• Communications for Statistical Applications and Methods
• /
• 제23권5호
• /
• pp.433-444
• /
• 2016

When we observe binary responses in a cluster (such as rat lab-subjects), they are usually correlated to each other. In clustered binomial counts, the independence assumption is violated and we encounter an extra-variation. In the presence of extra-variation, the ordinary statistical analyses of binomial data are inappropriate to apply. In testing the homogeneity of proportions between several treatment groups, the classical Pearson chi-squared test has a severe flaw in the control of Type I error rates. We focus on modifying the chi-squared statistic by incorporating variance inflation factors. We suggest a method to adjust data in terms of dispersion estimate based on a quasi-likelihood model. We explain the testing procedure via an illustrative example as well as compare the performance of a modified chi-squared test with competitive statistics through a Monte Carlo study.

• 대한가정학회지
• /
• 제50권2호
• /
• pp.25-38
• /
• 2012

The purpose of this study was to investigate how parents saw the relationship between early years educational institutions and parents, and how these perceptions were influenced by parental background factors. A total of 334 parents who sent their child to a kindergarten participated in this study. The collected data were analyzed by Chisquared test, t-test, and one-way ANOVA. The results of this study were as follows. First, parents had a high level of interest in their child's education, but little actual knowledge about the contents and strategies of education in the kindergarten setting. Second, regarding parental participation in early childhood education institutions, necessity for parents's involvement in the institutions was relatively higher than the average. Third, when considering the relationship between staff in early childhood education institutions, i.e. kindergartens, and parents both teachers and parents hoped to form a relationship in which they could freely exchange their opinions.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.150-154
• /
• 2024

In recent years, there are extensive researches on the applications of machine learning to the automation and decision support for medical experts during disease detection. However, the performance of machine learning still needs improvement so that machine learning model produces result that is more accurate and reliable for disease detection. Selecting the hyper-parameter that could produce the possible maximum classification accuracy on medical dataset is the most challenging task in developing decision support systems with machine learning algorithms for medical dataset classification. Moreover, selecting the features that best characterizes a disease is another challenge in developing machine-learning model with better classification accuracy. In this study, we have proposed an optimized decision tree model for heart disease classification by using heart disease dataset collected from kaggle data repository. The proposed model is evaluated and experimental test reveals that the performance of decision tree improves when an optimal number of features are used for training. Overall, the accuracy of the proposed decision tree model is 98.2% for heart disease classification.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권9호
• /
• pp.4521-4524
• /
• 2012

Object: In the present study, we compared the positive cytodiagnostic test rates with discrepancies using self-collection devices for cervical cancer screening. We made this survey to examine whether or not our self-smear preparation method using the Kato self-collection device contributed to an improved rate of detecting atypical cells compared with existing recommended preparation methods. Methods: Specimens were collected at 14 facilities handling self-collection methods, and samples were collected by a physician in 2 facilities. The chisquared test was performed using the SPSS ver. 20 statistical software to determine the relationships between the positive cytodiagnostic rate, specimen preparation methods, and self-collection devices. Results: Collecting cells using the Kato self-collection device and preparing liquid-based specimens, we obtained a significantly higher rate of positive cytodiagnosis and our results were equal to those obtained with the direct method. Conclusions: Taking into consideration increased needs for screening using the self-collection method in future, with even more improved test accuracy, a screening test that is acceptable to society needs to be established.

