A comparison between classification statistical models and neural networks with application on palestine data /
Abdallah Salman Mohammed Aldirawi
A comparison between classification statistical models and neural networks with application on palestine data / مقارنة بين نماذج التصنيف الإحصائية والشبكات العصبية مع التطبيق على بيانات من فلسطين Abdallah Salman Mohammed Aldirawi ; Supervised Amani Moussa Mohamed , Mahmoud A. Abdelfattah - Cairo : Abdallah Salman Mohammed Aldirawi , 2021 - 125 Leaves : charts ; 30cm
Thesis (Ph.D.) - Cairo University - Faculty of Graduate Studies for Statistical Research - Department of Statistics and Econometrics
This study aims at choosing the best statistical model for Labor Force data in Palestine in 2019, comparing between Multinomial Logistic Regression, Discriminant Analysis and Artificial Neural Networks. The Palestinian Labor Force data has 12 variables with manpower as the dependent variable containing three categories of Employment, Unemployment, and Outside of labor force.The other 11 are all nominal independent variables with the exception of age which is a scale variable. The results of these comparisons have shown that Multinomial Logistic Regression gave the best accuracy in prediction with (82.2%), (79.2%) for Discriminant Analysis and (81.6%) for Artificial Neural Networks. Labor Force data from a survey on Labor Force data with 9 variables have further been used, the dependent variable being nominal with two categories (Employed and Unemployed) while the other 8 independent variables are all nominal except, age variable.The results of these comparisons have shown that Artificial Neural Networks gave the best accuracy in prediction with (82.7%), (81.6%) for Logistic Regression and (79.5%) Discriminant Analysis
Artificial Neural Networks Discriminant Analysis Multinomial Logistic Regression
A comparison between classification statistical models and neural networks with application on palestine data / مقارنة بين نماذج التصنيف الإحصائية والشبكات العصبية مع التطبيق على بيانات من فلسطين Abdallah Salman Mohammed Aldirawi ; Supervised Amani Moussa Mohamed , Mahmoud A. Abdelfattah - Cairo : Abdallah Salman Mohammed Aldirawi , 2021 - 125 Leaves : charts ; 30cm
Thesis (Ph.D.) - Cairo University - Faculty of Graduate Studies for Statistical Research - Department of Statistics and Econometrics
This study aims at choosing the best statistical model for Labor Force data in Palestine in 2019, comparing between Multinomial Logistic Regression, Discriminant Analysis and Artificial Neural Networks. The Palestinian Labor Force data has 12 variables with manpower as the dependent variable containing three categories of Employment, Unemployment, and Outside of labor force.The other 11 are all nominal independent variables with the exception of age which is a scale variable. The results of these comparisons have shown that Multinomial Logistic Regression gave the best accuracy in prediction with (82.2%), (79.2%) for Discriminant Analysis and (81.6%) for Artificial Neural Networks. Labor Force data from a survey on Labor Force data with 9 variables have further been used, the dependent variable being nominal with two categories (Employed and Unemployed) while the other 8 independent variables are all nominal except, age variable.The results of these comparisons have shown that Artificial Neural Networks gave the best accuracy in prediction with (82.7%), (81.6%) for Logistic Regression and (79.5%) Discriminant Analysis
Artificial Neural Networks Discriminant Analysis Multinomial Logistic Regression