• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.589-597
• /
• 2021

In simple and multiple regression, there is a difference in the meaning of regression coefficients, and not only are the estimates of regression coefficients different, but they also have different signs. Understanding the relative contribution of explanatory variables in a regression model is an important part of regression analysis. In a standardized regression model, the regression coefficient can be interpreted as the change in the response variable with respect to the standard deviation when the explanatory variable increases by the standard deviation in a situation where the values of the explanatory variables other than the corresponding explanatory variable are fixed. However, the size of the standardized regression coefficient is not a proper measure of the relative importance of each explanatory variable. In this paper, the estimator of the regression coefficient in multiple regression is expressed as a function of the correlation coefficient and the coefficient of determination. Furthermore, it is considered in terms of the effect of an additional explanatory variable and additional increase in the coefficient of determination. We also explore the relationship between estimates of regression coefficients and correlation coefficients in various plots. These results are specifically applied when there are two explanatory variables.

• The Science & Technology
• /
• v.33 no.3 s.370
• /
• pp.76-77
• /
• 2000

한국의 우수두뇌유치 프로그램에 의해 지난해 2월부터 한국표준과학연구원에서 근무하고 있는 폴란드 과학자 리자드 브로다박사는 현재 베타방출핵종을 액체섬광계수방법으로 표준화하는 연구를 수행하고 있다. 그가 재직중인 폴란드방사성동위원소센터와 한국표준과학연구원 방사능그룹은 동시계수를 이용한 방사성 핵종의 표준화 등 비슷한 내용을 연구하고 있으므로 계측문제를 함께 풀어나가면서 훨씬 빠른 발전이 이루어질 것이라고 내다보았다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.364-372
• /
• 2016

This study examined the multi-phrased effects and outcomes of adult female learners who participated in lifelong learning activities, as well as the proposed structural relationships among the five latent variables. Questions established to achieve the purpose of the study are as follow: What effects do the learner's characteristics, lifelong education institutions, learning flow, and learning satisfaction have on the learning come? The participants of the survey numbered 632, but 54 respondents who were unreliable or did not complete their survey were excluded. A total of 578 cases were analyzed for this research. The structural relationships among the five latent variables-learner's characteristics, lifelong education institutions, learning flow and learning satisfaction, and learning outcome of the adult female learners-AMOS 18.0 program were also used for structural analysis. The major findings of this research are as follows. First, the model fitness showed that the hypothetical model provided a reasonable fit to the data ${\chi}^2=224.267$ (df=69, p<.001), RMSEA=.062, TLI=.943, RFI=.920, CFI=.957, IFI=.957, NFI=.939. Second, the learner's characteristics ( =.218, p<.001) and lifelong education institutions ( =.301, p<.001) have a direct effect on the learning outcomes. The learning flow ( =-.149 p=.541) does not have a direct effect on the learning outcome. Learning satisfaction ( =.405 p<.001) have a direct effect on the learning outcome. To put findings above together, in respect to adult female learners' performances, the learning outcomes are influenced directly by the learner characteristics, conditions of the lifelong education institutions, and learning satisfaction, whereas satisfaction indirectly affects the learners' learning outcome.

• Archives of design research
• /
• v.12 no.2
• /
• pp.121-130
• /
• 1999

The purpose of this study is to provide standardization on the examination that could measure students' diagrammatic creativity at design college. For this purpose, we tested college students, who was selected by educational system, regional, and grade groups to use the examination, and suggested the standardization criterion by analyzing these data. The data analysis procedures of this study consist of three step, the first that was to investigate the goodness of the examination paper, second step was to measure the reliability and the validity for the goodness of questions, the last step was to suggest the standardize scores for standardization on the examination. The results of the goodness and standardization analysis showed three structural factors(fluency, flexibility, originality) of this examination were proper to measure the diagrammatic creativity, and the proposed examination tool seemed to be good enough to apply in practice.

• The Korean Journal of Applied Statistics
• /
• v.28 no.3
• /
• pp.385-392
• /
• 2015

Principal component analysis (PCA), a dimension-reduction technique, is usually implemented after the variables are standardized when the measurement unit of variables are different. To standardize a variable we divide it by its standard deviation. But there is another way to transform a variable to be independent of its measurement unit. It is to divide it by its mean rather than standard deviation. Implementing PCA on standardized variables is equivalent to implementing PCA with a correlation matrix of original variables. Similarly, implementing PCA on the transformed variables divided by their means is equivalent to implementing PCA with a matrix related to the coefficients of variation of the original variables. We explain why we need to implement PCA on the variables transformed by their means.

