• 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.

• 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 Environmental Health Sciences
• /
• v.46 no.4
• /
• pp.457-469
• /
• 2020

Objective: This study was designed to estimate the precise nationwide number of those who used humidifier disinfectants (HDs) and experienced specific health effects, including death, due to exposure to HDs in Korea between 1994 and 2011. Methods: A total of 5,000 households (15,472 people) were surveyed by stratifying the sample with a design that is equivalent to nationally approved household systematic sampling and face-to-face interviews from October 16, 2019 to December 30, 2019. Results: The proportion of use of humidifier disinfectants at home was 18.4% (2,844/15,472 people) and the proportion of those who experienced health effects among those who were exposed to HDs was 10.7% (303/2,844 people). Based on these factors, it was estimated that 8.94 million people (95% CI=8.25-9.63 million) were exposed to HDs and 0.95 million people (95% CI=0.87-1.02 million) experienced health effects, which means almost one in five and one in fifty Koreans respectively. The estimated number of deaths from HDs were 20,366 people (95% CI=18,801-21,931). Conclusion: The survey was large and analyzed a representative sample across the country, so this estimation of the nationwide population exposed and at risk to HDs is more accurate and reliable than previous studies. However, it is necessary to confirm whether results similar to those of this study can be reproduced through a survey using a cross-sectional survey at the national level. In particular, a survey focused on death cases is needed.

• Journal of Forest and Environmental Science
• /
• v.25 no.3
• /
• pp.167-175
• /
• 2009

An exploratory study was conducted in Juri Forest Range-2, a proposed biodiversity conservation area of Bangladesh to explore the present growing stock of tree, regeneration condition and status of non-timber forest products (NTFPs). This conservation area contains both natural and artificial plantation was selected by using multistage random sampling method. For determination of plot size and sampling methods, the quadrate size ($10m{\times}10m$) for tree stock measurement, ($2m{\times}2m$) for regeneration survey, ($20m{\times}20m$) for NTFPs survey was determined. Regarding tree stock survey, 14 species under eight families were found where Tectona grandis shows average number of stem/ha was 624 and basal area/ha was (10.36 $m^2/ha$) followed by Acacia auriculiformis (0.2 $m^2/ha$ and 637 stem/ha), Gmelina arborea (0.2 $m^2/ha$ and 600 stem/ha). In regeneration survey, 14 species were found belonging to 9 families where Alstonia scholaris shows highest (3,750) seedling per hectare. Regarding NTFPs, bamboo and cane are the most common resources. In last ten years, the total timber output was 1,28,596.14 cubic feet and total amount of revenue was 4,64,434 US$. The vacant area is 1,335.5 acre which contains 14% of total area. If this vacant area is planted with suitable species and take proper steps for appropriate management of this species it will be a good biologically diversified area.

• Journal of Preventive Medicine and Public Health
• /
• v.34 no.4
• /
• pp.417-426
• /
• 2001

Objectives : To analyse the psychosocial factors associated with hypertension management(drug treatment and life style modification) of newly detected cases and to understand and assess their behavioral intention or behaviors. Methods : The survey area was a combined urban and rural area in Chungnam province, Korea, and the sampling method was cluster sampling. Study subjects included 541 newly detected cases of hypertension rated above stage 2 by JNC-VI from a community survey. The first survey was applied to 383 of these patients in order to discern their psychosocial characteristics. A follow-up survey was given to 345 persons with an 11-month interval following monthly telephone counseling concerning medication and life style modification by trained nurses. The final study subjects for analysis comprised 271 persons after excluding cases of incomplete data and change of address. Results : Among the 85(33.2%) new patients who had intended to undergo drug treatment, 30(35.3%) persons were treated with antihypertensive agent after 11 - month interval, while among the patients with no intention to receive treatment, only 36(21.1%) persons were treated. Hypertensive patients with a high intention score revealed a high score in life style modification compliance as well. Seventy three percent of the variance of behavioral intention to undergo hypertension management was explained by the patients attitude toward performing the behavior and subjective norm associated with behaviors related to the theory of reasoned action in structural modeling. Actual behaviors related positively with behavioral intention. The coefficient of determination was 0.255. Conclusion : Improving the compliance level of hypertensive patients in respect to drug treatment or life style modification requires a build up of positive behavioral intention, and caregivers must pay more attention to eventually converting behavioral intention to actual behaviors.

• The Korean Journal of Applied Statistics
• /
• v.14 no.1
• /
• pp.81-90
• /
• 2001

One of the Repeated survey which estimates variability of population, we can be consider rotation sample survey. There are two kinds of rotation sample survey - onelevel rotation sample survey and multi-level rotation sample survey. In rotation sample survey, Composite estimator is used to measure level or level change of the population. This study suggests Generalized Composite estimator as considering intraclass correlation in multi-level rotation sample survey, and optimal weight minimizing variance of estimator. Numerical example shows efficiency of Generalized Composite estimator as considering intraclass correlation according to the sample unit and change degree of intraclass correlation in the rotation group.

• Asia-Pacific Journal of Business
• /
• v.13 no.3
• /
• pp.329-341
• /
• 2022

Purpose - The purpose of this study was to investigate consistency in estimating the number of vacant jobs using the two business labor force survey with two different time points of survey. Design/methodology/approach - We studied the cause of the differences in estimating the number of vacant jobs between the monthly sample and the new sample in business labor force survey. Findings - To summarize our findings, As the size of the company increases, the number of vacant jobs in the company also increases, and the probability that the number of vacant jobs in the company is zero decreases. The monthly sample was assessed to have a higher likelihood that the number of vacant jobs in the company was zero and the number of vacant jobs was considerable compared to the local sample. Research implications or Originality - Because local survey sample companies tend to minimize the number of vacant jobs even when they reply under the same conditions, the estimation result of the number of vacant jobs in the current monthly survey differs significantly from the estimation result of the local survey. Divergent "degrees of knowledge of question items," survey methodologies, or investigators could be the causes of the various response trends.

• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.553-566
• /
• 2003

In many cases, the measurement error variances may be functions of the unknown true values or related covariates. This paper considers design-based estimators of the parameters of these variance functions based on the within-unit sample variances. This paper devotes to: (1) define an error scale factor $\delta$; (2) develop estimators of the parameters of the linear measurement error variance function of the true values under large-sample and small-error conditions; (3) use propensity methods to adjust survey weights to account for possible selection effects at the replicate level. The proposed methods are applied to medical examination data from the U.S. Third National Health and Nutrition Examination Survey (NHANES III).

• The Korean Journal of Applied Statistics
• /
• v.8 no.2
• /
• pp.43-54
• /
• 1995

The fishery household economy survey is a sample survey which produce estimates on the fishery household economy and fishery management in Korea. We propose a sample design for this survey. This design is developed based on results of 1990 fishery census and Shi-Do is assumed to be subpopulation for Shi-Do estimates. Samples are selected by stratified two-stage cluster sampling in Shi-Do and income function is found for stratification. Fishery household income is estimated by a linear estimator.