Comparison of Logistic Regression and Discriminant Analysis for Predicting Anemia Among Pregnant Women in Sana’a, Yemen
This study aimed to identify the primary factors influencing anemia among pregnant women and to compare then classification efficiency of Logistic Regression LR and Discriminant Analysis DA. The study utilized a random sample of (361) pregnant women visiting Al-Sabeen Hospital during the period (2023-2024). Independent variables included demographic characteristics, reproductive history, and health habits. Results indicated that nutritional Supplement Intake was the most influential predictor for classifying anemia in both models, followed by Body Missed Index BMI, Smoling, Age, Family size, N. of pregnancy, and N. of Births. Conversely, education level and household income showed no statistically significant impact. In terms of performance, LR demonstrated superior classification accuracy at 88.1%, compared to 86.9% for DA. These findings confirm the high predictive and discriminatory capacity of the models in identifying anemic cases within the clinical women.
Metrics
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
