• Journal of applied mathematics & informatics
• /
• v.4 no.2
• /
• pp.501-512
• /
• 1997

In multiple linear regression model we have presupposed assumptions (independence normality variance homogeneity and so on) on error term. When case weights are given because of variance heterogeneity we can estimate efficiently regression parameter using weighted least squares estimator. Unfortunately this estimator is sen-sitive to outliers like ordinary least squares estimator. Thus in this paper we proposed some statistics for detection of outliers in weighted least squares regression.

• Journal of applied mathematics & informatics
• /
• v.13 no.1_2
• /
• pp.501-508
• /
• 2003

Although the estimate of regression function is important, some have focused the variance estimation of error term in regression model. Different variance estimators perform well under different conditions. In many practical situations, it is rather hard to assess which conditions are approximately satisfied so as to identify the best variance estimator for the given data. In this article, we suggest SHM estimator compared to LS estimator, which is common estimator using in parametric multiple regression analysis. Moreover, a combined estimator of variance, VEM, is suggested. In the simulation study it is shown that VEM performs well in practice.

• Journal of applied mathematics & informatics
• /
• v.8 no.3
• /
• pp.881-888
• /
• 2001

Recently, Hooda and Ram [7] have proposed and characterized a new generalized measure of R-norm entropy. In the present communication we have studied its application in coding theory. Various mean codeword lengths and their bounds have been defined and a coding theorem on lower and upper bounds of a generalized mean codeword length in term of the generalized R-norm entropy has been proved.

• Journal of applied mathematics & informatics
• /
• v.19 no.1_2
• /
• pp.427-438
• /
• 2005

From a notion of d-pseudo-orthogonality for a sequence of poly-nomials ($d\;\in\;{2,3,\cdots}$), this paper introduces three different characterizations of natural exponential families (NEF's) with polynomial variance functions of exact degree 2d-1. These results provide extended versions of the Meixner (1934), Shanbhag (1972, 1979) and Feinsilver (1986) characterization results of quadratic NEF's based on classical orthogonal polynomials. Some news sets of polynomials with (2d-1)-term recurrence relation are then pointed out and we completely illustrate the cases associated to the families of positive stable distributions.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.05a
• /
• pp.179-184
• /
• 2005

Empirical findings on interet rate dynamics imply that short rates show some long memories and non-Markovin. It is well-known that fractional Brownian motion(fBm) is a proper candidate for modelling this empirical phenomena. fBm, however, is not a semimartingale process. For this reason, it is very hard to apply such processes for asset price modelling. With some modifications, this paper investigate the fBm interest rate theory, and obtain a pure discount bond price and Greeks.

• Communications for Statistical Applications and Methods
• /
• v.11 no.3
• /
• pp.495-501
• /
• 2004

HJM representation of the term structure of interest rates sometimes produces the negative interest rates with positive probability. This paper shows that the condition of positive interest rates can be derived from the jump diffusion process, if a proper positive martingale process with the compensated jump process is chosen. As in Flesaker and Hughston, the condition is incorporated into the bond price process.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.2
• /
• pp.685-693
• /
• 2012

The purpose of this study was to develop a dysphagia assessment tool and a intervention program for elderly in the long-term care facilities and to evaluate its effect. The dysphagia assessment tool consists of 20 items was developed through literature review, previous studies and discussion with nursing/medical members. The intervention program consisted of 72 items and participants for evaluation were 50 elders who were registered at long-term care facilities in 4 regions of Seoul. Collected data were analyzed using SPSS Statistics 18.0 and Spearman's Correlation, t-test, and $x^2$-test. After the application of the dysphagia assessment tool and intervention program, the weight in experimental group was increased (t=4.913, p=.000) and the total time of swallowing was reduced (t=-4.557, p=.000) than control group. These findings were statistically significant. Considering these results, by applying the dysphagia assessment tool and the intervention program, the lives of the elderly in long-term care facilities are expected to be improved and emergency situations such as aspiration pneumonia and asphyxia will be decreased.

