• The Korean Journal of Applied Statistics
• /
• v.18 no.3
• /
• pp.543-553
• /
• 2005

Linear logistic regression is one of the most widely used method for credit scoring in credit risk management. This paper deals with credit scoring using splines based on Logistic regression. Linear splines and an automatic basis selection algorithm are adopted. The final model is an example of the generalized additive model. A simulation using a real data set is used to illustrate the performance of the spline method.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.62 no.1
• /
• pp.61-70
• /
• 2020

To estimate the ventilation volume of mechanically ventilated swine farms, various regression models were applied, and errors were compared to select the regression model that can best simulate actual data. Linear regression, linear spline, polynomial regression (degrees 2 and 3), logistic curve, generalized additive model (GAM), and gompertz curve were compared. Overfitting models were excluded even when the error rate was small. The evaluation criteria were root mean square error (RMSE) and mean absolute percentage error (MAPE). The evaluation results indicated that degree 3 exhibited the lowest error rate; however, an overestimation contradiction was observed in a certain section. The logistic curve was the most stable and superior to all the models. In the estimation of ventilation volume by all of the models, the estimated ventilation volume of the logistic curve was the smallest except for the model with a large error rate and the overestimated model.

• Geomechanics and Engineering
• /
• v.10 no.3
• /
• pp.269-284
• /
• 2016

Simplified techniques based on in situ testing methods are commonly used to assess seismic liquefaction potential. Many of these simplified methods were developed by analyzing liquefaction case histories from which the liquefaction boundary (limit state) separating two categories (the occurrence or non-occurrence of liquefaction) is determined. As the liquefaction classification problem is highly nonlinear in nature, it is difficult to develop a comprehensive model using conventional modeling techniques that take into consideration all the independent variables, such as the seismic and soil properties. In this study, a modification of the Multivariate Adaptive Regression Splines (MARS) approach based on Logistic Regression (LR) LR_MARS is used to evaluate seismic liquefaction potential based on actual field records. Three different LR_MARS models were used to analyze three different field liquefaction databases and the results are compared with the neural network approaches. The developed spline functions and the limit state functions obtained reveal that the LR_MARS models can capture and describe the intrinsic, complex relationship between seismic parameters, soil parameters, and the liquefaction potential without having to make any assumptions about the underlying relationship between the various variables. Considering its computational efficiency, simplicity of interpretation, predictive accuracy, its data-driven and adaptive nature and its ability to map the interaction between variables, the use of LR_MARS model in assessing seismic liquefaction potential is promising.

• Land and Housing Review
• /
• v.12 no.4
• /
• pp.31-40
• /
• 2021

In the present article we examine life-cycle housing demand for Korea. Distinguished in this work from prior research is the consideration of non-monocinity in the life-cycle housing demand. To this end, we adopt spline logistic regression models. Our findings suggest that life-cyclicity is most clear in Korean housing demand; namely, 1) small (mid-large) house ownership falls (grows) dramatically as households age into middle aged; 2) middle aged households do not participate in the rental or purchase market actively; 3) elderly population does not dispose of their housing to the same extent as younger generations acquire housing.

• Journal of Nutrition and Health
• /
• v.52 no.6
• /
• pp.552-558
• /
• 2019

Purpose: Although vitamin D deficiency is common among Korean adolescent girls and young women, few studies have explored the potential health effects of vitamin D deficiency in this vulnerable population. This study examined the association between vitamin D deficiency and anemia in Korean adolescent girls and young women. Methods: The data from the Korea National Health and Nutrition Examination Survey 2008 ~ 2014 were used. A total of 3,643 girls and adult women aged 12 to 29 who provided all the information (including serum 25-hydroxy vitamin D, hemoglobin, and/or serum ferritin) needed for the analysis were included in the analysis. Demographic, lifestyle, and health data were obtained through survey questionnaires. Anemia and iron deficiency anemia were defined according to the World Health Organization cut-offs. Multivariable logistic regression, and restricted cubic spline regression were used in the analysis. Results: In fully adjusted logistic regression models, the vitamin D deficiency was significantly associated with higher prevalences of anemia (odds ratio (OR): 1.61, 95% confidence interval (CI): 1.04 ~ 2.49) and iron deficiency anemia (OR: 1.43, 95% CI: 1.01 ~ 2.03). In a cubic spline regression model, we observed a dose-response relationship between serum 25(OH)D concentration and anemia, and this linear relationship was also clearly observed between serum 25(OH)D concentration and iron deficiency anemia. Conclusion: Vitamin D deficiency may be associated with a higher prevalence of iron deficiency anemia and anemia in adolescent girls and young women. Alternatively, vitamin D deficiency may be a concurrent event for patients with anemia, which we cannot distinguish in this cross-sectional study. Further studies are needed to verify the causality in this population of low vitamin D levels.

