• Journal of the Korean Data and Information Science Society
• /
• v.17 no.4
• /
• pp.1151-1160
• /
• 2006

The similarity weight, the pearson's correlation coefficient, which is used in the recommender system has a weak point that it cannot predict all of the prediction value. The similarity weight, the vector similarity, has a weak point of the high MAE although the prediction coverage using the vector similarity is higher than that using the pearson's correlation coefficient. The purpose of this study is to suggest how to raise the prediction coverage. Also, the MAE using the suggested method in this study was compared both with the MAE using the pearson's correlation coefficient and with the MAE using the vector similarity, so was the prediction coverage. As a result, it was found that the low of the MAE in the case of using the suggested method was higher than that using the pearson's correlation coefficient. However, it was also shown that it was lower than that using the vector similarity. In terms of the prediction coverage, when the suggested method was compared with two similarity weights as I mentioned above, it was found that its prediction coverage was higher than that pearson's correlation coefficient as well as vector similarity.

• Journal of Nutrition and Health
• /
• v.22 no.1
• /
• pp.23-31
• /
• 1989

The purpose of this study was to evaluate the validity of various dietary methods. Dietary intake of 24 patients on regular diet was investigated by three methods. One method was a precise weighing method, the others were 24-hour dietary recall method and convenient dietary questionnaries. The results obtained are summarized as followes ; 1) There were no significant differences in mean nutrient intake of subjects among three dietary survey methods. 2) The validity coefficient between the precise weighing method and 24-hour recall method, ranging from 0.26(fat) to 0.59(carbohydrate) showed significant correlation for carbohydrate, vitamin A, thiamin, riboflavin and ascorbic and intakes. 3) The validity coefficient between precise weighting method and covenient dietary questionnaires, ranging from 0.14(fat) to 0.80(vitamin A), showed a significant correlation for most nutrients. 4) Female showed higher correlation between the precise weighing method and 24-hour recall method than male subjects for most nutrients. However, there was no significant sexual difference of correlation between weighing method and convenient method. 5) The correlation coefficient between the precise weighing method and the other two methods by age group showed younger sujbects have a higher significant correlation than older subjects for most nutrients.

• Communications for Statistical Applications and Methods
• /
• v.14 no.2
• /
• pp.301-307
• /
• 2007

A effective teaching method on correlation coefficient for elementary level statistics course is discussed in this article. The well known inequalities, such as Theorem 368 of Hardy et al. (1952), are used for the interpretation of concept of covariance. An Excel example is provided for the illustration of concept of correlation coefficient.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.6
• /
• pp.1649-1667
• /
• 2012

In order to improve the accuracy and universality of the flow metric correlation analysis, this paper firstly analyzes the characteristics of Internet flow metrics as random variables, points out the disadvantages of Pearson Correlation Coefficient which is used to measure the correlation between two flow metrics by current researches. Then a method based on Symmetrical Uncertainty is proposed to measure the correlation between two flow metrics, and is extended to measure the correlation among multi-variables. Meanwhile, the simulation and polynomial fitting method are used to reveal the threshold value between different correlation degrees for SU method. The statistical analysis results on the common flow metrics using several traces show that Symmetrical Uncertainty can not only represent the correct aspects of Pearson Correlation Coefficient, but also make up for its shortcomings, thus achieve the purpose of measuring flow metric correlation quantitatively and accurately. On the other hand, reveal the actual relationship among fourteen common flow metrics.

• 한국데이터정보과학회:학술대회논문집
• /
• 2006.11a
• /
• pp.119-128
• /
• 2006

The similarity weight, the pearson's correlation coefficient, which is used in the recommender system has a weak point that it cannot predict all of the prediction value. The similarity weight, the vector similarity, has a weak point of the high MAE although the prediction coverage using the vector similarity is higher than that using the pearson's correlation coefficient. The purpose of this study is to suggest how to raise the prediction coverage. Also, the MAE using the suggested method in this study was compared both with the MAE using the pearson's correlation coefficient and with the MAE using the vector similarity, so was the prediction coverage. As a result, it was found that the low of the MAE in the case of using the suggested method was higher than that using the pearson's correlation coefficient. However, it was also shown that it was lower than that using the vector similarity In terms of the prediction coverage, when the suggested method was compared with two similarity weights as I mentioned above, it was found that its prediction coverage was higher than that pearson's correlation coefficient as well as vector similarity.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.32 no.5
• /
• pp.374-381
• /
• 2008

