Weight adjustment using positive skew nature of blended small area on the neutrosopic perspective

The present study introduces a novel approach to blended small area estimation (SAE) by integrating reliable information from both real and simulated small areas. Operates within a neutrosophic framework, we explore some non-linear weight adjustments specifically designed using two-stage cluster sampling. The main contribution of this methodology successfully developed some flexible weighting techniques to address actual challenge posed by positively skewed nature. The proposed research utilizes a calibration method, leverages information across different blended small area timeframes under a neutrosophic perspective. For the purpose of this analysis, four blended small areas were framed according to meal intake intervals: breakfast, lunch, snacks, and dinner. The theoretical framework is validated with support of real-world data (Schwenck et al. Citation2022). Empirical results demonstrate that the proposed non-linear model-based logarithmic estimator consistently efficient over non-linear model-based Nguyen estimator and the linear design-based generalized regression (GREG) estimator in terms of efficiency across all blended areas.