• Journal of the Korean Statistical Society
• /
• 제30권4호
• /
• pp.637-644
• /
• 2001

We investigated two kinds of mean square error (MSE) estimator of homogeneous linear estimator (HLE) for the population total under stratified multi-stage sampling. One is studied when the second stage variance component is estimable and the other is found in cafe it is not estimable. The proposed estimators are necessary forms of non-negative unbiased MSE estimators of HLE.

• 한국조사연구학회:학술대회논문집
• /
• 한국조사연구학회 2001년도 춘계학술대회
• /
• pp.59-71
• /
• 2001

층화 다단계 샘플링에서 모총계 추정을 위하여 동질선형추정량을 고려하고, 이 추정량의 설계기반분산추정법을 고찰하였다. 한 방법은 분산을 일단계 분산과 이단계 분산으로 구분하여 각 층에서 각각을 비편향 추정하는 방법이고, 또 다른 방법은 이단계 표본에서 선정한 부차표본을 이용하여 일단계 분산만을 추정하여 전체분산을 비편향 추정하는 방법이다. 전자는 이단계 분산이 추정 가능할 때 이용하기 좋으며 후자는 이단계 분산을 추정할 수 없을 때 용이하게 쓸 수 있다. 각각의 추정법에 대하여 동질선형추정량에 대한 비음 비편향 분산 추정량의 형태를 제안하였다. 향후 실제 조사에서 본 논문에서 제안한 분산추정법이 효과적으로 사용될 수 있기를 기대한다.

• 한국조사연구학회지:조사연구
• /
• 제2권1호
• /
• pp.59-71
• /
• 2001

층화 다단계 샘플링에서 모총계 추정을 위하여 동질선형추정량을 고려하고. 이 추정량의 설계기반 분산추정법을 고찰하였다. 한 방법은 분산을 일단계 분산과 이단계 분산으로 구분하여 각 층에서 각각을 비편향 추정하는 방법이고, 또 다른 방법은 이단계 표본에서 선정한 부하표본을 이용하여 일단계 분산만을 추정하여 전체분산을 비편향 추정하는 방법이다. 전자는 이단계 분산이 추정 가능할 때 이용하기 좋으며 후자는 이단계 분산을 추정할 수 없을 때 용이하게 쓸 수 있다. 각각의 추정법에 대하여 동질선형추정량에 대한 비음 비편향 분산 추정량의 형태를 제안하였다. 향 후 실제 조사에서 본 논문에서 제안한 분산추정법이 효과적으로 사용될 수 있기를 기대한다.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권7호
• /
• pp.79-90
• /
• 2021

The purpose of this research is to identify factors affecting the acceptance and use of e-tax services among medium taxpayers in Phnom Penh, Cambodia. The researcher conducted the study based on a quantitative approach by using multi-stage sampling method, which selects a sample size by two or more stages. The first stage sampling was the stratified random sampling and the subsequent stage was purposive sampling. In this study, the stratified random sampling was first used, followed by purposive sampling. The data were collected from 450 medium taxpayers who experienced using e-tax services located in three tax branches in Phnom Penh. This study adapted the confirmatory factor analysis (CFA) and structural equation model (SEM) to analyze the model accuracy, reliability and influence of various variables. The primary result showed that behavioral intention has a significant effect on user behavior of e-tax services among medium taxpayers in Phnom Penh, Cambodia. Moreover, the results revealed that performance expectancy, effort expectancy, social influence, and anxiety have significant impact on behavioral intention. In addition, social influence has the strongest impact on behavioral intention, followed by anxiety, performance expectancy and effort expectancy. Conversely, facilitating conditions, trust in government, and trust in internet do not influence behavioral intention.