The correlation coefficient method, which was proposed by our research group, is applied to digital particle holography to locate the focal plane of particles. It uses the fact that the correlation coefficient is maximum at the focal plane. The factors influencing this method are discussed with a numerical simulation of holograms. For real holograms, the Wiener filter was proposed to process both recorded holograms and reconstructed images. The application results using the dot array target showed that the Wiener filter is a very effective tool for processing holography-related images. The effects of the dot size and the object distance on the errors in the determination of the focal plane by the correlation coefficient method were investigated by using the calibration target.

• IE interfaces
• /
• v.14 no.1
• /
• pp.79-83
• /
• 2001

In this paper, we propose a simple method to reduce categorical variables into smaller, but significant numbers, and also demonstrate how the proposed method can be applied to the problem of reduction that empirical research often faces in the course of data processing. For the purpose, we introduce a concept of pseudo-correlation coefficient to make it possible to use factor analysis (FA) as a tool for reducing variables. The main idea of the concept is to deal with the measures of association of categorical variables in the sense of the concept of Pearson's correlation coefficient in order to meet the input requirement of FA. Upon examination of existing measures that could play as pseudo-correlation coefficients, Cramer's V coefficient is selected for the best result among them. To show the detailed procedure of the proposed method, a specific demonstration with the data from 329 R&D projects conducted in 18 private laboratories in electric and electronics industry is presented.

• Analytical Science and Technology
• /
• v.33 no.3
• /
• pp.143-150
• /
• 2020

In this study, crude protein was analyzed and compared using the Kjeldahl and Dumas method for cereals, meat, sea food, chemical samples and vegetable. The nine kinds of cereal, including white rice, were analyzed. In the result, the correlation coefficient of the Kjeldahl and the Dumas method indicated that there was no significant difference between them, showing 0.994 of it and 0.956 of p-value. Also, for the nine kinds of meat, five kinds of sea food, three kinds of chemical samples, four kinds of vegetable, there was little difference about the correlation coefficient of the Kjeldahl and the Dumas method, showing 0.9725, 0.9879, 0.9985 and 0.9873 of it and 0.947, 0.761, 0.997 and 0.727 of p-value, respectively. For the samples of meat, they were not fully homogenized, so the reproducibility of them was not good in the Dumas method, which is required to be analyzed in small size. However, when vegetables, which contain a lot of nitrates, are analyzed using Kjeldahl, they showed the lower reproducibility compared to the result of using Dumas because they are not completely decomposed in the Kjeldahl method. In the Dumas method, the samples should be homogenized because only 0.1 g sample is used. In short, neither of the Kjeldahl and Dumas methods are an accurate quantitative test because both of them do not directly analyze pure protein but measure the amount of protein based on analysis of nitrogen. Therefore, it is important of selecting the appropriate analysis method considering the characteristics of samples.

• Journal of applied mathematics & informatics
• /
• v.19 no.1_2
• /
• pp.521-525
• /
• 2005

Case deletion diagnostic for multiple correlation coefficient is considered. A method of detecting observations that can hide or create multicollinearity is suggested. A numerical example is given for illustration.

• Journal of Korea Water Resources Association
• /
• v.38 no.10 s.159
• /
• pp.851-859
• /
• 2005

Normalized cross-correlation (correlation coefficient) is a useful measure for pattern matching in PIV (Particle Image Velocimetry) analysis. Because it does not have a corresponding simple expression in frequency domain, several fast but inexact measures have been used. Among them, three measures of correlation for PIV analysis and the normalized cross-correlation were evaluated with a sample calculation. The test revealed that all other proposed correlation measures sometimes show inaccurate results, except the normalized cross-correlation. However, correlation coefficient method has a weakpoint that it requires so long time for calculation. To overcome this shortcoming, a fast and exact method for calculating normalized cross-correlation is suggested. It adopts Fast Fourier Transform (FFT) for calculation of covariance and the successive-summing method for the denominator of correlation coefficient. The new algorithm showed that it is really fast and exact in calculating correlation coefficient.