Examining the Robustness of the HeckCOMPoisson Model in Quantifying EACC's Effectiveness on Bribery Reduction

@article{1707201,
      author = {Dr. Leonard Thuo},
      title = {Examining the Robustness of the HeckCOMPoisson Model in Quantifying EACC's Effectiveness on Bribery Reduction},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {8},
      pages = {371-380},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1707201.pdf},
      abstract = {This study evaluates the robustness of the Heckman-Conway-Maxwell-Poisson (HeckCOMPoisson) model in analyzing the effectiveness of Kenya's Ethics and Anti-Corruption Commission (EACC) on bribery reduction. The HeckCOMPoisson model, which integrates the Heckman and Conway-Maxwell-Poisson models, was specifically developed to handle count data with selection bias. Using EACC's 2019 corruption data, we assessed the model's capability to accurately predict and quantify bribery incidents while accounting for the EACC's intervention efforts. Corruption remains a critical societal challenge that undermines democratic progress through various negative socioeconomic impacts. Through extensive statistical analysis, including summary statistics and graphical representations, our results demonstrated the HeckCOMPoisson model's excellent performance in terms of Goodness-of-Fit (GOF) and its ability to predict count data with selection while effectively handling both under-dispersion and over-dispersion. The findings confirm that the HeckCOMPoisson distribution provides robust modeling for dispersed counts in corruption analysis. By parameterizing HeckCOMPoisson distributions through mean, variance, and model prediction, this study establishes the model's comparability with other count models in terms of interpretability and parsimony, particularly in evaluating anti-corruption initiatives' effectiveness.},
      keywords = {Corruption, HeckCOMPoisson},
      month = {February},
  }