• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.645-653
• /
• 2014

P-value is the probability of observing a current sample and possibly other samples departing equally or more extremely from the null hypothesis toward postulated alternative hypothesis. When p-value is less than a certain level called ${\alpha}$(= 0:05), researchers claim that the alternative hypothesis is supported empirically. Unfortunately, some findings discovered in that way are not reproducible, partly because the p-value itself is a statistic vulnerable to random variation. Boos and Stefanski (2011) suggests calculating the upper limit of p-value in hypothesis testing, using a bootstrap predictive distribution. To determine the sample size of a replication study, this study proposes thought experiments by simulating boosted bootstrap samples of different sizes from given observations. The method is illustrated for the cases of two-group comparison and multiple linear regression. This study also addresses the reproducibility of the points in the given 95% confidence interval. Numerical examples show that the center point is covered by 95% confidence intervals generated from bootstrap resamples. However, end points are covered with a 50% chance. Hence this study draws the graph of the reproducibility rate for each parameter in the confidence interval.

• The Korean Journal of Applied Statistics
• /
• v.1 no.1
• /
• pp.12-20
• /
• 1987

This paper aims at studing on a multi-purpose sampling design involving both a farm population survey and a livestock survey. Some features of this design are firstly to equalize the sampling errorsamong Shi-Gun (county) estimates, secondly, to make an efforts to increase the precision by introducing a purpose sample into the probability sample. There are two types of purpose samples according to sampling units; one is farm, the otheris enumeration district. A criterion of demarcation for selecting the farm purposesamle was investigated.

• Journal of Food Hygiene and Safety
• /
• v.30 no.2
• /
• pp.127-131
• /
• 2015

This study aimed to calculate the required sample size to monitor food items during risk assessment studies. Based on a data set from a previous study (2,400 data points for heavy metal assessment from 17 food items), the required sample size was estimated by using a single equation with the standard deviation value, error range, and 95%-99% confidence intervals. The required sample size was calculated with each of the heavy metals for the assessment. The results showed that cadmium, lead, and mercury of required sample sizes for further monitoring were range of 7-90, 7-1, 062, and 11-238, respectively. We found that the required sample size varied depending on the standard deviation of the previous monitoring data. This study provides a basic method to determine the minimum sample size required in food monitoring to devise practical sampling strategies.

• The Korean Journal of Applied Statistics
• /
• v.9 no.2
• /
• pp.145-159
• /
• 1996

We propose an adaptive searching method using some spatial relations among sample points to estimate the interesting area in the spatial population. The fundamental idea is to observe the neighboring sample points when a sample point is satified with some condition of an adaptive searching observation. For obseving the sample points with this method to estimate the area the sample size is decreased. From this result, we may expect to reduce the cost and time consuming in observation the sample points and to draw the shape of the interesting area without prior information of an spatial population. Some analytical simulation results are also presented.

• Korean Journal of Soil Science and Fertilizer
• /
• v.2 no.1
• /
• pp.75-78
• /
• 1969

The necessary number of hills for panicle counts have been obtained, and are more in Kangwon-Do and Chulla Nam-Do where the variability of sampling error is higher as compared to other provinces. It seems that number of samples do not depend on the latitude but on the variabilities of yield components within the province and it is considered that about 5% sampling fraction gives about 75 to 85% of relative information on the average.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.304-304
• /
• 2018

