• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.9 no.1
• /
• pp.13-19
• /
• 2004

We compared two different zooplankton data sets simultaneously obtained at the same place with different mesh-sized nets. Smaller mesh-sized net yielded less diverse zooplankton taxa. However, it was difficult to generalize the relationship between the size of the mesh of the net used and the length of the species list observed. It was not only because the sample sizes obtained by smaller mesh net were relatively smaller due to the clogging problem but also because smaller mesh net usually collected more tiny animals that were difficult to identify at lower taxonomic categories. In terms of abundances, on the other hand, the smaller and the larger mesh-sized nets collected smaller and larger-sized animals more effectively, respectively. The abundances of small sized animals were usually greater than those of large-sized animals by about an order of differences. Due to this different catchability of the nets, the community analyses based on Principal Component Analysis led to different results for the same community.

• Journal of Korea Trade
• /
• v.26 no.5
• /
• pp.39-55
• /
• 2022

Purpose - This study empirically examines the effect of the Korean government export promotion program (EPP) on small and medium-sized enterprise (SMEs) export performance using firm-level data. Unlike most previous studies that investigated some specific samples of firms, this study analyzes a vast amount of SME data of the Korean Small and Medium Business Administration over the period 2005 to 2008. Design/methodology - An endogeneity problem arises when a firm's probability of being selected is correlated with the likelihood of successfully implementing EPPs. To control for the endogeneity of the EPPs in a relatively short-period sample, we employ 2-Stage Residual Inclusion (2SRI) RE-Tobit and bivariate Tobit procedure. Findings - Analyses show that Korean government EPPs have positive significant effects on SME exports. Empirical results also show that SME export activities are significantly encouraged by R&D investment and capital intensity, but not obviously by labor productivity. Originality/value - This study provides evidence that SME capital intensity, R&D investment, and the number of workers are significant determinants to SME exporting activities, whereas per worker labor cost and employee education are not. These results imply that even for SMEs, firm size is a major factor in promoting exporting activities.

• Korea Journal of Hospital Management
• /
• v.7 no.4
• /
• pp.102-122
• /
• 2002

It has been 2 years since the implementation of the separation policy of drug prescription and dispensing. This study analyzes the changes in community pharmacy operation after the implementation of the policy. The main purposes of the analysis are to determine whether the changes in community pharmacy operation have occurred and to evaluate that the changes are consistent with the intention of the policy, if the changes actually have occurred. For the study a survey on 961 pharmacies chosen by stratified sampling method has been performed. Of the 961 sample pharmacies, 438 pharmacies were responded resulting 45.6% response rate. The sample pharmacies are classified by the location that the pharmacy are operating: the pharmacies around large size hospitals, the pharmacies around clinics or medium to small size hospitals and the pharmacies with no hospitals or clinics around. Based on the classification, the number of pharmacies, number of prescriptions processed, the personnel structure, the changes in facility, and other operational characteristics are compared. The results showed that the pharmacies were tended to concentrate around hospitals and clinic since the implementation of the policy. The number of pharmacists per pharmacy was increased, the size of pharmacy was increased and the facilities were improved to accomodate the requirements of the policy. The work hours a pharmacist spent on dispensing drug have increased almost twice, however, there was no corresponding increase in the time spent on patient education and medication history management, indicating a problem in the provision of quality pharmaceutical services. Based on the results, suggestions to minimize the negative effects of the policy are provided.

• Journal of Korean Society of Forest Science
• /
• v.4 no.1
• /
• pp.24-25
• /
• 1965

A statistical study was made on the size of sample plot to be used in the preparation of a yield table. This has always been an important problem needing solution in Korea. For this purpose, 3 replications of Korean white pine plantings with block size of $80m{\times}80m$ were established in the Kwangneung Experimental Forest. A location map was prepared of the pines in the blocks and the heights and the breast height diameters measured. Then those blocks were divided into 64, 64, 16, 16, 4, 4, and 1 standed $40m{\times}80m$ and $80m{\times}80m$ each. After these divisions, the average heights, average breast height diameters, standard deviations and coefficient of variations were computed for the plots and averaged according to plot size. As the results of these computations, it was shown that the standard deviation and the coefficient of variation suddenly increased with the beginning of an increase in plot size. However, these indicated an approximately constant value at a certain limit. Although the average value decreases with the initial increase in plot size, it also indicates an approximately constant value at a certain limit. This limit was between $20m{\times}40m$ and $40m{\times}40m$. With the purpose of evaluating these facts, the average height and the average diameter were computed for the number of standing trees in the $10m{\times}10m$ plots. A negative (minus) relationship was found between the number of standing trees and the average value. As a result of above evaluation, it was found that when the size of plot area was small, a larger estimated value, was obtained as well as a smaller standard deviation and coefficient of variation. It is possible, therefore, that an incorrect value might be used in the evalution of data as the stand structure could appear to be uniform when the plot size was small. In general, when the size of plot area is larger than $40m{\times}40m$, the probability of the difficulty occurring mentioned above is estimated to be small.

• Communications for Statistical Applications and Methods
• /
• v.15 no.5
• /
• pp.709-717
• /
• 2008

The difference of two one-sided kernel estimators is usually used to detect the location of the discontinuity points of regression function. The large absolute value of the statistic imply discontinuity of regression function, so we may use the difference of two one-sided kernel estimators as the test statistic for testing null hypothesis of a smooth regression function. The problem is, however, we only know the asymptotic distribution of the test statistic under $H_0$ and we hardly expect the good performance of test if we rely solely on the asymptotic distribution for determining the critical points. In this paper, we show that if we adjust the bias of test statistic properly, the asymptotic rules hold for even small sample size situation.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.69-72
• /
• 2003

The paper considers partial least squares (PLS) as a new dimension reduction technique for the feature vector to overcome the small sample size problem in face recognition. Principal component analysis (PCA), a conventional dimension reduction method, selects the components with maximum variability, irrespective of the class information. So PCA does not necessarily extract features that are important for the discrimination of classes. PLS, on the other hand, constructs the components so that the correlation between the class variable and themselves is maximized. Therefore PLS components are more predictive than PCA components in classification. The experimental results on Manchester and ORL databases show that PLS is to be preferred over PCA when classification is the goal and dimension reduction is needed.