• 대한방사선방어학회:학술대회논문집
• /
• 2011.11a
• /
• pp.316-317
• /
• 2011

• Journal of KIISE:Software and Applications
• /
• v.28 no.2
• /
• pp.141-148
• /
• 2001

DCT(Discrete Cosine Transform) 변환은 MPEG과 JPEG 표준에 의하여 영상이나 비디오 영상을 압축하는데 사용되어져 왔다. 본 연구에서는 이상적인 경계가 관련된 특성을 유도하고, 실시간 처리를 위하여 모델에 바탕을 둔 DCT 영역에서의 불연속 경계 평가 방법을 제안한다. 이 방법은 방향 검증과 위치 정렬 등의 평가로 구성된다. 두 가지의 평가 방법에 의하여 경계의 다양한 방향과위치를 알 수 있으며, DCT 계수들을 표준화된 형식으로 정렬시킬 수 있고, 표준화된 DCT 계수에서 이상적인 계단 경계의 특성과 비교하여 경계의 크기를 산출할 수 있다. DCT 계수가 8x8의 블록 단위로 이루어져 있어 경계의 표현이 조밀하지는 않지만 처리 시간이 빠르고 잡음에 강한 특성을 가지고 있어 다양한 실시간 응용분야에 사용될 수 있을 것이다.

• Broadcasting and Media Magazine
• /
• v.15 no.4
• /
• pp.77-94
• /
• 2010

2010년 1월부터 영상 부호화 표준의 양대 표준화 단체인MPEG과 VCEG에서는 JCT-VC라는 공동 협력팀을 구성하여 H.264/AVC 표준보다 2배 가량의 부호화 효율 향상을 목표로 한 HEVC 표준을 개발하고 있다. 가장 최근인 2010년10월 중국 광저우에서 개최된 3차 회의에서 부호화 기술들의 평가를 통해 HEVC 표준의 기반이 될 HM 1이 결정되었다. 본 고에서는 엔트로피 부호화 기술 중 변환 계수 주사 기술, 병렬 문맥 처리 기술, 변환 계수 부호화 기술을 위주로 HEVC 표준화에 제안되고 있는 기술 및 HM 1에 포함된 기술에 대해서 설명한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.546-548
• /
• 2015

HEVC(High Efficiency Video Coding)는 JCT-VC(Joint Collaborative Team on Video Coding)라는 ITU-T(VCEG)와 ISO-IEC(MPEG)가 공동으로 진행한 팀이 만들어낸 표준화이다. 이 표준화된 코덱에서 율-왜곡 최적화(RDO)는 실행함에 있어 높은 성능 향상을 보이지만 상대적으로 많은 부호화 시간이 요구된다. RDO 의 부호화 시간을 줄이기 위해서 이 논문에서는 변환 계수를 이용한 고속 인트라 예측 방법을 제안한다. 기존 HEVC 에서는 RMD(Rough Mode Decision)를 통해 상위 N 개의 후보를 구하고 MPM(Most Probable Mode)을 거쳐 나온 후보들의 수의 합을 가지고 RDO 를 구하게 된다. 여기서 제안하는 고속 인트라 예측 방법은 RDO 를 구하기 전에 나왔던 N 개의 후보에서 이산 여현 변환(DCT) 계수를 이용하여 예측 모드의 수를 한 번 더 줄임으로써 RDO 수행시간을 줄이는 방법이다. 이 방법은 기존 HEVC 부호화 방법보다 적은 손실에도 불구하고 높은 속도 향상을 보인다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2259-2264
• /
• 2008

Significant genes are defined as genes in which the expression level characterizes a specific experimental condition. Such genes in which the expression levels differ significantly between different groups are highly informative relevant to the studied phenomenon. In this paper, first the system can detect informative genes by similarity scale combination method being proposed in this paper after normalizing data with methods that are the most widely used among several normalization methods proposed the while. And it compare and analyze a performance of each of normalization methods with multi-perceptron neural network layer. The Result classifying in Multi-Perceptron neural network classifier for selected 200 genes using combination of PC(Pearson correlation coefficient) and ED(Euclidean distance coefficient) after Lowess normalization represented the improved classification performance of 98.84%.