• Journal of Korean Academy of Nursing
• /
• v.49 no.5
• /
• pp.575-585
• /
• 2019

Purpose: The purpose of this study was to develop predictive models for pressure ulcer incidence using electronic health record (EHR) data and to compare their predictive validity performance indicators with that of the Braden Scale used in the study hospital. Methods: A retrospective case-control study was conducted in a tertiary teaching hospital in Korea. Data of 202 pressure ulcer patients and 14,705 non-pressure ulcer patients admitted between January 2015 and May 2016 were extracted from the EHRs. Three predictive models for pressure ulcer incidence were developed using logistic regression, Cox proportional hazards regression, and decision tree modeling. The predictive validity performance indicators of the three models were compared with those of the Braden Scale. Results: The logistic regression model was most efficient with a high area under the receiver operating characteristics curve (AUC) estimate of 0.97, followed by the decision tree model (AUC 0.95), Cox proportional hazards regression model (AUC 0.95), and the Braden Scale (AUC 0.82). Decreased mobility was the most significant factor in the logistic regression and Cox proportional hazards models, and the endotracheal tube was the most important factor in the decision tree model. Conclusion: Predictive validity performance indicators of the Braden Scale were lower than those of the logistic regression, Cox proportional hazards regression, and decision tree models. The models developed in this study can be used to develop a clinical decision support system that automatically assesses risk for pressure ulcers to aid nurses.

• Korean Journal of Mathematics
• /
• v.22 no.2
• /
• pp.289-305
• /
• 2014

In this paper we propose a new approach to the variable selection problem for a primary resolution and wavelet basis functions in wavelet regression. Most wavelet shrinkage methods focus on thresholding the wavelet coefficients, given a primary resolution which is usually determined by the sample size. However, both a primary resolution and the basis functions are affected by the shape of an unknown function rather than the sample size. Unlike existing methods, our method does not depend on the sample size and also takes into account the shape of the unknown function.

• Geomechanics and Engineering
• /
• v.23 no.2
• /
• pp.115-125
• /
• 2020

This study aims to explore practical and useful equations for rapid evaluation of uniaxial compressive strength of concrete (UCS-C) during the preliminary design stage of aggregate selection. For this purpose, aggregates which were produced from eight different intact rocks were used in the production of concretes. Laboratory experiments involved the tests for uniaxial compressive strength (UCS-R), point load index (PLI-R), P wave velocity (UPV-R), apparent porosity (n-R), unit weight (UW-R) and aggregate impact value (AIV-R) of the rock samples. UCS-C, point load index (PLI-C) and P wave velocity (UPV-C) of concrete samples were also determined. Relationships between UCS-R-rock parameters and UCS-C-concrete parameters were developed by regression analyses. In the simple regression analyses, PLI-C, UPV-C, UCS-R, PLI-R, and UPV-R were found to be statistically significant independent variables to estimate the UCS-C. However, higher coefficients of determination (R²=0.97-1.0) were obtained by multiple regression analyses. The results of simple regression analysis were also compared to the limited number of previous studies. The strength conversion factor (k) values were found to be 14.3 and 14.7 for concrete and rock samples, respectively. It is concluded that the UCS-C can roughly be estimated from derived equations only for the specified rock types.

• Korean Journal of Community Nutrition
• /
• v.4 no.2
• /
• pp.157-165
• /
• 1999

This study was conducted to identify the determinants of regional body fat distribution of obesity(upper body obesity and lower body obesity) for adolescents. The macronutrient consumption pattern utilized the most important variables to test for potential determinants. A total of 726 adolescents living in rural areas in Korea had been observed for four years from 1992 to 1996 about their diet, sexual maturation, serum components and physical growth. The study design was similar to that of a case control study. Logistic regression analysis were used as an analytical method to identify the determinants of upper body obesity and lower body obesity. Odd ratios were estimated from the regression to identify the determinants of upper body obesity and lower body obesity. Odd ratios were estimated from the regression to identify the risk factors. Fat consumption pattern was the most frequent one among the three macronutrient consumption pattern of carbohydrate, fat and protein. Prevalence of obesity for the subjects was 9.5%. Prevalence of upper body obesity was higher in malestudents than in female students. On the other had, prevalence of lower body obesity was higher in females. The results of the logicstic regression analysis showed that the risk factor for upper body obesity was sexual maturity rather than dietary factors. None of the factors included in the analysis for lower body obesity appear to be the risk factor. The result may suggest that to develop a determinant model for obesity of adolescents, the model should include a wider range of variables other than diet, sexual maturity and changes in blood serum.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.20 no.2
• /
• pp.172-178
• /
• 2010

The multiple regression analysis and path analysis in each dominant area of noise source are conducted to analyze the relationship between dependent variables like annoyance and independent ones such as noise and non-noise factors. The multiple regression analysis shows that impact of noise factors is the highest to annoyance in dominant areas of road traffic and railway noise. Meanwhile, impact of non-noise factors such as sensitivity and satisfaction of environment on annoyance is also high in these areas. The path analysis result for multivariate analysis between various independent and dependent variables is similar to that of the multiple regression analysis. However, noise factor is the greatest factor influent on annoyance in the dominant areas of the combined noise, and relationship between annoyance and sensitivity is the highest in combined area exposed to road traffic noise and railway noise.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.603-613
• /
• 2008

We often encounter the situation that discrete count data have a large portion of zeros. In this case, it is not appropriate to analyze the data based on standard regression models such as the poisson or negative binomial regression models. In this article, we consider Bayesian analysis for two commonly used models. They are zero-inflated poisson and negative binomial regression models. We use the Bayes factor as a model selection tool and computation is proceeded via Markov chain Monte Carlo methods. Crash count data are analyzed to support theoretical results.