• Journal of Oral Medicine and Pain
• /
• 제45권2호
• /
• pp.23-28
• /
• 2020

Purpose: Temporomadibular disorders (TMDs) can result in chronic pain, which is often associated with psychological and sleep disturbance. Increased levels of psychological and sleep impairments are often related with poor treatment outcomes. The purpose of the present study was to evaluate clinical features, psychological profiles and the prevalence of clinical insomnia in TMD patients with chronic pain and to suggest an effective treatment approach. Methods: A total of 200 TMD patients who had visited the Pusan National University Hospital dental clinic for treatment of their pain were recruited from June 2018 through December 2019. TMD patients were classified into an acute (n=100) and chronic (n=100) group and compared the clinical symptoms. The primary diagnosis of TMD were categorized as TMD with joint pain group (TMD_J), TMD with muscle pain group (TMD_M) and TMD with joint-muscle mixed pain group (TMD_JM). Self- report measures of sleep quality and psychological profiles were evaluated via the Insomnia Severity Index (ISI) and the Korean Stress Response Inventory (SRI). Independent t-tests, Mann-Whitney U-tests, and chisquared test were used for the statistical analysis. Results: Chronic TMD patients showed higher pain intensity, as well as higher prevalence of related symptoms (headache, musculoskeletal pain) and myogenous pain. They also had significantly higher scores in all SRI parameters and a higher percentage of clinical insomnia than acute TMD patients. Conclusions: Based on the above results, psychological profiles and sleep quality assessments are necessary to provide essential data that will allow for improved treatment of chronic TMD patients.

• 정신신체의학
• /
• 제26권1호
• /
• pp.1-8
• /
• 2018

연구목적 본 연구에서는 기능성 위장질환(Functional gastrointestinal disorder, 이하 FGID)이 동반된 정신질환자들의 정신사회적 특성을 알아보고자 하였다. 방 법 일 대학병원 정신건강의학과 외래를 방문한 환자를 대상으로 Rome III questionnaire - Korean version에 따라 FGID를 선별하여 144명의 자료를 분석하였다. 인구학적 요인을 조사하였으며, 정신사회적 요인을 평가하기 위해 Hospital Anxiety Depression Scale, Patient Health Questionnaire-15, Childhood Trauma Questionnaire-Korean, State-Trait Anger Expression Inventory를 사용하였다. 통계분석은 독립표본 t-검정(independent t-test)과 교차분석(chi-square test)을 사용하였다. 결 과 FGID에 따른 집단간 비교에서 학력에 따른 차이가 나타났다(${\chi}^2=10.139$, p=0.017). FGID 집단에 따른 정신질환의 차이에서는 과민성 대장증후군(Irritable bowel syndrome, 이하 IBS) 집단에서 유의한 차이가 있었다. (${\chi}^2=11.408$, p=0.022) IBS 집단은 불안(t=-3.106, p=0.002), 우울증상(t=-2.105, p=0.037), 신체증상(t=-3.565, p<0.001), 특성분노(t=-3.683, p<0.001), 분노-억제(t=-2.463, p=0.015), 분노-표출(t=-2.355, p=0.020)에서 높은 점수를 나타냈다. 기능성 소화불량(Functional dyspepsia) 집단에서는 불안(t=-4.893, p<0.001), 우울증상(t=-3.459, p<0.001), 신체증상(t=-7.906, p<0.001), 특성분노(t=-4.148, p<0.001), 상태분노(t=-2.181, p=0.031), 분노-억제(t=-2.684, p=0.008), 분노-표출(t=-3.005, p=0.003)지표가 유의하게 높았다. 비미란성 위식도 역류증(Nonerosive reflux disease) 집단에서는 불안(t=-4.286, p<0.001), 우울증상(t=-3.402, p<0.001), 신체증상(t=-7.162, p<0.001), 특성분노(t=-2.994, p=0.003), 상태분노(t=-2.259, p=0.025), 분노-억제(t=-2.772, p=0.006), 분노-표출(t=-2.958, p=0.004)에서 유의미하게 높은 수준을 나타냈다. 결 론 본 연구에서는 정신질환자에서 FGID의 유병률이 매우 높고, 다양한 정신사회적 변인들이 이에 영향을 미치는 것으로 나타났다. 따라서 이러한 정신의학적 접근은 FGID 환자를 더 잘 이해하고 치료하는데 있어서 도움이 될 것으로 생각된다.