• Communications for Statistical Applications and Methods
• /
• v.3 no.1
• /
• pp.131-143
• /
• 1996

다변량 층화임의추출에서 한 변수의 Neyman 최적배분은 다른 변수에 대한 층화분산을 최소화시키지 못하는 결과를 초래할 수도 있다. 따라서 다변량 자료의 경우 '최적'배분 대신에 '절충'배분이 도입되어 왔다. 이 연구에서는 각 변수별 Neyman 최적배분에 근거해서 얻은 층화표본평균벡터의 공분산 행렬에 가장 잘 적합되는 층별로 동일한 크기의 절충배분을 찾고자 한다. 이에 적절한 기준 다섯가지를 제시하고 예를 통해 비교, 분석하였다.

• The Korean Journal of Applied Statistics
• /
• v.21 no.3
• /
• pp.377-385
• /
• 2008

Most of the sample surveys conducted by several statistics preparation agencies are multipurpose surveys inquiring into several distinguishing items through a single sample. In a multipurpose sample design, the stratification tends to be very complex since the stratification variables which are both multivariate and heterogeneous must be considered collectively. In this paper we point out an outlier effect in a multivariate stratification to which the K-means clustering method is applied and propose to consider outliers prior to the stratification step. We also show an empirical stratification effect under consideration of outliers through a case study of sample design for The Rural Living Indicators.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.1
• /
• pp.79-89
• /
• 1999

A counting rule that allows an element to be linked to more than one enumeration unit is called a multiplicity counting rule. Sample designs that use multiplicity counting rules are called network samples. Defining a network to be a set of observation units with a given linkage pattern, a network may be linked with more than one selection unit, and a single selection unit may be linked with more than one network. This paper considers allocation for multivariate stratified random sampling with multiplicity.

• Survey Research
• /
• v.9 no.1
• /
• pp.69-85
• /
• 2008

Stratification is a feature of the majority of field sample design. This paper considers the multivariate stratification strategy for multipurpose sample survey with several auxiliary variables. In a multipurpose survey, stratification procedure is very complicated because we have to simultaneously consider the efficiencies of stratification for several variables of interest. We propose stratification strategy based on factor analysis and cluster analysis using several stratification variables. To improve the efficiency of stratification, we first select the stratification variables by factor analysis, and then apply the K-means clustering algorithm to the formation of strata. An application of the stratification strategy in the sampling design for the Fisher Production Survey is discussed, and it turns out that the variances of estimators are significantly less than those obtained by simple random sampling.

• The Korean Journal of Applied Statistics
• /
• v.20 no.2
• /
• pp.387-394
• /
• 2007

This paper considers several stratification strategies for multivariate and multipurpose survey with several quantitative stratification variables. We propose three methods of stratification based on, respectively, the method of cumulative frequency square root which is the most popular one in univariate stratification, cluster analysis, and factor analysis followed by cluster analysis. We then compare the efficiency of those methods using the Dong-Eup-Myun data of the holding numbers of farming machines, extracted from the 2001 Agricultural Census. It turned out that the method based on cluster analysis with factor analysis would be a relatively satisfactory strategy.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.677-686
• /
• 2009

Stratification of population is widely used to improve the efficiency of the estimation in a sample survey. However, it causes several problems when there are some variables containing outliers. To overcome these problems, Park and Yun (2008) proposed a rather subjective method, which finds outliers before $\kappa$-means clustering for stratification. In this study, we propose the $\kappa$-spatial medians clustering method which is more robust than $\kappa$-means clustering method and also does not need the process of finding outliers in advance. We investigate the characteristics of the proposed method through a case study used in Park and Yun (2008) and confirm the efficiency of the proposed method.

• Journal of Preventive Medicine and Public Health
• /
• v.25 no.2 s.38
• /
• pp.148-156
• /
• 1992

A case-control study was conducted to investigate the relationship between blood cadmium, blood zinc and cadmium/zinc ratio and hypertension. Eighty-three hypertensive and seventy-seven normotensive study subjects matched for age and sex were selected from the workers who had no history of job-related cadmium exposure, in Ulsan city and it's vincinity, Korea. The blood cadmium in hypertensive group was $2.90{\eta}g/mL$, which was significantly higher than that of control group, $1.99{\eta}g/mL$(P<0.01). After stratifing for smoking and age variables, the relationship was still remained. The blood cadmium/zinc ratio in hypertensive group was 2.46, which was significantly higher than that of control group, 1.65(P<0.01), After stratifing for smoking and age variables, the relationship was still remained. There was no significant differance in blood zinc between hypertensive and control group. On multiple logistic regression analysis, the blood cadmium/zinc ratio is highly significant than blood cadmium. In conclusion, there is the possible relationship between blood cadmium level which has been known to be within normal limits and hypertension. But, futrher cohort studies to define the effect of cadmium on human hypertension are required.