• Transactions of Materials Processing
• /
• v.25 no.3
• /
• pp.182-188
• /
• 2016

Flexibly-reconfigurable roll forming (FRRF) is a novel sheet metal forming technology conducive to producing multi-curvature surfaces by controlling the strain distribution along longitudinal direction. In FRRF, a sheet metal is shaped into the desired curvature by using reconfigurable rollers and gaps between the rollers. As FRRF technology and equipment are under development, a simulation model corresponding to the physical FRRF would aid in investigating how the shape of a sheet varies with input parameters. To facilitate the investigation, the current study exploits regression analysis to construct a predictive model for the longitudinal curvature of the sheet. Variables considered as input parameters are sheet compression ratio, radius of curvature in the transverse direction, and initial blank width. Samples were generated by a three-level, three-factor full factorial design, and both convex and saddle curvatures are represented by a quadratic regression model with two-factor interactions. The fitted quadratic equations were verified numerically with R-squared values and root mean square errors.

• Proceedings of the Culinary Society of Korean Academy Conference
• /
• 2006.08a
• /
• pp.115-134
• /
• 2006

This study was conducted during a period from July 4 to 30 to investigate the effect of restaurant environment upon customer's satisfaction and crowdedness awareness. Total 800sets of questionnaire were distributed among major food service corporations. They were 16 restaurants from McDonald, Burger King, Popeyes, KFC, Rits Carlton, Intercontinental, The Westin Chosun, Hilton, Merriot, Outback Steak House, Bennigans, VIPS, Pizza Hut Pul-hyanggi(Scent of grass), Nolboo Co.,, and Our Story, and received 50 see each to hand out to their customers. Out of total 800 sets of questionnaires, 592 sets (74.25% were retrieved and underwent a Multiple Regression Analysis. We found the following results from the study. First among each variable of restaurant environment that had a significant effect on the crowding, 'pTast service' and 'responsiveness to customer complaints' sooted a regression coefficient value 0.381 and 0.325 respectively. Second, among each restaurant environment factor that had a significant effect on crowding, 'quality of facility' sooted the highest regression coefficient value 0.423 with a standard error score 0.1074, fellowed by 'status of waiting', 'overall ambience' and 'service quality' in ascending order. Third, in the analysis of the effect of each environmental factor upon the satisfaction rate, 'status of waiting' showed the highest regression coefficient value 0.3821 with a standard error score 0.4565, followed by 'cleanliness', 'service quality' and 'conveniency', in ascending order.

• Culinary science and hospitality research
• /
• v.12 no.4 s.31
• /
• pp.63-79
• /
• 2006

This study was conducted to investigate the effect of restaurant environment upon customers' satisfaction and crowdedness awareness from July 4 to 30. Total 800 sets of questionnaire were distributed among major foodservice corporations including 16 restaurants from McDonald, Burger King, Popeyes, KFC, Ritz Carlton, Intercontinental, The Westin Chosun, Hilton, Merriot, Outback Steak House, Bennigans, VIPS, Pizza Hut, Pul-hyanggi(Scent of grass), Nolboo Co., and Our Story. They received 50 sets each to hand out to their customers. Out of total 800 sets of questionnaires, 592 sets (74.25%) were retrieved and underwent the Multiple Regression Analysis. We found the following results from the study. First, among each variable of restaurant environment that had a significant effect on crowdedness, "fast service" and "responsiveness to customer complaints" scored a regression coefficient value 0.381 and 0.325 respectively. Second, among each restaurant environment factor that had a significant effect on crowdedness, "quality of facilities" scored the highest regression coefficient value 0.423 with a standard error score 0.1074, followed by "condition of waiting", "overall ambience" and "service quality" in ascending order. Third, in the analysis of the effect of each environmental factor upon the satisfaction rate, "condition of waiting" showed the highest regression coefficient value 0.3821 with a standard error score 0.4565, followed by "cleanliness", "service quality" and "convenience', in ascending order.

• Communications for Statistical Applications and Methods
• /
• v.27 no.2
• /
• pp.189-199
• /
• 2020

This paper studies a Bayesian ordered multiple linear regression model with skew normal error. It is reasonable that the kind of inherent information available in an applied regression requires some constraints on the coefficients to be estimated. In addition, the assumption of normality of the errors is sometimes not appropriate in the real data. Therefore, to explain such situations more flexibly, we use the skew-normal distribution given by Sahu et al. (The Canadian Journal of Statistics, 31, 129-150, 2003) for error-terms including normal distribution. For Bayesian methodology, the Markov chain Monte Carlo method is employed to resolve complicated integration problems. Also, under the improper priors, the propriety of the associated posterior density is shown. Our Bayesian proposed model is applied to NZAPB's apple data. For model comparison between the skew normal error model and the normal error model, we use the Bayes factor and deviance information criterion given by Spiegelhalter et al. (Journal of the Royal Statistical Society Series B (Statistical Methodology), 64, 583-639, 2002). We also consider the problem of detecting an influential point concerning skewness using Bayes factors. Finally, concluding remarks are discussed.