• The Research Journal of the Costume Culture
• /
• v.11 no.1
• /
• pp.88-102
• /
• 2003

In our culture, the term, "be like", is frequently used. There are expressions such as "feminine-looking dress" and "manly style" relating to this term when we describe the styles of clothing. This study addresses the question on which type of garment would be selected under the description of the term, "be-like", in relation to gender. This term reveals the preconception of gender as being feminine or masculine according to the styles and colors of clothes. A group of 362 college students from Seoul and Gyeonggi area was surveyed fur the study The statistical analysis of SPSS 10.0 was applied f3r analyzing the data, and the significant variances were reviewed by the basic statistics, multi-variate and T-test. The results are as follows: First, the details of clothes imply the preconceived idea of gender. As a result, women's blouses and skirts were selected as the most feminine upper and bottom garments. The Y-shirt and T-shirt were selected as the most masculine upper garments. However, in contrast to the . skirts being the most feminine bottom wear, the pants were not significantly recognized as the most masculine ,clothes. Second, the variances of the survey show that the female students are more conscious of the sexual identity expressed in clothes than the male students. Third, the styles of clothes reflect the general understanding of what is considered to be "feminine or not feminine" and "masculine or not masculine" In conclusion, this study has discovered that the certain characteristics of gender are predominantly implicated in the styles length, and color of clothes. Both men and women responded differently in defining their idea of "femininity" and "masculinity". Nevertheless, there still exists strong preconception of what is considered to be feminine or masculine, and it affects the choices people make in selecting clothes.

• Journal of Home Health Care Nursing
• /
• v.27 no.1
• /
• pp.16-28
• /
• 2020

Purpose: The aim of this study was to evaluate the efficiency of long-term care visiting nursing centers in communities using data envelopment analysis (DEA). Methods: Data were collected using a self-reported questionnaire. The average number of staff per 6 months and total space of center were used as input variables. The average number of clients per 6 months and the average profits per 6 months were used as output variables. EMS Window version 3.1 was used to measure the efficiency scores. Descriptive statistics and tobit regression were applied to analyze the general characteristics of the variables and the factors affecting efficiency scores. Results: The average efficiency of 30 long-term care visiting nursing centers in communities was approximately 66.9% on technical efficiency analysis, and 79.1% on scale efficiency analysis. Eight nursing centers on technical efficiency analysis and 12 centers on scale efficiency analysis had 100.0% efficiency. Conclusion: Our findings reveal that long-term care visiting nursing centers in communities have low operational efficiency. Therefore, it is essential to institute policies and regulations to improve the efficiency of visiting nursing centers and to strengthen the business competencies of center officers.

• Journal of the Korean Society of Safety
• /
• v.27 no.5
• /
• pp.219-223
• /
• 2012

For an off-site consequence analysis at nuclear power plant, MELCOR Accident Consequence Code System(MACCS) II code is widely used as a software tool. In this study, the algorithm of web-based off-site consequence analysis program(OSCAP) using the MACCS II code was developed for an Integrated Leak Rate Test (ILRT) interval extension and Level 3 probabilistic safety assessment(PSA), and verification and validation(V&V) of the program was performed. The main input data for the MACCS II code are meteorological, population distribution and source term information. However, it requires lots of time and efforts to generate the main input data for an off-site consequence analysis using the MACCS II code. For example, the meteorological data are collected from each nuclear power site in real time, but the formats of the raw data collected are different from each site. To reduce the efforts and time for risk assessments, the web-based OSCAP has an automatic processing module which converts the format of the raw data collected from each site to the input data format of the MACCS II code. The program also provides an automatic function of converting the latest population data from Statistics Korea, the National Statistical Office, to the population distribution input data format of the MACCS II code. For the source term data, the program includes the release fraction of each source term category resulting from modular accident analysis program(MAAP) code analysis and the core inventory data from ORIGEN. These analysis results of each plant in Korea are stored in a database module of the web-based OSCAP, so the user can select the defaulted source term data of each plant without handling source term input data.