• 응용통계연구
• /
• 제35권4호
• /
• pp.569-577
• /
• 2022

비모수적 추정량의 성능을 이론적으로 비교하기 힘들 때 흔히 모의실험을 실시한다. 다양한 실험조건에서 여러 추정량에 대해 얻어진 모의실험 결과를 회귀모형을 이용해 분석하면 보다 체계적이고 정확한 비교를 할 수 있다는 것을 Kim과 Kim (2021)에서 보였다. 이 연구는 Kim과 Kim (2021)에 대한 후속연구이자 보완연구이다. 회귀모형의 오차항에 대한 분산공분산행렬에서 이분산성만 고려하고 공분산을 선행연구에서 무시했는데, 공분산을 고려하게 되면 분산공분산행렬은 블록대각행렬이 된다. 본 연구에서 블록대각행렬인 분산공분산행렬을 추정하여 분석에 이용하는 방법을 제시하였다. 이렇게 하면 명목신뢰수준을 보장하면서 유의하게 성능 차이가 나는 추정량 짝을 더 잘 찾을 수 있다는 것도 보였다.

• Journal of the Korean Data and Information Science Society
• /
• 제27권2호
• /
• pp.373-380
• /
• 2016

리커트형 데이터가 순서척도임에도 불구하고 많은 연구자들이 구간척도로 간주하여 모수 방법을 적용하고 있다. 본 연구에서는 리커트형 데이터를 어떻게 분석하는 것이 적절한지 모의 실험을 통하여 알아본다. 다양한 분포를 갖는 5점 리커트형 표본을 추출하여 위치를 비교하고, 순서척도의 경우 위치비교 보다 응답분포를 살펴보는 것이 더 타당하므로 응답분포 검정을 실시한다. 위치를 비교하는 방법으로는 구간척도로 생각하고 분석하는 모수 방법인 t-검정과 순서척도로 생각하는 비모수 방법인 만- 휘트니검정 (M-W검정)을 적용하고, 응답분포를 검정하기 위해서는 카이제곱 검정과 콜모고로프 - 스미르노프검정 (K-S검정)을 실시한다. 네 가지 방법의 효율성을 비교하기 위하여 제 1종 오류 (Type I error)의 비율과 검정력 (power)을 구한다.

• 한국환경과학회지
• /
• 제27권11호
• /
• pp.1029-1048
• /
• 2018

In this study, seasonal Mann - Kendall test method was applied to 12 stations of the water quality measurement network of Nam-River based on data of BOD, COD, TN and TP for 11 years from January 2005 to December 2015 The changes of water quality at each station were examined through linear trends and the tendency of water quality change during the study period was analyzed by applying the locally weighted scatter plot smoother (LOWESS) method. In addition, spatial trends of the whole Nam-River were examined by items. The flow-adjusted seasonal Kendall test was performed to remove the flow at the water quality measurement station. As a result, BOD, COD concentration showed "no trand" and TN and TP concentration showed "down trand" in regional Kendall test throughout the study period. BOD and TP concentration in "no trand", COD, and TN concentration showed an "up trand" tendency in Nam-River dam. LOWESS analysis showed no significant water quality change in most of the analysis items and stations, but water quality fluctuation characteristics were shown at some stations such as NR1 (Kyungho-River 1), NR2 (Kyungho-River 2), NR3 (Nam-River), NR6 (Nam-River 2A). In addition, the flow-adjusted seasonal Kendall results showed that the BOD concentration was "up trand" due to the flow at the NR3 (Nam-River) station. The COD concentration was "up trand" due to the flow at NR1 (Kyungho-River 1) and NR2 (Kyungho-River 2) located upstream of the Nam-River. The effect of influent flow on water quality varies according to each site and analysis item. Therefore, for the effective water quality management in the Nam-River, it is necessary to take measures to improve the water quality at the point where the water quality is continuously "up trand" during the study period.

• 응용통계연구
• /
• 제10권2호
• /
• pp.293-308
• /
• 1997

일변량 분할 역회귀 방법은 일반화 회귀모형에서 효과적인 차원축약방향과 공간을 추정하는 방법이다. 본 논문에서는 두 일반화 회귀모형을 동시에 고려하여 효과적인 차원축약방향과 공간을 추정하는 방법으로 이변량 분할 역회귀를 제안한다. 이러한 이변량 분할 역회귀 방법은 모형식이 선형, 이차형, 삼차형, 비선형 등의 여러 모형식에서 효과적인 차원축약방향을 추정하며, 일변량 분할 역회귀에 비하여 모형에 존재하는 오차에 크게 영향을 받지 않고 효과적인 차원축약방향을 추정한다. 특히 모형식이 대칭의 이차형인 경우에 일변량 분할 역회귀 방법이 효과적인 차원축약방향을 추정하지 못하는 문제를 해결할 수 있다.

