Analysis by data mining methods of relationships among egg quality characteristics in Japanese quails [Bıldırcınlarda yumurta kalite özellikleri arasındaki ilişkilerin veri madenciliği yöntemleri ile incelenmesi]

Abstract

This study examined the relationships between some egg quality characteristics in quails (shape index, shell thickness, shell weight, egg white index, egg white height, yolk index, yolk height and Haugh unit) and the yolk and white weights of eggs by using the CHAID (Chi-Squared Automatic Interaction Detection), Extended CHAID and CART (Classification and Regression Trees) algorithms. The CHAID, Extended CHAID and CART algorithms have significant advantages as they do not require assumptions such as normality, linearity and homogeneity. The methods were compared by using the criteria of coefficient of determination (R2), adjusted coefficient of determination (R2) and Root Mean Square Error (RMSE). As a result, the most suitable method for determining the egg quality characteristics that are effective on the yolk weight of eggs was found to be the CHAID algorithm. With this method, the highest yolk weight was obtained from the group where egg weight was higher than 13.36 g, and the shape index was higher than 0.895. For determining the quality characteristics that affect egg white weight, the most suitable method was found to be the CART algorithm. With this method, the highest egg white weight was obtained from the group where egg weight was higher than 12.47 g, the egg white index was 0.326, and the shape index was 0.865. © 2019, Centenary University. All rights reserved.