 효과(效果)를 나타냈으며, 중동토양(中東土壤)의 경우 점토함량(含量)만 Nugget효과(效果)를 나타내었고 미사와 모래함량(含量)은 순수(純粹) Nugget 효과(效果)를 나타내었다. (3) 표본수(標本數) 96과 근사(近似)한 결과(結果)를 가져올 최적표본수(最適標本數)는 화동토양(華東土壤)의 미사, 점토, 그리고 모래 함량(含量)에서 각각 27, 13, 그리고 6개였으며, 중동토양(中東土壤)의 점토함량(含量)은 17개로 추정(推定)되었다. (4) 순수(純粹) Nugget 효과(效果)를 보인 중동토양(中東土壤)의 미사와 모래함량(含量)에 대하여 유의수준(有意水準) 0.05 에서 모평균(母平均)의 5% 정도(精度)에 필요(必要)한 표본(標本)크기는 각각 14 및 26개 이었다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권1호
• /
• pp.373-376
• /
• 2016

The Mini Parasep SF fecal parasite concentrator (MPSFC) is a new modification of the closed concentration system, which can easily be adopted in any routine clinical pathology laboratory. Here we describe our experience with the system in diagnosing Opisthorchis viverrini. A total of 199 fecal samples was submitted for routine examination in the clinical pathology laboratory of Suranaree University of Technology hospital, Nakhon Ratchasima province, Thailand, during August to October 2015. Out of all samples examined, 10 (5.03%) were positive with intestinal parasites including O. viverrini (2.01%), followed by Strongyloided stercoralis (1.51%), Hookworm (0.5%), Taenia spp. (0.5%), and Entamoeba coli (0.5%). Regarding the distribution of intestinal parasites in relation to the methods used, and found that 4 samples (2.01%) were positive using the direct wet smear method while 10 (5.03%) were positive with the Mini Parasep SF method; the difference was statistically significant ($X^2$-test = 116.506, p-value =0.001). Mean time for processing using the Parasep system was 6.03 min/sample, the conventional direct wet smear method at 0.3 min/sample. Cost per test, conventional direct wet smear method costing less than the Parasep method at USD 0.74/sample versus USD 1.47/sample. This first report of O. viverrini detection using MPSFC indicates that Parasep concentration test is useful in the routine laboratory, increasing the yield of parasites as compared to direct microscopy, but with greater processing time and cost. Further comparisons between the Parasep concentration test and common methods for O. viverrini detection are required, particularly concerning use in epidemiological surveys.

• 한국대기환경학회지
• /
• 제16권2호
• /
• pp.89-102
• /
• 2000

A total of 318 particulate sample sets consisting of both fine PM(FPM : dp$\leq$2.5 ${\mu}{\textrm}{m}$) and coarse PM(CPM : 2.5${\mu}{\textrm}{m}$${\mu}{\textrm}{m}$) was collected by a dichotomous sampler in Suwon area from December 1996 to November 1997. The concentration of seven inorganic elements such as pb. Cr, Cd, Cu, Zn Fe and Na were determined from each sample using an AAS. The purpose of the study was to extensively investigate environmental behaviors of particulate matters and to provide air quality management schemes applying various statistical approaches. The mean concentrations of PM10 Results of correlation analyses indicated the existence of strong correlations among inorganic elements PM10 FPM CPM and various meterological variables. Our study also examined the degree of uncertainties whether the particular elements can be assorted into the accumulation mode or the coarse mode in their size distribution. Furthermore the analysis of the pollution rose showed graphically the direction of potential sources of particulate matters. According to statistical analyses of our data quantitative differences appeared in the pollution patterns between weekdays and weekends.

• 소성∙가공
• /
• 제26권6호
• /
• pp.341-347
• /
• 2017

Flexibly-reconfigurable roll forming (FRRF) is a novel sheet metal forming technology conducive to produce multi-curvature surfaces by controlling strain distribution along longitudinal direction. Reconfigurable rollers could be arranged to implement a kind of punch die set. By utilizing these reconfigurable rollers, desired curved surface can be formed. In FRRF process, three-dimensional surface is formed from two-dimensional curve. Thus, it is difficult to predict the forming result. In this study, a regression analysis was suggested to construct a predictive model for a longitudinal curvature of FRRF process. To facilitate investigation, input parameters affecting the longitudinal curvature of FRRF were determined as maximum compression value, curvature radius in the transverse direction, and initial blank width. Three-factor three-level full factorial experimental design was utilized and 27 experiments using FRRF apparatus were performed to obtain sample data of the regression model. Regression analysis was carried out using experimental results as sample data. The model used for regression analysis was a quadratic nonlinear regression model. Determination factor and root mean square root error were calculated to confirm the conformity of this model. Through goodness of fit test, this regression predictive model was verified.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• pp.811-822
• /
• 2020