• Bioinformatics and Biosystems
• /
• 제1권1호
• /
• pp.67-72
• /
• 2006

The aim of this paper is to discuss the effect of missing values in detecting differentially expressed genes in a cDNA microarray experiment in the context of a one sample problem. We conducted a cDNA micro array experiment to detect differentially expressed genes for the metastasis of colorectal cancer based on twenty patients who underwent liver resection due to liver metastasis from colorectal cancer. Total RNAs from metastatic liver tumor and adjacent normal liver tissue from a single patient were labeled with cy5 and cy3, respectively, and competitively hybridized to a cDNA microarray with 7775 human genes. We used $M=log_2(R/G)$ for the signal evaluation, where Rand G denoted the fluorescent intensities of Cy5 and Cy3 dyes, respectively. The statistical problem comprises a one sample test of testing E(M)=0 for each gene and involves multiple tests. The twenty cDNA microarray data would comprise a matrix of dimension 7775 by 20, if there were no missing values. However, missing values occur for various reasons. For each gene, the no missing proportion (NMP) was defined to be the proportion of non-missing values out of twenty. In detecting differentially expressed (DE) genes, we used the genes whose NMP is greater than or equal to 0.4 and then sequentially increased NMP by 0.1 for investigating its effect on the detection of DE genes. For each fixed NMP, we imputed the missing values with K-nearest neighbor method (K=10) and applied the nonparametric t-test of Dudoit et al. (2002), SAM by Tusher et al. (2001) and empirical Bayes procedure by $L\ddot{o}nnstedt$ and Speed (2002) to find out the effect of missing values in the final outcome. These three procedures yielded substantially agreeable result in detecting DE genes. Of these three procedures we used SAM for exploring the acceptable NMP level. The result showed that the optimum no missing proportion (NMP) found in this data set turned out to be 80%. It is more desirable to find the optimum level of NMP for each data set by applying the method described in this note, when the plot of (NMP, Number of overlapping genes) shows a turning point.

• Journal of Korean Neurosurgical Society
• /
• 제52권6호
• /
• pp.523-527
• /
• 2012

Objective : The incidence of spontaneous spinal epidural hematoma (SSEH) is rare. Patients with SSEH, however, present disabling neurologic deficits. Clinical outcomes are variable among patients. To evaluate the adequate treatment method according to initial patients' neurological status and clinical outcome with comparison of variables affecting the clinical outcome. Methods : We included 15 patients suffered from SSEH. Patients were divided into two groups by treatment method. Initial neurological status and clinical outcomes were assessed by the American Spinal Injury Association (ASIA) impairment scale. Also sagittal hematoma location and length of involved segment was analyzed with magnetic resonance images. Other factors such as age, sex, premorbid medication and duration of hospital stay were reviewed with medical records. Nonparametric statistical analysis and subgroup analysis were performed to overcome small sample size. Results : Among fifteen patients, ten patients underwent decompressive surgery, and remaining five were treated with conservative therapy. Patients showed no different initial neurologic status between treatment groups. Initial neurologic status was strongly associated with neurological recovery (p=0.030). Factors that did not seem to affect clinical outcomes included : age, sex, length of the involved spinal segment, sagittal location of hematoma, premorbid medication of antiplatelets or anticoagulants, and treatment methods. Conclusion : For the management of SSEH, early decompressive surgery is usually recommended. However, conservative management can also be feasible in selective patients who present neurologic status as ASIA scale E or in whom early recovery of function has initiated with ASIA scale C or D.

• 지역연구
• /
• 제34권2호
• /
• pp.49-64
• /
• 2018

본 연구에서는 수도권의 통근통행에 기초하여 중심지의 설정방법론을 제시하고, 기존의 중심지 설정방법과 비교 분석하였다. 이를 위해 수도권의 행정동을 대상으로 지역 간 통근통행량을 이용하여 요인분석 및 공간적 자기상관분석을 수행함으로써 중심지를 도출하였다. 또한 선행연구의 중심지 설정 방법론을 특성에 따라 단일지표 기반의 방법, 다수지표 기반의 방법, 비모수적 분석방법, 공간통계 분석방법의 네 가지로 분류하여 각각의 방법론을 적용한 결과를 비교분석하였다. 분석결과, 서울의 주요한 중심지를 포함하여 일부 유사한 중심지가 도출되었으나 각 방법론마다 상이한 결과가 나타났고, 수도권의 다핵 중심지를 설정하는데 한계가 있음을 보여주었다. 이 연구를 통해, 이미 다핵 도시공간구조의 수도권이 이제는 광역도시권의 맥락에서 논의되고 있는 상황에서 새로운 중심지 체계에 기반한 공간구조계획의 수립 보완이 필요함을 재확인할 수 있다.

