• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.345-355
• /
• 2001

동일한 유효성분을 가지면서 용량 혹은 형식 만이 다른 제제의 개발이 증가되고 이에 따른 두 제제 이상의 생물학적 동등성시험의 필요성이 제기되었다. 이에 이용주 등(1998)은 온단세트론 제제에 대한 생물학적 동등시험에서 3$\times$3 교차설계법을 적용하였다. 그러나 3$\times$3 교차설계법에서 각 순서에 피험자의 수가 다르거나 실험중에 결락(dropout)되는 피험자가 발생하는 경우에는 일반적인 통계적 방법은 적용할 수 없었다. 본 연구에서는 이러한 경우에 제제효과의 추론에 대한 통계적 방법과 생물학적 동등성 시험 방법을 제안하고 모의실험을 통하여 생물학적 동등성평가의 정도를 측정하였다.

• The Korean Journal of Applied Statistics
• /
• v.10 no.1
• /
• pp.151-161
• /
• 1997

An easy Monte Carlo Gibbs sampling approach is suggested for Bayesian analysis of cumulative logit models for ordinal polytomous data. Because in the cumulative logit model the posterior conditional distributions of parameters are not given in convenient forms for random sample generation, appropriate latent variables are introduced into the model so that in the new model all the conditional distributions are given in very convenient forms for implementation of the Gibbs sampler.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.263-266
• /
• 2007

This paper discusses the Bayesian statistical inference. This paper discusses the Bayesian inference, MCMC (Markov Chain Monte Carlo) integration, MCMC method, Metropolis-Hastings algorithm, Gibbs sampling, Maximum likelihood estimation, Expectation Maximization algorithm, missing data processing, and BMA (Bayesian Model Averaging). The Bayesian statistical inference is used to process a large amount of data in the areas of biology, medicine, bioengineering, science and engineering, and general data analysis and processing, and provides the important method to draw the optimal inference result. Lastly, this paper discusses the method of principal component analysis. The PCA method is also used for data analysis and inference.

• The Korean Journal of Applied Statistics
• /
• v.21 no.6
• /
• pp.1015-1026
• /
• 2008

In this paper, we are interested in tennis games and the best of all matches that is fair to most of all participants. We introduce a loss function. And using our introduced loss function and round robin method, we get a best match that obtains the minimal loss according to the number of participants.

• The Korean Journal of Applied Statistics
• /
• v.6 no.2
• /
• pp.227-235
• /
• 1993

Calibration relates the estimation of independent variable which rquires more effort or expense than dependent variable does. It would be provided with high accuracy because a little change of the result of independent variable cn cause a serious effect to the human being. Usual statistical analysis assumes the normality of error distribution or linearity of data. It is desirable to analyze the data without those assumptions for the accuracy of the calibration. In this paper, we calibrated the data nonparametrically without those assumptions and derived confidence interval estimate for the independent variable. As a method, we used kernel method which is popular in modern statistical branch. We derived bootstrap confidence interval estimate from the bootstrap confidence band.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.27 no.4
• /
• pp.343-358
• /
• 2011

As implant treatment has become popular, lots of different shapes and materials of the implant upper component have been supplied. And there are also diverse reports about failures including loosening of the abutment screw which is one of the most common reason. Purpose : The purpose of this study is to find out how different screw tightening orders and methods influence on screw loosening according to the different connection systems. The upper component was fabricated by casting method. After fabricating master models that are precisely attached to the upper component, 5 experimental models each for the external connection system and internal connection system were fabricated using splinting impression technique. First, to find out the influence of the screw tightening order, screws were tightened in 3 orders; 1-2-3-4, 2-3-1-4, 2-4-3-1. After tightening, removal torque values (RTV) of each group was measured. And also to find out the influence of screw tightening method, a model with 2-3-1-4 screw tightening order was tightened with 30 Ncm at one time(1-step method) and the RTV was compared with the same order group (2-3-1-4) in the 2 step method. In the external connection system, RTV appeared significantly lower in group 2-3-1-4 than group 2-4-3-1 (p<0.05). And also in the internal connection system, the RTV of group 2-3-1-4 appeared significantly lower than that of group 2-4-3-1 and 1-2-3-4 (p<0.05). When comparing the tightening number of the screw without considering the screw tightening order, the first tightened screw appeared significantly higher RTV than the second one in the external connection system (p<0.05), however there was no significant difference from the first tightened screw to the last tightened screw in the internal connection system. And there was no statistically significant difference between the two screw tightening methods in both internal and external connection system. In the comparison of external and internal connection system, each RTV appeared 16.27 Ncm and 14.25 Ncm and appeared as a statistically significant difference (p<0.05). There was a significant difference in RTV measured according to the screw tightening order. The lowest RTV appeared in the groups started tightening from the middle. There was also a significant difference in RTV between the two connection system groups. A further study is needed to find out the influence factors in RTV and also a study is required related to the load condition.

• School Mathematics
• /
• v.9 no.2
• /
• pp.223-240
• /
• 2007

The purpose of this study was to investigate the degree to which the middle school mathematics curriculum matched the item difficulty levels of representative mathematics items. The items used in this study were developed for the National Assessment of Educational Achievement. Ranks for difficulty values of the 60 multiple-choice item were calculated via both Classical Test Theory and Item Response Theory and correlated with the rank order of the mathematics content and cognitive domains sequence. There are six content domains; number and operation, algebra, measurement, figure, pattern and function, and probability and statistics. The cognitive domains include computation, understanding, reasoning and problem-solving. Results suggest a congruence between cognitive domain's sequence and item difficulty levels of items based on that sequence. This finding indicates that the linear or hierarchical assumptions concerning the sequence appears to be reasonable. The characteristics of items that were exceptions to this trend were addressed.

• 한국노년학
• /
• v.40 no.3
• /
• pp.389-411
• /
• 2020

The purpose of this study was to identify the needs and characteristics of Korean senior consumers. To this end, the factors of Maslow's seven-levels of needs hierarchy were re-established and applied to suit the actual situation in Korea. For analysis, an online survey was conducted on 440 adults (50-75 years old), who are considered active seniors living in Korea, on the factors of 7-levels of needs and demographic characteristics. The study found that the 7-levels needs of Korean senior consumers were derived in a different order from Maslow's. Other diverse theoretical and practical implications were also presented.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.41-50
• /
• 2009

Chain-linking is a method for aggregating volume measures which would improve the quality of estimates of economic growth over the present fixed base in Korea. There is a risk that choice of chain-linking techniques such annual overlap, one-quarter overlap or over-the-year overlap may create an artificial seasonality to the volume series. The empirical results on Korean GDP suggest that the use of the annual overlap is recommended. And conducting seasonal adjustment after chain-linking to produce the chain-linked seasonally adjusted GDP is more appropriated in Korea.

• Journal of Korea Multimedia Society
• /
• v.12 no.9
• /
• pp.1210-1216
• /
• 2009

In this paper we analyze the convergence behavior of the recursive least rank (RLR) L-filter. The RLR L-filter is an order statistics filter, filter coefficients of which are the weights according to the order of magnitude of inputs. And RLR L-filter is a non-linear adaptive filter, that uses RLR algorithm for coefficient updating. The RLR algorithm is a non-linear adaptive algorithm based on rank estimates in Robust statistics. The mean and mean-squared convergence behavior of the RLR L-filter is examined with variable step-sizes. The RLR L-filter adapts the median filter type to the heavy-tailed distribution function of impulse noise, and adapts the average filter type to Gaussian noises.