Evaluation of decision making support models for managing re-equipping fire truck park using statistical testing method

Abstract

Purpose. The article examines the possibility of applying the statistical testing method to evaluate the effectiveness of decision making support models for distributing fire trucks among territorial fire and rescue garrisons. Based on previously developed criteria of operational readiness, technical readiness, and modern equipment availability, a probabilistic approach to analyzing the stability of management decisions is proposed. A numerical example of ranking garrisons with assessment of confidence intervals and probabilities of making correct decisions is provided. Methods. The methodology is based on the statistical testing method, which accounts for the probabilistic nature of initial data. The study includes a mathematical apparatus of simulation modeling — generation of random variables with specified distribution laws (normal, exponential, Erlang), procedures for multi-criteria optimization using the Cobb–Douglas function, and subsequent statistical processing of results to construct confidence intervals and estimate probabilities. Findings. As a result of the modeling, probabilistic estimates of ranking five garrisons using two-criteria and three-criteria models were obtained. It was established that the three-criteria model, which accounts for modern equipment availability, provides greater stability to variations in input data and a lower probability of error. Confidence intervals for criterion values and probabilities of objects falling into priority groups (“red,” “yellow,” "green") were determined. The Kendall concordance coefficient was calculated, amounting to W2 = 0.83 for the two-criteria model and W3 = 0.91 for the three-criteria model, indicating high ranking consistency. Research application field. The proposed methodology is intended for use in the logistics system of EMERCOM of Russia. The results can be used by decision-makers to improve justifiability and reduce risks when distributing limited resources (fire trucks) among territorial fire and rescue garrisons under conditions of data uncertainty. Conclusions. The application of the statistical testing method has proven effective for comparative analysis of decision support models under uncertainty. The three-criteria model is recognized as more preferable for practical use, as it reduces the risk of erroneous classification of garrisons and provides more stable ranking.