"This study applies advanced statistical methods to support regional planning by comparing the performance of logistic regression and artificial neural networks in classifying observations related to the key factors influencing household income in the city of Baghdad. By accurately identifying these factors, the study provides data-driven insights that can guide effective policy-making, promote equitable resource allocation, and strengthen the foundations of sustainable regional development. “It is worth mentioning that, the logistic regression model is one of statistical models that used when the dependent variable is a dichotomous or polychotomous. It is a special case of linear regression model, and hence restrictively relevant in the sense that results obtained from it may be useless if linearity does not hold. On the other hand, "Artificial Neural networks" is a method of analysis based on both linear and non-linear relationships, which makes it more relevant in such circumstances. This study presents a real life application of these two methods in order to compare the performance of the two models.
Hamid, Al-A. A. (2013). "Introduction to Artificial Neural Networks and Their Applications in Social Sciences Using SPSS," Baghdad University, Institute of Statistical Studies and Research, Department of Biostatistics and Population Statistics.
Bassam, Al-G. H. (2004). "Using Financial Ratios to Predict Corporate Distress," Master's Thesis, Gaza Islamic University.
Al-Mutawa, B. M., Al-Aqil, A. H. (1996). "Using Discriminant Analysis and Neural Networks to Predict the Degree of Banking Client Reliability," Arab Journal of Administrative Sciences, Kuwait, Volume (3), Issue (2), pp: 315-295.
Naji, J. H. (2010). "Comparing Methods of Estimating Economic Functions with Qualitative Dependent Variables," Iraq, Tikrit Journal of Administrative and Economic Sciences, Volume (6), Issue (18).
Risan, D. T. (2008). "Using Neural Networks for Discrimination Purposes," Al-Qadisiyah University, College of Management and Economics, Department of Statistics, Volume (52/14), pp: 246 - 256.
Denosern, R. D. (1997) - Translated by Abdel Rahman Hamed Azam, "Multivariate Statistical Analysis from an Applied Perspective," Dar Al-Merikh Publishing, Riyadh.
Aal, A., Ahmed, M. M. (2004). "Neural Networks and Business Management Applications," Baghdad, Scientific Journal of Economics and Commerce, Issue 1, pp: 465 - 494.
Qader, A. A. (2004). "Modern Econometrics between Theory and Practice," Al-Dar Al-Jami'iya for Publishing and Distribution, Alexandria, Egypt.
Adam, A. F. (2016). "Using Linear Discriminant Function to Identify the Most Important Economic and Social Factors Affecting Household Income Sufficiency in North Kordofan State," Master's Thesis, College of Sciences, Sudan University of Science and Technology.
Zaki, I. A. (2000). "Neural Networks - Engineering Structure, Algorithms, and Applications," First Edition, Shuaa Publishing and Science, Syria, Aleppo.
Al-Jaouni, G. A. F. (2011). "Using Binary Logistic Regression in Studying the Most Important Economic and Social Determinants of Household Income Sufficiency - An Empirical Study on a Random Sample of Households in Damascus Governorate," Syria, Damascus University Journal of Economic and Legal Sciences, Volume (27), Issue 1.
Al-Jaouni, G. A. F. (2007). "Multivariate Statistical Analysis (Discriminant Analysis) in Describing and Distributing Households within the Socio-Economic Structure of Society," Syria, Damascus University Journal of Economic and Legal Sciences, Volume (23), Issue 2.
Al-Taher, N. A. (2015). "Classification and Analysis of Income Categories in Sudan Using Discriminant Function Compared to Neural Network Models," PhD Thesis, Sudan University of Science and Technology, Graduate College.
Central Agency for Public Mobilization and Statistics. (2016). "Annual Statistical Book."
Central Agency for Public Mobilization and Statistics. (2016). "Results of the Income, Expenditure, and Consumption Survey."
Bandy, H. (1994). "Thoughts on Desirable Features for a neural Network - Based Financial Trading System", NUROVST Journal, 2(3): 19-22
-Hosmer, W. & Lemeshow, S. (2000). "Applied Logistic Regression", 2nd edition New York: Johnson Wiley & Sons, Inc.
King, J. E. (2002). "Logistic Regression: Going beyond point-and-click", Paper Presented at the annual Meeting of the American Educational Research Association, New Orleans, LA, April.
King, J. E. (2003). "Running A Best-Subsets Logistic Regression: An Alternative to Stepwise Methods", Educational and Psychological Measurement, Vol. 63, No. 3, June, 392-403.
Krose, B. & Smagt, P. (1996), "An introduction to neural networks", Eighth edition, The University of Amsterdam.
Lea, S. (1997). "Multivariate Analysis II: Manifest Variables analysis Topic 4: Logistic Regression and Discriminant Analysis", University of EXETER Department of Psychology Available at: www.exeter. Ac.uk/_SEGL ea./multivar2/diclogi.htm1
Lea, S. (2004). "Application of Likelihood ratio and Logistic Regression models to Landslide susceptibility mapping using GLS". Environmental Management, Vol. 34, No. 2, 223-232
Menard, S. W. (2002). "applied Logistic Regression analysis", 2nd edition Sage Publication Series Quantitative Application in the Social Sciences, No. 106, Thousand Oaks, CA: Sage.
Pample, F. (2000). " Logistic Regression a Primer". Sage Publication Series Quantitative Application in the Social Sciences, No.07- 132, Thousand Oaks, CA: Sage.
Rahman, A. (2009)."statistical Analysis of the Different Socioeconomic Factors Affecting the Education of N.W.F.P (PAKISTAN), "PhD, Institute of Mathematical methods in Economic (EOS), University of Technolgy Vienna, Austria, Journal of Applied Quantitative Methods, Vol (4), No (1).
Tang, M. (2001). "Exact Goodness of Fit test for Binary Logistic Model". Statistica Sinica (11), The Chinese University of Hong Kong.
Yoon, Y., Swales, G. (1993). "A Comparison of Discriminant Analysis Versus Artificial Neural Network", Journal of Operational Research, 44: 51-60.
Munther, S. S. (2025). Using Applied Statistics to Support Regional Planning: Statistical Approaches to Data Prediction: From Traditional Models to Modern Techniques in Analyzing Key Drivers (Household Income in Baghdad (. International Journal of Academic Research in Business and Social Sciences, 15(5), 860–879.
Copyright: © 2025 The Author(s)
Published by Knowledge Words Publications (www.kwpublications.com)
This article is published under the Creative Commons Attribution (CC BY 4.0) license. Anyone may reproduce, distribute, translate and create derivative works of this article (for both commercial and non-commercial purposes), subject to full attribution to the original publication and authors. The full terms of this license may be seen at: http://creativecommons.org/licences/by/4.0/legalcode