• Journal of the Korea Convergence Society
• /
• v.7 no.4
• /
• pp.1-7
• /
• 2016

Structural MRI(sMRI) imaging is used to extract morphometric features after Grey Matter (GM), White Matter (WM) for several univariate and multivariate method, and Cerebro-spinal Fluid (CSF) segmentation. A new approach is applied for the diagnosis of very mild to mild AD. We propose the classification method of Alzheimer disease patients from normal controls by combining morphometric features and Gaussian Mixture Models parameters along with MMSE (Mini Mental State Examination) score. The combined features are fed into Multi-kernel SVM classifier after getting rid of curse of dimensionality using principal component analysis. The experimenral results of the proposed diagnosis method yield up to 96% stratification accuracy with Multi-kernel SVM along with high sensitivity and specificity above 90%.

• Journal of Preventive Medicine and Public Health
• /
• v.30 no.4 s.59
• /
• pp.669-685
• /
• 1997

Previous studies, reporting the inverse relationship between osteoarthritis and osteoporosis suggest the existence of possible pathophysiologic mechanisms between them. To examinine the hypothesis that 'bone mineral densities of women with osteoarthritis are significantly higher than that of women without osteoarthritis in Korea', subjects from the health and nutritional examination survey in Kuri city were sampled. Samples were selected through multi-stage sampling frame using established clusters in Kuri city. From August 18 to September 10,1997, the survey was conducted. Among the. total number of selected sample population (1,656 people), response .ate was 52.4 percent (348 men and 519 women). 420 women who took BMD measurement, radiologic exam, and anthropometric exam were selected for the analysis. The analytic results are as follows. 1. General characteristics: Mean BMD was $0.493g/cm^2$, mean age was 43.0, mean BMI was $23.9kg/m^2$. The number of women who experienced menopause was 106, hysterectomy was 19. There were 0 case of osteoarthritis of hip, 64 cases of osteoarthritis of knee, and 2 cases of osteoarthritis of hand. 2. Univariate analysis results: Mean BMD of women with the osteoarthritis of knee was significantly lower than that of women without the osteoarthritis of knee(0.4269 vs. $0.5057g/cm^2$). But, there were too few cases of osteoarthritis of hip and hand, so comparative studies of BMD in osteoarthritis of hip and hand could not be conducted. There were significant differences of BMD among pre-menopause group(0.5204), post-menopause group(0.4206), and hysterectomy group(0.4881). Additionally, there were significant differences of BMD among diabetes group(0.4297), impaired glucose tolerance group(0.4874), and normal group(0.5057). Furthermore, age, parity, BMI, bioimpedance were significantly related with BMD. 3. Multivariate analysis results: To examinine the relationship between osteoarthritis and BMD while controlling the other variables' effects which were significant in the univariate analyses, multiple linear regression analysis was done. But, it was found that osteoarthritis of knee was not a significant variable to BMD anymore. While age and menopause had significant negative relationship with BMD. Diabetes, parity, BMI, and bioimpedance did not have significant relationships with BMD. After stratification of subjects according to menopause, multiple linear regression analyses were done to each strata. Consequently, age in post-menopause group, age and osteoarthritis of knee in hysterectomy group showed significant negative relationship with BMD. The results did not support the many results of other previous studies done with white men and women. further studies of biological plausibility to Korean women are recommended. Also it is suggested that longitudinal study to verify the relationship between osteoarthritis and BMD will be valuable.

• Journal of agricultural medicine and community health
• /
• v.29 no.1
• /
• pp.1-14
• /
• 2004

Objectives: We investigated the factors related to health examination behaviors, sociodemographic aspects and lifestyles of elderly persons with different social backgrounds, and compared sexual and regional differences in urban and rural elderlies. Methods: The total study subjects(464 individuals) from urban(236) and rural areas(228), recruited by a stratified cluster random sampling were interviewed and examined about their sociodemographic profiles, daily lifestyles, subjective health status, conditions concerning use of medical resources, hearing acuity, visual acuity and ADL(activity of daily living), and whether they receive health examination or not. For statistical analysis, Chi-square test was used for sexual and regional comparisons among the groups who have been given a health examination and the one who have not. Results: In urban areas, the rate of having underwent health examination was 54.5% in men and 46.9% in women, and in rural areas, it was 59.8% in men and 42.7% in women, showing its higher rate in men than in women in both areas. For regional differences between the group who have taken a health examination and the one who have not, there was a significant difference in terms of age, family pattern, current job, monthly household income, owning a house, drinking status, eating habit, subjective health status, whether they have taken outpatient medical service for the recent 3 months or not, anxiety for the health, and IADL conditions according to whether the community is rural or urban. In multiple regressions, the influential factors on the health examination behaviors were selected such as having their own house, their family doctor, amnesia, urinary incontinence and chronic disease in urban districts. But in rural districts, the variables were selected such as having or not of their family doctor, urinary incontinence, anxiety for the health, educational level, their own house and chronic disease. Conclusions: It is suggested that the approach to the health examination of an older patient requires substantial consideration of highly variable individual sociodemographic characteristics involving regional attributes as well as their daily life styles, subjective health status, status of performing health examination, physical health status and ADL conditions.