This study investigates the gender differences in determinants of customers' satisfaction when purchasing online beauty and cosmetics products in Vietnamese market. To do so, we construct a data set via online survey of 419 Vietnamese customers including both males and females, and examine such sample using t-tests and multiple regressions. Our regression model is constructed based on our five-construct model including online shopping experience, customer service, external incentives, security and privacy, and personal characteristics. The t-tests results reveal that the mean difference of customer satisfaction (negative coefficient) between the two groups of customers (females and males) is statistically significant. This suggests that the purchasing satisfaction of male customers is significantly higher than that of their female counterparts. Similarly, we also find that male customers are more satisfied with their online shopping experience, customer service and external incentives offered by the online sellers than female peers. Furthermore, regression results for full sample show that, on average, the online shopping experience, customer service and external incentives are significantly and positively related to customer satisfaction. Yet, such positive effect of customer service on customer satisfaction is more likely for males while females' satisfaction is more positively influenced by security and privacy.

• Journal of the Korean Statistical Society
• /
• 제32권3호
• /
• pp.299-309
• /
• 2003

Let ${\pi}_1,...,{\pi}_{k}$k($\geq$2) independent logistic populations such that the cumulative distribution function (cdf) of an observation from the population ${\pi}_{i}$ is $$F_{i}\;=\; {\frac{1}{1+exp{-\pi(x-{\mu}_{i})/(\sigma\sqrt{3})}}},\;$\mid$x$\mid$<\;{\infty}$$ where ${\mu}_{i}(-{\infty}\; < \; {\mu}_{i}\; <\; {\infty}$ is unknown location mean and ${\delta}^2$ is known variance, i ＝ 1,..., $textsc{k}$. Let ${\mu}_{[k]}$ be the largest of all ${\mu}$'s and the population ${\pi}_{i}$ is defined to be 'good' if ${\mu}_{i}\;{\geq}\;{\mu}_{[k]}\;-\;{\delta}_1$, where ${\delta}_1\;>\;0$, i = 1,...,$textsc{k}$. A selection procedure based on sample median is proposed to select a subset of $textsc{k}$ logistic populations which includes all the good populations with probability at least $P^{*}$(a preassigned value). Simultaneous confidence intervals for the differences of location parameters, which can be derived with the help of proposed procedures, are discussed. If a population with location parameter ${\mu}_{i}\;<\;{\mu}_{[k]}\;-\;{\delta}_2({\delta}_2\;>{\delta}_1)$, i ＝ 1,...,$textsc{k}$ is considered 'bad', a selection procedure is proposed so that the probability of either selecting a bad population or omitting a good population is at most 1­ $P^{*}$.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• 융합경영연구
• /
• 제10권5호
• /
• pp.15-24
• /
• 2022

Purpose: The purpose of this study is to find a way to improve and overcome the psychological treatment limited to the negative factors dealt with in psychology from a positive psychological point of view. To this end, this study aims to verify whether a positive psychotherapy program can improve happiness, resilience, and post-traumatic growth along with improvement of psychological symptoms such as depression. Research design, data and methodology: To this end, in this study, mean difference analysis was conducted using t-test on 10 participants in the 16th PPT program and 14 in the control group. Also, after setting the main variables, we tried to confirm the effectiveness through simple regression analysis and multiple regression analysis of the causal relationship model. Results: As a result of the independent sample t-test and the paired sample t-test, it was confirmed that the group participating in the PPT program had higher flourish, happiness, resilience, post-traumatic growth, and lower depression. In addition, as a result of regression analysis, it was confirmed that post-traumatic growth had a positive effect, and that depression was a life-threatening factor. Conclusions: Since the PPT program has a positive effect on the participants with relatively negative psychological symptoms, it is necessary to expand it. In addition, it is necessary to introduce various preventive programs such as PPT as well as traditional psychological treatment for negative symptoms such as depression.

• 한국해양공학회지
• /
• 제7권2호
• /
• pp.114-120
• /
• 1993

Responses of marine vehicles and ocean structures in a seaway can be predicted by applying the probabilistic approach. When we consider a linear system, the responses in a random seaway can be evaluated through spectral analysis in the frequency domain. But when we treat nonlinear system in irregular waves, it is necessary to get time history of waves. In the previous study we introduced one-directional waves (long crested waves)as wave environment and carried out calculations and experiments in the waves. But the real sea in which marine vehicles and structures are operated has multi-directional waves (short crested waves). It is important to get a simulated random sea and analyse dynamic problems in the sea. We need entire sample function or probabillty density function to infer statistical value of random process. However if the process are ergodic process, we can get statistical values by analysis of one sample function. In this paper, we developed the simulation technique of multi-directional waves and proved that the time history given by this method keep ergodic characteristics by the statistical analysis.