Salah satu kendala yang sering dihadapi pada penelitian survival adalah adanya data tersensor. Jika data tersensor dihilangkan, maka akan terjadi bias. Pengolahan data tersensor dapat dilakukan dengan Cox Semiparametric Hazards model. Pada penelitian ini, digunakan data tersensor kanan yang dianalisis dengan Cox semiparametric hazards model, yang parameternya diestimasi dengan metode Efron. Pada penelitian ini dilakukan studi kasus dengan menganalisis Hazard rasio terjadinya diabetik retinopati pada pasien diabetes tipe juvenile dan tipe adult. Setelah melakukan stratifikasi jenis mata yang dilakukan treatment, diperoleh risiko terjadinya retinopati pada penderita diabetes tipe adult 0.678 kali dari penderita diabetes tipe juvenile. Artinya, risiko terjadinya diabetik retinopati pada penderita diabetes tipe adult 0.322 kali lebih besar dari penderita diabetes tipe juvenile.Kata Kunci: Cox Semiparametric Hazards model, Data tersensor Kanan, Metode Efron

Pemetaan kontraksi Reich siklik pada ruang kuasi αB-metrik akan diperkenalkan dalam tulisan ini. Akan ditunjukkan bahwa setiap pemetaan kontraksi Reich siklik memiliki titik tetap yang tunggal. Selain itu, diberikan pula contoh fungsi yang memenuhi kontraksi Reich siklik.

Information Literacy skills are needed to find quality sources and manage and sort information so that it can be used to improve the quality of life and community empowerment. The number of factors that affect information literacy causes the need for classification. The method used is Improved Chi-Square Automatic Interaction Detection (Improved CHAID), which aims to classify influencing factors with Information Literacy abilities. This study uses primary data, namely 237 Mananggu Young Generation (15-24 years), with Information Literacy as the dependent variable. The independent variables consist of reading interest, reading habits, gender, digital literacy, information needs, critical thinking, and information-seeking behavior. Based on the Improved CHAID analysis, the factors that significantly affect information literacy are Reading Habits (83%), Information Needs (89%), and Critical Thinking (94%). The classification performance of Testing Data is 40%, with a classification accuracy of 77% or from 95 samples, there are 73 samples that are properly classified. The sensitivity of 78% shows that the classification results are able to predict samples that have information literacy, 74% specificity indicates that the classification results are able to predict samples that do not have information literacy, and Press's Q 27.38 indicates a stable classification or statistically significant.

Sharia-based investment is an investment by the community to obtain profits in accordance with Islamic principles and law. This study aims to calculate the optimal portfolio return value using the Single Index Model, calculate risk with VaR (Value at Risk), and then implement it with Matlab’s GUI (Graphical User Interface). The data used is closing stock price data on the JII (Jakarta Islamic Index) using 30 stocks for two consecutive years. Furthermore, these stocks are selected which have a positive average return value. The study results show that 14 stocks are candidates for optimal portfolios with positive return values, namely: ACES, ADRO, ANTM, BRPT, BTPS, CTRA, EXCL, INCO, MDKA, MNCN, SCMA, TPIA, UNTR, and WIKA. Then the optimal portfolio of the 14 stocks is determined using the Single Index Model considering the ERB (Excess Return to Beta) value ≥ cut-off point value (C*). Based on the value, 4 shares were obtained that belong to the optimal portfolio, namely: MDKA, BRPT, BTPS, and ANTM. Furthermore, VaR calculations are performed on the 4 optimal portfolios to obtain optimum VaR consistency values with 500 repetitions. The VaR calculation results with a 95% confidence level show that the average VaR result is in the range of -0.14704 to -0.3420 so that when investors invest in 4 optimal stocks, the losses experienced by investors are no more than 34%.

The goal of this research to compare Chi-Square feature selection with Mutual Information feature selection based on computation time and classification accuracy. In this research, people's comments on Twitter are classified based on positive, negative, and neutral sentiments using the Support Vector Machine method. Sentiment classification has the disadvantage that it has many features that are used, therefore feature selection is needed to optimize a sentiment classification performance. Chi-square feature selection and mutual information feature selection are feature selections that both can improve the accuracy of sentiment classification. How to collect the data on twitter taken using the IDE application from python. The results of this study indicate that sentiment classification using Chi-Square feature selection produces a computation time of 0.4375 seconds with an accuracy of 78% while sentiment classification using Mutual Information feature selection produces an accuracy of 80% with a required computation time of 252.75 seconds. So that the conclusion are obtained based on the computational time aspect, the Chi-Square feature selection is superior to the Mutual Information feature selection, while based on the classification accuracy aspect, the Mutual Information feature selection is more accurate than the Chi-Square feature selection. The recommendations for further research can use mutual information feature selection to get high accuracy results on sentiment classification