• Communications for Statistical Applications and Methods
• /
• v.2 no.2
• /
• pp.296-302
• /
• 1995

When heteroscedasticity occurs in random effects linear model, the error variance may depend on the values of one or more of the explanatory variables or on other relevant quantities such as time or spatial ordering. In this paper we derive a score test as a diagnostic tool for detecting non-constant error variance in random effefts linear model based on the model expansion on error variance. This score test is compared to loglikelihood ratio test.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.19 no.4
• /
• pp.463-473
• /
• 2012

Purpose: The main purpose of this study was to identify factors affecting medication adherence and to develop an explanatory model for medication adherence in elders with chronic disease. Method: Empirical data were collected from 312 older adults with chronic disease and the data collect period was from August 8 to 31, 2011, and were analyzed using SPSS for Windows 19.0 program and confirmatory factor analysis with the structural equation model (SEM) procedure performed with AMOS 19.0 program. Results: Results of this study showed that perceived self-efficacy was the strongest factor influencing medication adherence, and it affected also outcome expectations positively but impediments were negatively influenced by self-efficacy. Outcome expectations and impediments subsequently acted on medication adherence with the same relationship as self-efficacy. In additional results, self-efficacy and medication adherence were further significantly affected by the factors; social support, medication knowledge, and depression. Conclusion: These results show that nursing interventions to promote medication adherence in this population should focus on self-efficacy promotion including social support, education for delivery of medication knowledge, and reduction in depression.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.17 no.1
• /
• pp.45-54
• /
• 2010

Purpose: The purpose of this study was to develop and test an explanatory model of dyspnea in patients with chronic lung disease (CLD). Methods: Participants were 181 patients with CLD, recruited from the outpatient pulmonary clinic of one university hospital in Korea. Data were collected using questionnaires, as well as measurement of 6-minute walking distance (6MWD), oxygen saturation ($SpO_2$), FEV1% predicted, and Body Mass Index (BMI). Results: The results indicated a good fit between the proposed dyspnea model and the collected data [$x^2$=91.27, p= .13, $x^2$/d.f.=1.17, Normal Fit Index= .934]. Oxygenation ($SpO_2$, = -.530), self-efficacy (= -.429), anxiety (= .253), depression (= .224), exercise endurance (6MWD, = -.211), and pulmonary function (FEV1% predicted, = -.178) had a direct effect on dyspnea (all p< .05) and these variables explained 74% of variance in dyspnea. BMI, smoking history, and social support had an indirect effect on dyspnea. Conclusion: The findings of this study suggest that comprehensive nursing interventions should focus on recovery of respiratory health and improvement of emotions, exercise ability, and nutritional status. From this perspective, pulmonary rehabilitation would be an effective strategy for managing dyspnea in patients with CLD.

• Korean Journal of Adult Nursing
• /
• v.20 no.4
• /
• pp.652-663
• /
• 2008

Purpose: This study was conducted to develop and test an explanatory model on functional capacity in patients with chronic obstructive pulmonary disease using path analysis. Methods: Data were collected from 149 chronic obstructive pulmonary disease patients using 6-minute walk test, measurement of oxygen saturation, pulmonary function test, and self-reported questionnaires from June to October, 2005. The collected data were analyzed using SPSS/WIN 12.0 program and AMOS/WIN 4.0 program. Results: The overall fitness indices of modified model were good($x^2$ = 14.324, p = .281 GFI = .981, RMSEA = .006, AGFI = .944, NFI = .927, NNFI = .999, CFI = .999, PNFI = .613, $x^2$/df = 1.194). Functional capacity was influenced directly by age(${\beta}$ = -.304, p = .000), dyspnea(${\beta}$ = -.278, p = .000), self-efficacy(${\beta}$ = .240, p = .000), social support(${\beta}$ = .175, p = .004), pulmonary function(${\beta}$ = .169, p = .008), and oxygen saturation(${\beta}$ = .099, p = .048). These variables explained 39.3% in functional capacity. Conclusion: The findings of this study suggest that comprehensive nursing interventions should focus on decreasing dyspnea and increasing self-efficacy, social support, and oxygen saturation. In this perspective, pulmonary rehabilitation would be an effective strategy for improving functional capacity in patients with chronic obstructive pulmonary disease.

