Using Kaplan–Meier analysis together with decision tree methods (C&amp;RT, CHAID, QUEST, C4.5 and ID3) in determining recurrence-free survival of breast cancer patients

Türe, Mevlüt; Tokatli, Füsun; Kurt, İmran

doi:10.1016/j.eswa.2007.12.002

Cited by 170 publications

(97 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CART veya C&RT 1984 yılında Breiman, Friedman, Olshen ve Stone tarafından geliştirilen bir algoritmadır. (Ture, Tokatlı, Kurt, & Using, 2009) (Singh & Gupta, 2014)İkili ağaç üreten bir algoritma olup veriyi iki alt kümeye ayıran ağaç oluşturur. CHAID algoritması ise ayırma kriteri olarak ki-kareyi kullanan 1980 yılında Kass tarafından geliştirilmiş bir algoritma olup bağımsız değişkenlerin tüm değerlerini dikkate alarak analiz yapar.…”

Section: Yöntemunclassified

Üniversitelerdeki Akademik Üretkenliğe Etki Eden Faktörlerin İncelenmesi

Etı

2016

İş'te Davranış Dergisi

View full text Add to dashboard Cite

ÖZAmaç: Üniversitelerde görev yapan araştırmacıların akademik üretkenliklerinin hangi faktörlere göre farklılaştığının belirlenmesi. Tasarım/Yöntem: Kolayda Örnekleme yöntemi kullanılarak elde edilen örneklemden anket yolu ile akademisyenlerin son bir yılda yayınlanan makale sayıları ve yaptıkları bildiri sayıları ile birlikte üniversitedeki işlerinin yapısıyla ilgili veri toplanmış, karar ağaçları CHAID modellemesi kullanılarak veriler analiz edilmiştir. Sonuçlar: Analiz sonuçlarına göre akademisyenlerin akademik üretkenlikleri temelde unvana göre değişmekle birlikte, yardımcı doçent ve doçentlerin başka üniversitelerde de ders vermelerinin üretkenliklerini düşürdüğü bulunmuştur. Araştırma görevlileri için ise öncelikli olarak yaş faktörü ardından ise çalıştıkları üniversitenin devlet veya vakıf üniversitesi olması etkili olmuştur. Öğretim görevlilerine bakıldığında ise cinsiyetin üretkenlik açısından ayırt edici bir faktör olduğu görülmüştür. Özgün Değer: Çalışma konusu ve yöntemi itibari ile Türkiye'de daha önce yapılmamış bir araştırmadır. Türkiye'deki akademisyenlerin akademik üretkenliklerinde ayırt edici faktörler hakkında bilgi vermesi açısından ileride yapılacak çalışmalara yön verebileceği, üniversiteler için geliştirilebilecek strateji ve politikalar için de kaynak sağlayacağı düşünülmektedir. MAKALE BİLGİSİ ABSTRACTObjectives: Determination of the academic productivity of researchers working at universities according to the factors. Methods: Through the questionnaire obtained through easy sampling method, the data about the structure of the university jobs were collected by the academicians together with the number of the articles published in the last year and the number of the papers they have published, and the decision trees were analyzed using the CHAID model. Results: According to the results of the analysis, the academic productivity of the academicians is mainly changed according to the title, but the assistant professors and associate professors have found to decrease the productivity of teaching at other universities. For researchers, the primary factor is the age factor, followed by the universities being state or foundation universities. Gender is seen as a distinctive factor in terms of productivity when looking at teaching staff. Conclusions: It is a research that has not been done in Turkey before. It is thought that the academicians in Turkey will provide resources for the strategies and policies that can be developed for the universities in order to give information about the distinguishing factors in their academic productivity

show abstract

Section: Yöntemunclassified

Üniversitelerdeki Akademik Üretkenliğe Etki Eden Faktörlerin İncelenmesi

Etı

2016

İş'te Davranış Dergisi

View full text Add to dashboard Cite

show abstract

“…These algorithms are categorized as supervised learning classification algorithm that can be used to build decision tree from the dataset. From a given set of pre-classified cases, these algorithms build diagram to map the attribute values to classes [34]. Those six decision tree algorithms work in similar way, but use different split criteria and different splitting methods.…”

Section: Related Workmentioning

confidence: 99%

A Data Mining Approach for Developing Quality Prediction Model in Multi-Stage Manufacturing

Arif¹,

Suryana²,

Hussin³

2013

IJCA

View full text Add to dashboard Cite

Quality prediction model has been developed in various industries to realize the faultless manufacturing. However, most of quality prediction model is developed in single-stage manufacturing. Previous studies show that single-stage quality system cannot solve quality problem in multi-stage manufacturing effectively. This study is intended to propose combination of multiple PCA+ID3 algorithm to develop quality prediction model in MMS. This technique is applied to a semiconductor manufacturing dataset using the cascade prediction approach. The result shows that the combination of multiple PCA+ID3 is manage to produce the more accurate prediction model in term of classifying both positive and negative classes. General TermsData Mining, Prediction Model.

show abstract

“…Other techniques create binary trees whereas CHAID analysis creates multiple trees (Türe et al, 2009(Türe et al, :2020. A regression equation obtained by CHAID analysis is exempt from all known classical hypotheses (normality, linearity, homogeneity etc.)…”

Section: Chaid Analysismentioning

confidence: 99%

Determination of the Demographic Variables Predicting Accommodation Business Employees Organizational Commitment and Job Satisfaction through CHAID Analysis

Üngüren¹,

Ehtíyar²

2016

isarder

View full text Add to dashboard Cite

The main objective of this research is to determine the demographic variables that affect job satisfaction and organizational commitment attitudes via CHAID analysis which is one of the decision tree techniques. CHAID analysis creates sub-clusters by grouping the factors that affect the dependant variable in line with their importance levels and allows the results to be understood and interpreted more easily by displaying the relationship between variables visually. The research was carried out with 821 employees working in five star accommodation businesses in Alanya, Turkey. Survey forms were used as data collection tool. The collected data were analyzed by descriptive statistics, cluster analysis and CHAID analysis. The results of the research point a strong positive relationship between organizational commitment and job satisfaction. According to the CHAID analysis results, age was the dominant demographic variable influential on job satisfaction and organizational commitment attitudes. It was also found that job satisfaction and organizational commitment scores of the employees differ significantly in terms of department, marital status, education, status and gender. As a result of CHAID analysis it was determined that "the housekeeping, bar and kitchen department employees in the age range of 18 to 27" and "the married male employees in the age range of 28 to 37" predominantly have negative job satisfaction and organizational commitment attitude. Another result of CHAID analysis has also revealed that "high school and college graduate employees in the age range of 38 to 47" and "48 and over" totally have positive attitude in terms of job satisfaction and organizational commitment.

show abstract

Using Kaplan–Meier analysis together with decision tree methods (C&RT, CHAID, QUEST, C4.5 and ID3) in determining recurrence-free survival of breast cancer patients

Cited by 170 publications

References 22 publications

Üniversitelerdeki Akademik Üretkenliğe Etki Eden Faktörlerin İncelenmesi

Üniversitelerdeki Akademik Üretkenliğe Etki Eden Faktörlerin İncelenmesi

A Data Mining Approach for Developing Quality Prediction Model in Multi-Stage Manufacturing

Determination of the Demographic Variables Predicting Accommodation Business Employees Organizational Commitment and Job Satisfaction through CHAID Analysis

Contact Info

Product

Resources

About