Analysis of Adaptive Approach Through Statistical Trends and Measures of Central Tendency

Incomplete data can greatly hinder the effectiveness of data-driven decision-making. When values are missing at random, accurately filling these gaps presents a key challenge in data mining. This research introduces a method called local-average Computation method, designed to reconstruct incomplete datasets by utilizing balanced information from the local data context. The approach calculates missing values based on the averaged input from nearby data points, maintaining both symmetry and numerical consistency. The technique was tested on five real-world datasets, showing that the imputed values closely align with the statistical properties of the original data, with only minor differences. Statistical tests, including ANOVA and covariance analysis, confirmed that there is no significant deviation between the original and imputed datasets, validating the method's accuracy and robustness.