• 한국임상수의학회지
• /
• 제27권1호
• /
• pp.66-70
• /
• 2010

Reference interval is critical for interpreting laboratory results, monitoring response to therapy and predicting the prognosis of the patients in clinical settings. The aim of the present study was to update established reference intervals for routine hematologic and serum chemistry values for a population of clinically healthy dogs (range, 1-8 years) seen in an animal hospital. Blood was obtained by venipuncture while animals were physically restrained, and samples were analyzed for 9 chemistries on MS9-5H (Melot Schloesing Lab, France) and 6 hematology on Vet Test 8008 (IDEXX, USA). Data from 105 dogs (52 males and 53 females) for hematology and 113 dogs (37 males and 76 females) for chemistry were used to determine reference intervals using the parametric, nonparametric and bootstrap methods. Prior to analysis, all parameters were tested for normal distribution using Anderson-Darling criterion. Of the 9 biochemical analytes, alkaline phosphatase, alanine aminotransferase, aspartate aminotransferase, creatinine, total protein, and glucose concentrations did not fit normal distribution for both original and transformed data. All but eosinophil count satisfied normal distribution for either original or transformed data. Parametric method can be used for original cholesterol concentrations, RBC, WBC, and neutrophil counts. This technique can also be used for power-transformed values of blood urea nitrogen concentrations and for logarithm of lymphocyte and monocyte counts. Non-parametric or bootstrap method was the preferred choice for the remaining 7 biochemical parameters and eosinophil count as they did not follow normal distributions. All three statistical techniques performed in similar reference intervals. When establishing reference intervals for clinical laboratory data, it is essential to assess the distribution of the original data to increase the accuracy of the interval, and non-parametric or bootstrap methods are of alternative for the data that do not fit normal distribution.

• 한국안전학회지
• /
• 제37권1호
• /
• pp.64-69
• /
• 2022

The study measured a subway construction worker's Macpa stress by Heart Rate Variability measuring instrument and conducted a survey of Korean job stress from subway construction workers. Also, the study analyzed the relationship between Macpa stress index and Korean job stress result and suggested managing stress method for each item. According to National Statistical Office data, the first line subway in Seoul was started to open in 1974. The extended total length is 996 kilometers until 2019. Many aged workers are currently working at subway construction sites due to the avoidance of young workers since the past until now. It means that the elderly has a substantial portion among subway construction workers. The productivity has been adversely affected by health problems due to the aging of workers, job stress due to heavy work, and personal health problems. So, the regulation and policies on job stress health management are being strengthened. The data were measured Macpa stress by machine measuring heart rate variability and conducted Korean job stress survey(shortened) from Sa-sang to Ha-dan line Busan subway construction workers for analyzing the relationship. Independent variable were age, job duration, job position, employment type, working type in this study. Macpa's dependent variable was stress index and Korean job stress survey(shortened)'s dependent variables were job requirements, job autonomy, relationship conflict, job instability, organizational structure, inappropriate compensation, working place culture, and total score. SPSS 12.0 K Statistics Program was used for statistical analysis. Kruskal-wallis test, a nonparametric statistical analysis, was used because the data are difficult to be assumed as normal distribution. As a result, the paper indicated the significant correlation between Macpa stress index and Korean job stress(short version). The elderly workers presented higher Macpa index and higher job stress due to aging and heavy-duty work. The majority workers were daily workers who had unstable working condition and uncertainty about the future. The study suggested a manual that could reduce job stress for subway construction workers and future study deriving management tool through analyzing job stress factor is necessary.

• 재활치료과학
• /
• 제3권2호
• /
• pp.71-81
• /
• 2014

목적: 본 연구의 목적은 CPM (Continuous Passive Motion)을 뇌졸중 환자의 손 기능 및 수부 근력 재활에 사용하고 그 영향을 살펴보는데 있다. 연구방법 : 본 연구의 대상자는 뇌졸중으로 인한 편마비 증상을 가진, Brunnstrom 4-6단계에 해당하는 치료후 18개월 이내의 급성기 환자 3명이다 연구방법은 3명의 대상자에 대하여 단일사례 (A-B) 실험설계를 사용하였으며 CPM의 영향을 검사하기 위해 젭슨수지기능, 퍼듀페그보드, 수부근력 세 가지를 측정하였다. CPM 적용기간은 3주였으며, 적용회수는 하루 2회, 매회 20분씩, 총 30회기였다. 연구결과: 수부근력 측정 중 손끝잡기에서 대상자 2명의 값이 변화가 없었다. 그 외의 젭슨수지기능, 퍼듀페그보드, 수부근력 검사에서는 CPM 적용 후의 검사 결과가 향상되었다. 결과의 유효성 검증을 위하여 비모수적 통계방법인 Wilcoxon signed ranks test를 실시한 결과 모든 항목에 대한 P-Value가 0. 05 보다 큰 값이 나와 처치 전 후 값의 차이가 통계적으로는 유의미하지 않다는 결과를 얻었다. 결론: 참여 대상자 수가 적고 프로그램 적용 기간이 짧은 제한점이 있으나, 수부 재활을 위해 실시한 CPM이 연구대상자 전원의 손 기능 및 근력 향상에 영향을 주었다는 것을 확인하였다. 이는 주로 하지 기능과 근력 향상을 위해 사용되는 CPM이 급성기 뇌졸중 환자의 수부 치료에도 유용하게 사용될 수 있음을 보여준다.