• Communications for Statistical Applications and Methods
• /
• v.25 no.5
• /
• pp.559-568
• /
• 2018

Gene classification can involve complex order-restricted inference. Examining gene expression pattern across groups with order-restriction makes standard statistical inference ineffective and thus, requires different methods. For this problem, Roy's union-intersection principle has some merit. The M-estimator adjusting for outlier arrays in a microarray study produces a robust test statistic with distribution-insensitive clustering of genes. The M-estimator in conjunction with a union-intersection principle provides a nonstandard robust procedure. By exact permutation distribution theory, a conditionally distribution-free test based on the proposed test statistic generates corresponding p-values in a small sample size setup. We apply a false discovery rate (FDR) as a multiple testing procedure to p-values in simulated data and real microarray data. FDR procedure for proposed test statistics controls the FDR at all levels of ${\alpha}$ and ${\pi}_0$ (the proportion of true null); however, the FDR procedure for test statistics based upon normal theory (ANOVA) fails to control FDR.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2709-2729
• /
• 2016

Representation based classification, kernel method and sparse representation have received much attention in the field of face recognition. In this paper, we proposed an improved kernel principal component analysis method based on sparse representation to improve the accuracy and robustness for face recognition. First, the distances between the test sample and all training samples in kernel space are estimated based on collaborative representation. Second, S training samples with the smallest distances are selected, and Kernel Principal Component Analysis (KPCA) is used to extract the features that are exploited for classification. The proposed method implements the sparse representation under ℓ₂ regularization and performs feature extraction twice to improve the robustness. Also, we investigate the relationship between the accuracy and the sparseness coefficient, the relationship between the accuracy and the dimensionality respectively. The comparative experiments are conducted on the ORL, the GT and the UMIST face database. The experimental results show that the proposed method is more effective and robust than several state-of-the-art methods including Sparse Representation based Classification (SRC), Collaborative Representation based Classification (CRC), KCRC and Two Phase Test samples Sparse Representation (TPTSR).

• Korean Business Review
• /
• v.17 no.2
• /
• pp.63-87
• /
• 2004

To create and maintain comparative supremacy as a strategic tool of business, many organizations have introduced informational technology and system. By using this system, Some companies got a beneficial value for achieving organizational goals but others could not obtain their effectiveness and efficiency. In particular, a lot of organizations that tried to make strategic supremacy with e-commercial trade are under hard condition because of poor profit. It implies that it is essential to identify and analyse the consumer who uses e-commercial trade. This paper, therefore, focusing on internet shopping malls between business and consumer as one of areas of e-commercial trades, shows the difference between consumer expectation and performance. The results of this study are as follows: First, as for the significant difference of influencing factors to consumer satisfactions according to the types of internet shopping malls, there is a meaningful difference in consumer anxiety and internet usefulness, but not in consumer service. Prior to verify the differences in detail on consumer's anxiety and internet usefulness, we examined that there is any difference between expectation and performance. T-test was used for the variants of consumer anxiety and internet usefulness, and its meaningful probability was 0.000, which means that both showed statistically significant difference. Based on the results, we also found that regardless of the types of internet shopping malls, consumer expectation was greater than performance. although the difference between expectation and performance was not equal according to the internet shopping malls. Second, a regression analysis was performed to understand the relation between consumer service, internet usefulness, consumer anxiety, and consumer satisfaction, it was found that consumer service, internet usefulness, consumer anxiety had significantly effected on consumer satisfaction. Third, To verify the relation between consumer satisfaction and repurchase-intentions, intentions to spread out, Pearson correlation analysis was used. it was found that consumer satisfaction had positive effect on both intentions. This study has some limitations because of the shorts of money and time. since the sample of this study was consumers who have ever bought one or more products via internet shopping mall, this sample was appropriate. but the major parts of sample were college students, and the sample size was so small. therefore this results should carefully be generalized. For further study, it is required to select more precise samples and to include more variables.

• Korean Journal of Occupational Health Nursing
• /
• v.12 no.1
• /
• pp.19-30
• /
• 2003

Increasing occupational cerebrovascular & cardiovascular disease, it becomes the most serious problem in the occupational health management. Hypertension is the most important risk factor of cerebrovascular & cardiovascular disease. Although treatment for hypertension has the priority, hypertension has not been managed systematically at the worksite. The objectives of this study were to investigate the actual situation of its treatment, figure out what factors can affect compliance for hypertension treatment and analyze the relations between compliance and employment status. Subjects were 28 workers who have been diagnosed as hypertension at periodic health examination, 20 workers who have been managed for hypertension at dispensary and 22 workers who were diagnosed during the study periods. The results of the study were as follows; 1. More women have been hired as part time workers and had lower education background and income than the full time workers. 2. Among the factors that have been known to affect the treatment compliance, part time workers had less supports from the company than full time workers. 3. We got the comparison of difference between compliance and variables that the factor grade of cure promotion and average ages are high in high compliance. In conclusion there were not the difference of compliance by employment status. But it was hard to rule out the selection vias because the sample size was so small. So it seems difficult to generalized the conclusion that employment status doesn't affect the treatment compliance.