• Title/Summary/Keyword: 로지스틱 회귀모형

Search Result 432, Processing Time 0.033 seconds

Comparison of resampling methods for dealing with imbalanced data in binary classification problem (이분형 자료의 분류문제에서 불균형을 다루기 위한 표본재추출 방법 비교)

  • Park, Geun U;Jung, Inkyung
    • The Korean Journal of Applied Statistics
    • /
    • v.32 no.3
    • /
    • pp.349-374
    • /
    • 2019
  • A class imbalance problem arises when one class outnumbers the other class by a large proportion in binary data. Studies such as transforming the learning data have been conducted to solve this imbalance problem. In this study, we compared resampling methods among methods to deal with an imbalance in the classification problem. We sought to find a way to more effectively detect the minority class in the data. Through simulation, a total of 20 methods of over-sampling, under-sampling, and combined method of over- and under-sampling were compared. The logistic regression, support vector machine, and random forest models, which are commonly used in classification problems, were used as classifiers. The simulation results showed that the random under sampling (RUS) method had the highest sensitivity with an accuracy over 0.5. The next most sensitive method was an over-sampling adaptive synthetic sampling approach. This revealed that the RUS method was suitable for finding minority class values. The results of applying to some real data sets were similar to those of the simulation.

Influence of Multidimensional Deprivation on the Latent Class of Changing Trajectories: Comparison by Gender Differences (다차원적 박탈이 문제음주 변화궤적의 잠재집단에 미치는 영향: 성별 차이 비교)

  • Lee, SooBi;Lee, Suyoung
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.4
    • /
    • pp.278-291
    • /
    • 2021
  • This study performed a longitudinal research on the causal relationship between multidimensionality of problem drinking and poverty, and multidimensional deprivation meaning the inequality, focusing on gender difference. For this, this study examined the latent group of problem drinking change trajectory through the latent class growth analysis targeting total 3,770 men and 5,632 women by using the 6th-year Korea Welfare Panel Study data from 2013 to 2018, and then conducted the multinominal logistic regression analysis to verify the influence of multidimensional deprivation factors on this latent group. The main results of this study are as follows. First, the latent group of problem drinking change trajectory according to gender was classified into three latent groups in both men and women while the development aspect was different from each other. The male latent group with 'moderate level' or higher showed higher level of problem drinking than women. However, in case of 'drinking group with high level' according to gender, as time passed, the men tended to maintain it while the women tended to increase it. Second, in the results of examining the effects of multidimensional deprivation on the latent group of problem drinking change trajectory, the men with more experiences of social deprivation and the women with more experiences of social security deprivation showed the higher possibility to belong to the 'drinking group with high level' compared to the 'drinking group with low level'. Based on such results above, this study discussed the preventive/intervention measures for problem drinking according to gender.

The Relationship between Lifestyle Choices and Substance Addiction in Young Adults (국내외 청년의 라이프스타일과 물질중독의 관련성)

  • Jang, Se Eun;Yun, Mi-Eun;Kim, Jinsoo Jason;Kim, Sun-Hee;Ramirez, Francisco Eddie;Nedley, Neil
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.6
    • /
    • pp.580-595
    • /
    • 2022
  • This study looked at the relationship between lifestyle choices and various substance addictions in young adults by applying the Relapse Prevention model of addiction. The data was obtained from a cross-sectional questionnaire (Depression and Anxiety Assessment Test) of 926 young adults aged 18~24 from 24 countries. Of these, 17.6% reported that they had a serious substance addiction, with alcohol addiction being the highest (11.2%), followed by nicotine (10.3%) and illicit drug (8.7%) usage. Results of chi-square test and logistic regression analysis revealed a significant association between various lifestyle factors (exercise patterns, intake of dietary nutrients like tryptophan, folic acid, omega-3 fatty acids and micronutrients, spiritual habits such as Bible reading and prayer) and addiction to various substances (illicit drugs, alcohol and nicotine). Depression was also found to be a significant factor influencing substance addiction. Interestingly, the risk of alcohol abuse was the highest at 9.870 (95% CI: 4.525-21.525) times among those who didn't have the habit of daily Bible reading. The highest risk of nicotine and illicit drug addiction was among those who consumed 'less than 1 serving' of dietary micronutrients per day compared to those who consumed '5 or more servings', with odds ratios of 9.606(95% CI: 2.726-30.111) and 8.642(95% CI: 2.022-37.378), respectively. These findings suggest that holistic lifestyle interventions may help prevent and reduce substance addiction in young adults.