이변량 빈도해석은 일반적으로 고정지속기간 강우량에 대해 빈도해석하는 단변량 빈도해석에 비해 지속기간을 확률변수로 이용하여 강우량과 동시에 확률변수로 사용할 수 있다는 장점이 있다. 하지만 확률분포형의 차원이 증가하기 때문에 기존 단변량 빈도해석에서 요구되던 표본크기보다 더 많은 표본이 필요하다. 우리나라 강우관측소의 경우 오래된 관측소의 경우에도 기록년수가 60년을 넘지 않아 연최대계열로 확률표본을 작성할 경우 이변량 빈도해석을 수행하기에 부족할 수 있다. 따라서 본 연구에서는 Peaks Over Threshold (POT) 방법을 이용하여 적정 확률표본을 선택하는 연구를 진행하였다. 서울 기상청 지점의 강우자료로부터 최소무강우시간을 이용하여 모든 강우사상을 추출하였으며 각 강우사상의 강우량과 지속기간이 확률변수로 사용되었다. 기존에 알려진 POT 방법들과 Anderson-Darling 적합도 검정을 이용한 절단값 산정방법등을 적용하여 확률표본 개수의 변화에 따른 주변분포형의 적합도 검정과 이변량 확률모형의 적합성을 살펴보았다.

• Composites Research
• /
• v.37 no.3
• /
• pp.179-185
• /
• 2024

This study quantitatively evaluated and investigated the changes in transverse tensile strength of unidirectional fiber-reinforced composites with initial void defects using a Representative Volume Element (RVE) model. After calculating the appropriate sample size based on margin of error and confidence level for initial void defects, a sample group of 5000 RVE models with initial void defects was generated. Dimensional reduction and density-based clustering analysis were conducted on the sample group to assess similarity, confirming and verifying that the sample group was unbiased. The validated sample analysis results were represented using a Weibull distribution, allowing them to be applied to the reliability analysis of composite structures.

• Journal of Korean Society of Transportation
• /
• v.24 no.3 s.89
• /
• pp.7-15
• /
• 2006

A large sample can Provide more information about the Population. As the sample size Increases, analysts will be more confident about the survey results. On the other hand, the costs for survey will increase in time and manpower. Therefore, determination of the sample size is a trade-off between the required accuracy and the cost. In addition, permitted error and significance level should be considered. Sample size determination in surveys for O/D estimation is also connected with confidence of survey result. However, the past methods were usually too simple to consider confidence. Therefore, a new method for O/D surveys was Proposed and it was accurate enough, but it has too large sample size when we have current budget constraint. In this research, several minimum sample size determination methods for origin-destination survey under budget constraint were proposed. Each method decreased sample size, but has its own advantages. Selection of the sample size will depend on the study Purpose and budget constraint.

• Survey Research
• /
• v.10 no.1
• /
• pp.155-168
• /
• 2009

As an efficient sampling design, stratified random sampling is often used when auxiliary information is available at the designing stage. Although one - per - stratum design is an efficient design that can be used when many auxiliary variables are available, it does not provide any unbiased variance estimator. With a two - per - stratum sample in which two elements are selected from each stratum, it is possible to obtain an unbiased variance estimator. However the loss of efficiency could be significant if any important stratification variable is missed. In this study, we investigated a sampling design that uses the all given auxiliary information and also permits an unbiased variance estimator suggested by Park and Fuller(2008). Through a simulation study, we compared several stratified random sampling and systematic sampling design. We also applied the proposed stratified sampling designs to 2007 youth panel data.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.26 no.4
• /
• pp.293-297
• /
• 1981

An attempt has been made to determine the optimum size of sampling unit and the number of samples for a given precision in wheat, using the data collected from the various experiments in 1979/80. It was found that the coefficients of variation for number of spikes except the case of high-ridge broadcasting by 8HP rotarized seeder are in the same order of those for yield of wheat, and the regression coefficients associated with the coefficients of variation and the size of sampling unit were significant at 1% level of type I error. A wide range of variation in the size of sampling unit was observed for different methods of seeding, indicating the proper sizes of sampling units for 40cm \times 18cm, 60cm \times 18cm, 20cm \times 5cm, 120cm \times 90cm to be 0.40$m^2$, 0.17$m^2$, , 0.11$m^2$, , 0.55$m^2$, , respectively. The variance component for the experimental error was not physically possible to estimate due probably to high variability among the sampling units. The number of the sampling units per plot for a given precision of CV=12% was estimated to be one in an experiment with 4 replicates.