• 한국임상수의학회지
• /
• 제28권4호
• /
• pp.422-426
• /
• 2011

For a national survey in which wide geographic region or an entire country is targeted, multi-stage sampling approach is widely used to overcome the problem of simple random sampling, to consider both herd- and animallevel factors associated with disease occurrence, and to adjust clustering effect of disease in the population in the calculation of sample size. The aim of this study was to establish sample size for estimating bovine tuberculosis (TB) in Korea using stratified two-stage sampling design. The sample size was determined by taking into account the possible clustering of TB-infected animals on individual herds to increase the reliability of survey results. In this study, the country was stratified into nine provinces (administrative unit) and herd, the primary sampling unit, was considered as a cluster. For all analyses, design effect of 2, between-cluster prevalence of 50% to yield maximum sample size, and mean herd size of 65 were assumed due to lack of information available. Using a two-stage sampling scheme, the number of cattle sampled per herd was 65 cattle, regardless of confidence level, prevalence, and mean herd size examined. Number of clusters to be sampled at a 95% level of confidence was estimated to be 296, 74, 33, 19, 12, and 9 for desired precision of 0.01, 0.02, 0.03, 0.04, 0.05, and 0.06, respectively. Therefore, the total sample size with a 95% confidence level was 172,872, 43,218, 19,224, 10,818, 6,930, and 4,806 for desired precision ranging from 0.01 to 0.06. The sample size was increased with desired precision and design effect. In a situation where the number of cattle sampled per herd is fixed ranging from 5 to 40 with a 5-head interval, total sample size with a 95% confidence level was estimated to be 6,480, 10,080, 13,770, 17,280, 20.925, 24,570, 28,350, and 31,680, respectively. The percent increase in total sample size resulting from the use of intra-cluster correlation coefficient of 0.3 was 22.2, 32.1, 36.3, 39.6, 41.9, 42.9, 42,2, and 44.3%, respectively in comparison to the use of coefficient of 0.2.

• 응용통계연구
• /
• 제28권6호
• /
• pp.1047-1061
• /
• 2015

층화표본추출(stratified sampling)은 모집단을 구성하는 층에 대한 정보를 표본설계에 반영함으로써 추정량의 분산을 낮추기 위한 표본추출 방법으로, 표본배분 방안의 선택이 층화표본의 효과를 결정하는데 매우 중요한 요소이다. 전통적인 표본배분 방법으로는 비례배분법(proportional allocation)과 네이만배분법(Neyman alloction)이 주로 사용되는데, 이는 층별 추정량의 분산에 영향을 미치는 요인들을 표본 배분에 반영함으로써 전체 추정량의 분산을 최적화하기 위한 것이다. 이론적으로는 층크기(size of strata)만을 반영하는 비례배분법보다 층별 표준편차(standard deviation)를 함께 고려하는 네이만배분법이 추정량의 분산을 낮추는데 더 효과적임이 알려져 있다. 그러나 층별 표준편차에 대한 사전 정보가 모집단을 잘 반영하지 못하면 네이만배분법의 효과를 기대할 수 없으며, 특히 복수의 관심변수를 조사하는 다목적조사(multi-purpose survey)에서는 각 관심변수들의 층별 표준편차가 서로 다른 양상을 나타내기 때문에 네이만배분법이 적합하지 않다는 주장이 제기되기도 한다. 한편 표본조사에서는 조사단계에서 발생하는 무응답으로 인한 추정량의 편향을 제거하기 위해 응답률 보정 방법이 사용되는데, 이 또한 추정량의 분산에 영향을 미치는 주요한 요인 중에 하나이다. 그러나 전통적인 표본배분 방법은 응답률(response rate)을 감안하지 않기 때문에 층별 응답율에 차이가 크게 나타날 경우 층화표본에 의한 효과가 저하될 수 있다. 이에 본 연구는 층화표본추출에서 층간 응답률의 차이가 추정량의 분산에 미치는 영향을 살펴보고, 층별 응답률 정보를 표본설계에 반영하는 새로운 표본배분 방법을 제안하였다. 모의실험을 통해 확인한 결과 네이만배분법은 당초 표본배분 시에 적용한 층별 표준편차의 구조가 각 층의 응답률 보정과정에서 증가하는 분산을 반영하지 못하기 때문에 층간 응답률의 편차가 커질수록 효율이 저하되는 것으로 나타났다. 반면 층 크기와 층별 응답률을 함께 반영한 배분방법은 비례배분법에 비해 효율이 개선되며, 층간 응답률의 편차가 클수록 그 효과는 커진다. 특히 층별 응답률의 변동계수(coefficient of variance)가 층별 표준편차의 변동계수를 상회하는 경우는 네이만배분법 보다도 효율적인 추정량을 제공함을 확인하였다. 아울러 응답률을 반영한 배분방법은 기존 배분방법에 비해 각 층별 추정량을 보다 안정적으로 추정할 수 있기 때문에 층별 추정을 목적으로 하는 층화표본조사에서는 여타 추정방법보다 더 효과적이다. 층별 응답률에 대한 정보는 관심변수가 다르더라도 추출틀이 유사한 기존 조사의 결과를 활용할 수 있다는 점에서 표준편차에 비해 비교적 정보 수집이 용이한 장점이 있고, 다목적조사에서도 관심변수의 척도(scale)나 개수와 관계없이 적용 가능하기 때문에 활용도가 높을 것으로 생각된다.