• Korean Journal of Community Nutrition
• /
• v.17 no.3
• /
• pp.329-340
• /
• 2012

Hypertension is a well-known risk factor for cardiovascular disease. Previous studies have shown that changes in diet and lifestyle factors can prevent the development of hypertension, but the combined effects of these modifiable factors on hypertension are not well established. The objective of this study is to investigate associations of diet and lifestyle factors, evaluated both individually and in combination, with prevalent hypertension among Korean adults. We analyzed data obtained from the 2007-2008 Korean National Health and Nutritional Examination Survey, a nationwide cross-sectional study using a stratified, multistage probability sampling design. The associations of 12 nutrient intakes and lifestyle factors with risk of hypertension were explored using restricted cubic spline regression and logistic regression models among 6,351 adults. Total energy and several nutrients and minerals, including, calcium, vitamin A, vitamin C, and sodium, showed non-linear relationships with the risk of prevalent hypertension. In multivariate logistic regression models, dietary score, obesity and alcohol intake were independently associated with the risk of prevalent hypertension, but smoking and physical activity were not. Overall, participants whose dietary habits and lifestyle factors were all in the low-risk group had 68% lower prevalence of hypertension (OR: 0.32, 95 CI: 0.14-0.74) compared to those who were at least one in the high-risk group of any dietary or lifestyle factors. The result suggests that combined optimal lifestyle habits are strongly associated with lower prevalence of hypertension among Korean adults.

• Communications for Statistical Applications and Methods
• /
• v.16 no.4
• /
• pp.713-722
• /
• 2009

The estimation of odds ratio and corresponding confidence intervals for case-control data have been done by traditional generalized linear models which assumed that the logarithm of odds ratio is linearly related to risk factors. We adapt a lower-dimensional approximation of Gu and Kim (2002) to provide a faster computation in nonparametric method for the estimation of odds ratio by allowing flexibility of the estimating function and its Bayesian confidence interval under the Bayes model for the lower-dimensional approximations. Simulation studies showed that taking larger samples with the lower-dimensional approximations help to improve the smoothing spline estimates of odds ratio in this settings. The proposed method can be used to analyze case-control data in medical studies.

• Nutrition Research and Practice
• /
• v.15 no.4
• /
• pp.468-478
• /
• 2021

BACKGROUND/OBJECTIVES: This study aimed to analyze the association between dietary omega-3 fatty acid intake and depression in postmenopausal women using data from the Korea National Health and Nutrition Examination Survey (KNHANES) VI. SUBJECTS/METHODS: The KNHANES is a cross-sectional nationwide health and nutrition survey. Dietary data, including omega-3 fatty acids, were assessed using the 24-h recall method. Depression was evaluated using a survey questionnaire. The association between dietary omega-3 fatty acids and depression was evaluated using multivariate logistic regression analysis. Depression, according to the dietary omega-3 fatty acid intake, was expressed as the odds ratio (OR) with a 95% confidence interval (CI). A total of 4,150 postmenopausal women were included in the analysis. RESULTS: In the fully-adjusted model, the group with the highest dietary omega-3 fatty acid intake significantly showed lower prevalence of depression than the group with the lowest intake (OR, 0.52; 95% CI, 0.33-0.83); a significant linear trend was detected (P for trend = 0.04). According to the dose-response analysis using cubic restricted spline regression, this association was linear and monotonic (P for non-linearity = 0.32). CONCLUSIONS: In this study, the dietary omega-3 fatty acid intake in postmenopausal women was inversely proportional to depression in a dose-response manner. Large cohort studies are needed to verify the causality between omega-3 fatty acids and depression in Korean postmenopausal women.