• Journal of the Korean Statistical Society
• /
• v.4 no.1
• /
• pp.19-33
• /
• 1975

The Ministry of Agriculture and Fishery had carried out a random sample survey on rice yield by the method of plot cutting since 1959 to obtain correct statistics on rice production. There are important problems connected with the determination of optimum size and shape of sample plot, variation of yield between plots and field and variation in the time needed for different types of plot cutting. This kind of research has been performed in India by Dr. P. V. Sukhatme and Dr. V. G. Panse. Also the same optimum procedures are much different in Japan that in India. In Korea, the optimum procedures may well be different from either of these countries. Although the government is proceeding with the crop yield survey, it does not attempt to investigate plot problems but emphasize total rice yield estimation. This particular research was conducted on a scale enough that the author could personally supervise all of the work.

• Communications for Statistical Applications and Methods
• /
• v.20 no.5
• /
• pp.367-376
• /
• 2013

Cut-off sampling is widely used for a highly skewed population like a business survey by discarding a part of the population (the take-nothing stratum). In this paper, we suggest a new composite estimator of the take-nothing stratum total obtained by use of the survey results of the take-nothing stratum and a take-some sub-stratum (a part of take-some stratum) for a more accurate estimate of the population total. Small simulation studies are conducted to compare the performances of known estimators and the new composite estimator suggested in this study. In addition, we use briquette consumption survey data for real data analysis.

• Journal of the Korean Statistical Society
• /
• v.32 no.2
• /
• pp.103-119
• /
• 2003

Properties of stochastic regression imputation are discussed under the uniform within-cell response model. Variance estimator is proposed and its asymptotic properties are discussed. A limited simulation is also presented.

• Journal of the Korean Statistical Society
• /
• v.23 no.2
• /
• pp.463-482
• /
• 1994

In Bayesian analysis of randomized response models, the likelihood function does not combine tractably with typical priors for the parameters of interest, causing computational difficulties in posterior analysis of the parameters of interest. In this article, the difficulties are solved by introducing appropriate latent variables to the model and using the Gibbs sampling algorithm.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.465-471
• /
• 2001

Randomized response technique is a survey technique for eliminating evasive answer bias. But this technique has a problem. This procedure suffers from linguistic expression in randomizing device. Thus for solving the problem, in this paper, we suggested the randomized response technique using fuzzy logic.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.767-775
• /
• 2001

In this paper we propose a poll system using e-mail. This system expects to increase the response ratio because of including a questionnaire inner e-mail. Especially, this system automatically provides a general paper which is a result of categorical data analysis.

• Communications for Statistical Applications and Methods
• /
• v.3 no.1
• /
• pp.179-188
• /
• 1996

복합조사표본추출법(complex survey sampling)에 근거한 분할표분석에 카이제곱검정법을 사용할 때의 문제점들과 해결방법들을 살펴보았다. 나아가, 군집표본추출의 경우에 붓스트랩방법의 타당성을 보였으며, 실제자료분석을 통하여 실제 활용가능성과 잇점을 제시하였다.

• Journal of The Korean Digital Architecture Interior Association
• /
• v.13 no.3
• /
• pp.15-23
• /
• 2013

As a succeeding analysis on the variables' significance to 'Quality of Life(QOL)'(Kim, Dong-Yoon, 2012a), which has a purpose of trying to enhance the intersubjectiveness by means of quantitive methods to find the factors on the QOL, this study aims at finding the time serial change in the deciding factors to deepen the related researches on the theme. Using the similar statistical methods such as multiple regression and factor analysis for "2012 Seoul Survey" this study shows two similar points and one differentia. The similarities include the fact that five subcategories of happiness have relative statistical importance in the order of (1)financial condition, (2)health condition, (3)social activities, (4)community relationship and (5)family life and the fact that the five subcategories are conceptually different from the 5 deciding factors, which means the possibility to improve the survey design. And the difference is the 5 factors such as (1) social trust - amenities, (2)cultural life, (3)social indiscrimination - hope for elevation, (4)sharing - giving and (5)community spirit which are largely different from preceding study. Although only the first two factors have statistical significance this result has a implication that they reflect the new paradigm of social capital and the essential necessity of human survival; sharing-community-culture.

• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.883-897
• /
• 2008

This paper provides correct informations inflecting the present situation using the sample design in population that the National Statistical Office puts in operation of the mining and manufacturing industry statistical survey in 2006. This paper proposes new sampling design which is able to grasp business fluctuations and provide basic data for the rearing policy and management of the material industry and components industry. These sample design are the modified cut-off method and multivariate Neyman allocation using principal components and sampling method is the probability proportional systematic sampling.

• The Korean Journal of Applied Statistics
• /
• v.23 no.2
• /
• pp.325-333
• /
• 2010

Protection against disclosure of survey respondents' identifiable and/or sensitive information is a prerequisite for statistical agencies that release microdata files from their sample surveys. Coarsening is one of popular methods for protecting the confidentiality of the data. Grouped data can be released in the form of microdata or tabular data. Instead of releasing the data in a tabular form only, having microdata available to the public with interval codes with their representative values greatly enhances the utility of the data. It allows the researchers to compute covariance between the variables and build statistical models or to run a variety of statistical tests on the data. It may be conjectured that the variance of the interval data is lower that of the ungrouped data in the sense that the coarsened data do not have the within interval variance. This conjecture will be investigated using the uniform and triangular distributions. Traditionally, midpoint is used to represent all the values in an interval. This approach implicitly assumes that the data is uniformly distributed within each interval. However, this assumption may not hold, especially in the last interval of the economic data. In this paper, we will use three distributional assumptions - uniform, Pareto and lognormal distribution - in the last interval and use either midpoint or median for other intervals for wage and food costs of the Statistics Korea's 2006 Household Income and Expenditure Survey(HIES) data and compare these approaches in terms of the first two moments.