The Influence Factors on the Stages of Change of Exercise in Middle Aged Men who Work based on the Transtheoretical Model (범이론적모형에 근거한 직장 중년남성의 운동행위변화단계에 미치는 영향요인)

  • Hyea-Kyung Lee
    • Journal of Industrial Convergence
    • /
    • v.20 no.12
    • /
    • pp.1-9
    • /
    • 2022
  • The objective of this study was to analyze the factors affecting the stages of change of exercise in middle-aged men who work. 170 middle-aged men who work surveyed, 40 to 59 years old, is residing, Chung-Buk and Chung-Nam province, who understand the purpose of this study and agree to participate in this study. This study data is analyzed by using frequency, percentage, standard deviation, t-test, 𝑥2 test and Logistic regression analysis. The study show that the exercise self-efficacy(𝛽=.965, p=.003) and the perceived health status(𝛽=.805, p=.025) among middle aged men who work have an effect on the stages of change of exercise meaningfully. That is, the exercise self-efficacy of middle aged men who work who have exercise behavior is 2.6 times higher than middle aged men at work who don't have exercise behavior, and the perceived health status is 2.2 times higher. This study suggests that the development of better exercise practice for middle aged men who work should be aimed at promoting exercise self-efficacy and perceived health status, Based on this, it is necessary to find ways to operate exercise programs at the workplace and community level.

Corporate Bankruptcy Prediction Model using Explainable AI-based Feature Selection (설명가능 AI 기반의 변수선정을 이용한 기업부실예측모형)

  • Gundoo Moon;Kyoung-jae Kim
    • Journal of Intelligence and Information Systems
    • /
    • v.29 no.2
    • /
    • pp.241-265
    • /
    • 2023
  • A corporate insolvency prediction model serves as a vital tool for objectively monitoring the financial condition of companies. It enables timely warnings, facilitates responsive actions, and supports the formulation of effective management strategies to mitigate bankruptcy risks and enhance performance. Investors and financial institutions utilize default prediction models to minimize financial losses. As the interest in utilizing artificial intelligence (AI) technology for corporate insolvency prediction grows, extensive research has been conducted in this domain. However, there is an increasing demand for explainable AI models in corporate insolvency prediction, emphasizing interpretability and reliability. The SHAP (SHapley Additive exPlanations) technique has gained significant popularity and has demonstrated strong performance in various applications. Nonetheless, it has limitations such as computational cost, processing time, and scalability concerns based on the number of variables. This study introduces a novel approach to variable selection that reduces the number of variables by averaging SHAP values from bootstrapped data subsets instead of using the entire dataset. This technique aims to improve computational efficiency while maintaining excellent predictive performance. To obtain classification results, we aim to train random forest, XGBoost, and C5.0 models using carefully selected variables with high interpretability. The classification accuracy of the ensemble model, generated through soft voting as the goal of high-performance model design, is compared with the individual models. The study leverages data from 1,698 Korean light industrial companies and employs bootstrapping to create distinct data groups. Logistic Regression is employed to calculate SHAP values for each data group, and their averages are computed to derive the final SHAP values. The proposed model enhances interpretability and aims to achieve superior predictive performance.

The Association between Resistance Exercise Frequency, Muscular Strength, and Health-Related Quality of Life in Korean Cancer Patients: The Korea National Health and Nutrition Examination Survey (KNHANES) 2014-2016 (한국 암환자들의 근력운동 빈도, 근력과 건강관련 삶의 질과의 관계: 국민건강영양조사 2014-2016년)

  • An, Ki-Yong;Kang, Dong-Woo;Min, Ji Hee
    • 한국체육학회지인문사회과학편
    • /
    • v.57 no.5
    • /
    • pp.269-279
    • /
    • 2018
  • The purpose of this study is to examine the association between resistance exercise frequency, muscular strength, and health-related quality of life in Korean cancer patients. We performed complex sample general linear model and logistic regression analysis using data from a total of 647 cancer patients in the 2014~2016 Korean National Health and Nutrition Examination Survey (KNHANES). Participants who were participating in resistance exercise 0~1 day per week had lower EQ-5D index (0.852±0.016 vs. 0.890±0.020; p=0.006) and a significantly higher risk of having problems in mobility (Odd ratio[OR]=4.07; 95% confidence interval [CI]=1.31-12.63) compared to those who were participating in resistance exercise ≥ 5 days per week. Participants with low hand-grip strength had lower EQ-5D index (0.850±0.018 vs. 0.911±0.016; p<0.001) and a significantly higher risk of having problems in mobility (OR=4.94, 95% CI=2.14-11.41), usual activities (OR=5.18, 95% CI=1.56-17.14), and pain/discomfort (OR=2.46, 95% CI=1.33-4.55) compared to those with high hand-grip strength. This study showed that resistance exercise frequency and muscular strength were associated with health-related quality of life in Korean cancer patients.

Determinants of Long-Term Care Service Use by Elderly (노인장기요양서비스 이용형태 결정요인 연구)

  • Lee, Yun-kyung
    • 한국노년학
    • /
    • v.29 no.3
    • /
    • pp.917-933
    • /
    • 2009
  • This study examined the factors affecting forms of long-term care service use by elderly and the forms of use are classified facility care service, home care service, and unused. It is used data from the 2nd pilot program for the Long Term Care Insurance scheme and it is analysed 5,497 cases. Multi-nominal regression is used. According to the results, women use formal service more than man do, and wowen use facility care than home care. Those who eligible for National Basic Livelihood Security System(NBLSS) are shown to have higher use of formal care(especially facility care) than the middle income class, and the low income class than the middle income class has lower use of formal care. In addition, higher the family care is available, lower the taking part in the service. The big cities and mid sized cities than rural are used the formal service and moreover mid sized cities are used facility care than home care. Furthermore, the level of care need is determinants of service use and function of ADL, IADL, and abnormal behavior is also determinants of formal service(especially facility care). But nursing need and rehabilitation need are not determinants of formal service use. Based on the results, the recommendations are developed and implemented for the improvement the elderly long-term care insurance.