• Journal of Korean Academy of Nursing
• /
• v.37 no.7
• /
• pp.1080-1090
• /
• 2007

Purpose: Although concerns of female sexual dysfunction (FSD) are increasing in Korea, sexual dysfunction related factors are limited in research studies. The aim of this study was to develop an explanatory model that will further explain the continuously increasing female sexual dysfunction cases in Korea. Methods: Survey visits were conducted to four hundred and eighty five women, over 25 years of age and presently residing in either urban or rural areas. All of them were analyzed using a structured questionnaire. A total of 8 instruments were used in this model. The analysis of data was done with both SPSS WIN for descriptive statistics and AMOS 5.0 for covariance structure analysis. Results: As a result, variables that showed notably direct effects on FSD were: sexual concept (sexual attitude), sexual distress, and psychosocial health (depression, crisis, traumatic life events). On the other hand, variables such as age, educational level, economic status, and marital status showed indirect influences on health-promoting behaviors. Conclusion: By comprehensively addressing the factors related to sexual dysfunction, and comparing each influence, this study can contribute to designing an appropriate sexual dysfunction prevention strategy in tune with the particular characteristics and problems of a client.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.4
• /
• pp.643-648
• /
• 2012

There are lots of analysis to determine the relation between dependent variable and explanatory variables. Often the regression analysis is used to do this, and we can analyze the how much the explanatory variable can be related with dependent variable and how much the regression model can explain the data. But the validation check of regression model is usually determined by coefficient of determination. We should check the validation of regression coefficient with different methods. This paper introduces the method for validation check the regression coefficient using the jackknife regression and bootstrap regression in clinical data.

• The Korean Journal of Financial Management
• /
• v.22 no.2
• /
• pp.43-69
• /
• 2005

This study provides empirical evidence that the stochastic beta model based on Bayesian analysis outperforms the existing conditional beta model and GARCH model in terms of the estimation accuracy and the explanatory power in the cross-section of stock returns in Korea. Betas estimated by the stochastic beta model explain $30{\sim}50%$ of the cross-sectional variation in stock-returns, whereas other time-varying beta models account for less than 3%. Such a difference in explanatory power across models turns out to come from the fact that the stochastic beta model absorbs the variation due to the market anomalies such as size, BE/ME, and idiosyncratic volatility. These results support the rational asset pricing model in that market anomalies are closely related to the variation of expected returns generated by time-varying betas.

• The Korean Journal of Applied Statistics
• /
• v.8 no.1
• /
• pp.61-74
• /
• 1995

These days, many kinds of graphical methods have been developed, and it is possible to get information directly from data. Especially, R-code (Cook and Weisberg, 1994) make it possible to draw various kinds of two and three dimensional plots, and to rotate the axis of the plots. But the maximum dimensional of the plot is three, so we can not draw plot of one response variable with more than three explanatory variables. Li(1991, 1992) has developed a method to reduce the dimension of the explanatory variables, so it is possible to draw lower dimensional plots to get information of the full explanatory variables. One of the dimension reduction method developed by Li is pHd. In this paper, we have tried to apply the pHd method for the model with multivariate response.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.431-434
• /
• 2003

In this paper we introduce a modified objective function for fuzzy c-means clustering with logistic regression model in the presence of noise cluster. The logistic regression model is commonly used to describe the effect of one or several explanatory variables on a binary response variable. In real application there is very often no sharp boundary between clusters so that fuzzy clustering is often better suited for the data.

• Journal of the Korean Society of Safety
• /
• v.33 no.4
• /
• pp.98-104
• /
• 2018

Macroscopic accident analyses have been conducted to incorporate transportation safety into long-term transportation planning. In macro-level accident prediction model, exposure variable(e.g. a settled population) have been used as fundamental explanatory variable under the concept that each trip will be subjected to a probable risk of accident. However, a settled population may be embedded error by exclusion of active population concept. The objective of this research study is to develop macro-level accident prediction model using floating population variable(concept of including a settled population and active population) collected from mobile phone data. The concept of accident prediction models is introduced utilizing exposure variable as explanatory variable in a generalized linear regression with assumption of a negative binomial error structure. The goodness of fit of model using floating population variable is compared with that of the each models using population and the number of household variables. Also, log transformation models are additionally developed to improve the goodness of fit. The results show that the log transformation model using floating population variable is useful for capturing the relationships between accident and exposure variable and generally perform better than the models using other existing exposure variables. The developed model using floating population variable can be used to guide transportation safety policy decision makers to allocate resources more efficiently for the regions(or zones) with higher risk and improve urban transportation safety in transportation planning step.