پیش‌بینی الگوهای حکمرانی و توسعه: رویکردی ترکیبی مبتنی بر خوشه‌بندی و رگرسیون لجستیک چندگانه با استفاده از شاخص‌های توسعه انسانی و ادراک فساد

The present study examines global and regional patterns of governance and development, with a focus on the interaction between two key indicators: the Human Development Index and the Corruption Perceptions Index. While the inverse relationship between these two indicators has been confirmed in many previous studies, most of them have relied on traditional correlation and regression analyses and have shown shortcomings in predicting the position of countries. To address this gap, this study employs a two-step analytical framework. In the first step, using the k-means clustering algorithm, countries are classified into four distinct clusters based on similarity in the mentioned indicators, which represent different patterns in the state of governance and development among these countries. In the second step, a multinomial logistic regression model is developed to predict the probability of countries belonging to each of the clusters based on the numerical values of the Human Development Index and the Corruption Perceptions Index. The findings indicate that the Human Development Index has a stronger predictive role compared to the Corruption Perceptions Index, such that an increase in this index significantly raises the probability of countries belonging to clusters with higher development and transparency. In contrast, the Corruption Perceptions Index alone does not possess significant predictive power. The high explanatory power of the model, with a coefficient of determination equal to 0.984, confirms its validity in analyzing the cluster structure. These results have important policy implications and emphasize the strategic necessity of focusing on human development as a more effective lever in improving governance compared to merely anti-corruption policies. The combination of cluster analysis and predictive modeling in this study provides an innovative, data-driven tool for comparative analysis and the design of policy scenarios.