Correlation between oral frailty and health-related quality of life (HINT-8) among older adults in Korea (한국 노인의 구강노쇠와 건강관련 삶의 질(HINT-8)의 관련성)

  • In-Ja Kim
    • Journal of Korean society of Dental Hygiene
    • /
    • v.24 no.2
    • /
    • pp.109-119
    • /
    • 2024
  • Objectives: This study aimed to confirm the correlation between oral frailty and health-related quality of life (HINT-8) among older adults in Korea. Methods: The data of 1,318 individuals aged ≥65 years who participated in the eighth Korean National Health and Nutrition Examination Survey (2019) were analyzed using complex sample statistical analysis. Results: Chewing discomfort was found to decrease the HINT-8 scores by 1.246, 1.324, and 1.089 times in the physical, social, and mental domains, respectively. Speech discomfort was found to decrease the HINT-8 scores by 1.275, 1.449, and 1.175 times in the physical, social, and mental domains, respectively. The HINT-8 scores of participants with ≤19 natural teeth were lower in the physical and social domains. Similarly, the HINT-8 scores of participants with brushing frequency of ≤2 were lower in the positive health domain. Non-use of oral hygiene products led to a reduction in the HINT-8 score in the social health domain. Conclusions: Oral frailty in older adults reduces the health-related quality of life. Thus, it is necessary to formulate policies to manage oral frailty in this population and develop specialized programs for the management of oral frailty.

Gender Difference in Quality of Life After Controlling for Related Factors among Korean Young-old and Old-old Elderly (한국 전·후기 노인의 삶의 질 관련요인과 성별 차이)

  • Chung, Younghae;Cho, Yoo Hyang
    • Journal of agricultural medicine and community health
    • /
    • v.39 no.3
    • /
    • pp.176-186
    • /
    • 2014
  • Objectives: As a sequel to the former analysis of the quality of life (QoL) among young-old and old-old in Korea, this research was aimed to identify factors related to the quality of life and the gender difference after controlling for the related factors among Korean elderly. Methods: Selected elderly data of 1,339 subjects from the 5th Korea National Health and Nutrition Examination Survey conducted in 2010 was analyzed. In this survey, QoL was measured using Euro Quality of Life (EQ-5D) instrument. Data were analyzed using complex survey data analysis on IBM-SPSS 20.0. The related factors were identified using general linear models with backward elimination. The gender difference was tested also using general linear models. Results: The distributions of educational level, family income level, and presence of cohabitant were different between male and female elderly in both young-old and old-old age group. So were the health behaviors and perceived health, and experience of stress, depression, and suicidal thoughts. QoL and its subscales- mobility, self care, daily living, pain and discomfort, and anxiety and depression- were consistently better among male elderly regardless of age group. Among the variables considered, education, family income level, presence of cohabitant, perceived health, age group and BMI were found to be related to the QoL at p=.05, and presence of chronic diseases at p=.10. The difference in QoL between male and female elderly after controlling for the variables was statistically significant. Conclusion: Improving QoL is particularly important for the elderly. In order to improve QoL of the elderly, age- and gender- differences need to be considered when developing services and programs for the elderly.

Therapeutic compliance and its related factors in pediatrics patients (소아 환자의 치료 순응도 및 이에 영향을 미치는 요인)

  • Park, Ki Soo;Kam, Sin;Kim, Heung Sik;Lee, Jeong Kwon;Hwang, Jin-Bok
    • Clinical and Experimental Pediatrics
    • /
    • v.51 no.6
    • /
    • pp.584-596
    • /
    • 2008
  • Purpose : This study was conducted to investigate treatment compliance and related factors in pediatric patients. Methods : Three hundred and fifty-five patients diagnosed with various acute diseases at a teaching hospital or clinic in October 2003 were enrolled. Data were analyzed using the Health Belief Model, which includes items on self-efficacy and family assistance. Results : The study found that 62.9% of pediatric patients adhered faithfully to agreed-upon hospital revisits, 41.6% complied with dose timings instructions, 65.8% precisely took medication, and 27.2% complied with all of these requirements. According to ${\chi}^2$ test analysis, the factors found to be related to therapeutic compliance (the taking of medicines requested) were; susceptibility, severity, benefit, barriers, mother's self-efficacy, and family assistance (P<.05). Multiple logistic analysis and path analysis showed that susceptibility, severity, barriers, and mother's self-efficacy were related to therapeutic compliance (P<.05). Moreover, mother's self-efficacy was identified as the most important factor. Conclusion : To improve therapeutic compliance among pediatric patients, parental education is necessary, and a health care professional must take a thorough history of how the medication was taken before it is assumed that treatment failure is attributable to the medication prescribed. Furthermore, the type of device recommended for dosing should be determined by clinicians. In addition, it is important that pediatric medications be discussed in relation to their palatability and internal acceptability.