• 대한수의학회지
• /
• 제47권1호
• /
• pp.51-57
• /
• 2007

To establish a statistically reliable sampling strategy for serological surveillance of classical swinefever (CSF) in Korea, antibody test data from CSF surveillance conducted during year 2005 were analyzed.The most appropriate sampling method was determined to be stratified multi-stage random sampling strategy,in which the primary sampling unit is a pig farm and the secondary are the pigs by the strata of breedersand finishers in the selected farm. The optimum sample size was 5 to 19 including 1 to 2 breeders accordingto the number of pigs in the farm. The optimum sampling strategy demonstrated in this study was veryFindings of our study provide practical guidelines for surveillance of herd immunity level to CSF in Korea.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권7호
• /
• pp.225-234
• /
• 2021

This research aimed to investigate the key factors affecting student satisfaction and loyalty in selected private universities in Cambodia. The study implemented a quantitative survey designed and guided by seven hypotheses to test the causal relationships among variables, such as academic experience, faculty services, campus life, social integration, student support facilities, student satisfaction, university image, and student loyalty. The research applied a multi-stage sampling technique of probability procedures to guarantee the presence of the research population. Confirmatory Factor Analysis (CFA) and Structural Equation Modeling (SEM) were applied for data analysis to test the hypotheses model. The collected survey totaled 543 from three universities. The purposive sampling methods were used to select the three target universities, based on their reputation, the number of students, year of establishment, and the recognition from the Ministry of Education, Youth, and Sport. The stratified random sampling method was employed to select target respondents for data collection by dividing the population into subgroups to ensure a random sample. The results showed that student support facilities, campus life, and social integration, faculty services, and university image play very important roles in the satisfaction and loyalty of the students in three universities.

• 대한임상전기생리학회지
• /
• 제2권2호
• /
• pp.51-59
• /
• 2004

The purpose of this study was to analyze. The effect of participation physical activities on health care patterns in the aged. The subject of the study was selected by multi-stage stratified cluster random sampling among the aged center and aged club to participate program whose age were 65 and over year old among inhabitant the Kwangju metropolitan area. The data were collected through a questionnaire adapted from Payne and Hahn's(1986) 'Understanding Your Health-A personal profile; Evaluating Your Health'. The pilot test was executed after the questionnaire was translated into Korean.

• Journal of Preventive Medicine and Public Health
• /
• 제22권1호
• /
• pp.162-168
• /
• 1989

This study was conducted to analyse attitudes to a new health care system in a rural community. The specific purpose of this thesis was to classify attitudes to the patient referral system in Kangwha county, and to identify factors affecting the attitudes. Sampling was done by a multi-stage stratified cluster sampling method from the population. The data were collected in Kangwha county through a structured interview survey for two weeks in June, 1957. Attitudes to the patient referral system were classified into four types based upon answers to questions about awareness of the system, the recognition for the necessity of the system, and opinions on the improvement of the system. The four types of attitudes were active acceptance(10.2%), partial acceptance (27.2%), refusal(35.8%), and indifference(26.7%). The respondent's age, educational level, age of head of household, medical insurance fee, the number of ill family members, and the percentage of medical utilization by the family were the variables which affected the attitudes. The medical insurance fee, respondent's age, age of head of household, and the percentage of medical utilization by the family were the statistically significant discriminant factors of the four types of attitudes.