Joint Analysis of Multiple Algorithms and Performance Measures

There has been an increasing interest in the development of new methods using Pareto optimality to deal with multi-objective criteria (for example, accuracy and time complexity). Once one has developed an approach to a problem of interest, the problem is then how to compare it with the state of art. In machine learning, algorithms are typically evaluated by comparing their performance on different data sets by means of statistical tests. Standard tests used for this purpose are able to consider jointly neither performance measures nor multiple competitors at once. The aim of this paper is to resolve these issues by developing statistical procedures that are able to account for multiple competing measures at the same time and to compare multiple algorithms altogether. In particular, we develop two tests: a frequentist procedure based on the generalized likelihood-ratio test and a Bayesian procedure based on a multinomial-Dirichlet conjugate model. We further extend them by discovering conditional independences among measures to reduce the number of parameters of such models, as usually the number of studied cases is very reduced in such comparisons. Data from a comparison among general purpose classifiers is used to show a practical application of our tests.

Project Pró-Natal: population-based study of perinatal and infant mortality in Natal, Northeast Brazil

RAMOS, Ana Maria de Oliveira et al. Project Pró-Natal: population-based study of perinatal and infant mortality in Natal, Northeast Brazil. Pediatric and Developmental Pathology, v.3, n.1, p.29-35, 2000

Perceived Work-related Factors and Turnover Intention : A Case Study of a South Korean Construction Company

Purpose – Employee turnover entails considerable costs and is a major problem for the construction industry. By creating an extensive framework, this study aims to examine whether perceived work-related factors affect turnover intention in South Korean construction companies. Research design – The paper is based on the results of a questionnaire of 136 employees that was conducted and provided by a Korean construction company. Research hypotheses were tested via correlation analyses. The most influencing work-related factors, as well as differences among job levels, were determined by multiple regression analyses. Findings – Communication, immediate leaders, organizational commitment, and organizational pride substantially affect turnover intentions. All of these factors can be considered as relational factors. The most influencing factors differ among job levels. Discussion/practical implications – Immediate leaders should be aware of their role in retaining employees and enhance communication, organizational commitment and pride. This study shows how the importance of certain variables differs for groups of employees. Theoretical implications/limitations– This study is based on a sample of employees from a Korean construction company. Therefore, the generalizability of the findings has to be tested. Future research should test the proposed framework with other factors or resources. Originality/value – This study shed light on the turnover subject in the South Korean construction industry. It shows that different factors can influence turnover intention among job levels. A framework was created, which is based on 16 work-related factors including organizational factors, HRM practices and job attitudes.

Perceived Work-related Factors and Turnover Intention : - A Case Study of a South Korean Construction Company

Purpose – Employee turnover entails considerable costs and is a major problem for the construction industry. By creating an extensive framework, this study aims to examine whether perceived work-related factors affect turnover intention in South Korean construction companies. Research design – The paper is based on the results of a questionnaire of 136 employees that was conducted and provided by a Korean construction company. Research hypotheses were tested via correlation analyses. The most influencing work-related factors, as well as differences among job levels, were determined by multiple regression analyses. Findings – Communication, immediate leaders, organizational commitment, and organizational pride substantially affect turnover intentions. All of these factors can be considered as relational factors. The most influencing factors differ among job levels. Discussion/practical implications – Immediate leaders should be aware of their role in retaining employees and enhance communication, organizational commitment and pride. This study shows how the importance of certain variables differs for groups of employees. Theoretical implications/limitations– This study is based on a sample of employees from a Korean construction company. Therefore, the generalizability of the findings has to be tested. Future research should test the proposed framework with other factors or resources. Originality/value – This study shed light on the turnover subject in the South Korean construction industry. It shows that different factors can influence turnover intention among job levels. A framework was created, which is based on 16 work-related factors including organizational factors, HRM practices and job attitudes.

HELLP Syndrome a Severe Form of Preeclampsia: a Comparative Study of Clinical and Laboratorial Parameters

The objective of this study was to compare clinical, laboratorial, maternal and perinatal results between HELLP Syndrome and severe Preeclampsia. An observational study comparing women with HELLP Syndrome (n=71) to women with severe preeclampsia (n=253) was done. The authors analyzed the early course of the pathologies and the outcomes in both groups. HELLP syndrome occurred in 28% of all the cases and was more frequent at gestational age before 32 weeks (n=39 – 55%) than severe preeclampsia (n=108 - 42%), with more newborns weighting less than 1500g (27 – 38.6% vs 65 – 25.6%; p=0.036). Thrombocytopenia below 100 000/μL (aOR, 2.14; 95% CI, 1.49 – 3.06) and LDH>1 000 UI/L (aOR: 5.17; 95% CI 2.19 – 12.16) were risk factors for HELLP. Maternal morbidity (eclampsia, abruptio placentae, and acute renal failure) was similar in both cohorts; eight stillbirths (6 in severe preeclampsia and 2 in HELLP Syndrome) occurred. There were no maternal deaths. In conclusion, in this study the authors confirmed that HELLP Syndrome is a severe form of preeclampsia with an earlier presentation in pregnancy, worst laboratorial findings and more prematurity rates.