An Exponential-Cum-Sine-Type Hybrid Imputation Technique for Missing Data.

Area of Science:

• Statistics
• Survey Methodology
• Data Science

Background:

• Missing data is a common challenge in surveys, potentially biasing results.
• Accurate estimation of population parameters is crucial for reliable survey analysis.

Purpose of the Study:

• To introduce a new exponential-cum-sine-type hybrid imputation technique.
• To evaluate the bias and mean square errors of the proposed point estimator for population mean.

Main Methods:

• Developing a novel hybrid imputation technique.
• Analyzing the statistical properties (bias, MSE) of the estimator.
• Conducting simulation studies with Normal, Poisson, and Gamma distributions.

Main Results:

• The proposed imputation technique demonstrated competitive performance.
• The estimator's properties were evaluated against established methods.
• Simulation results provide insights into the estimator's effectiveness across different data distributions.

Conclusions:

• The new hybrid imputation technique offers a viable solution for handling missing survey data.
• The proposed estimator shows potential for real-life applications in survey analysis.