Mathematics
6 years ago

New Estimator Outperforms Competitors in Handling Missing Data for Accurate Analysis

International journal of statistics and applications
Comparison of Shrinkage–Based Estimators in the Presence of Missing Data: A Multiple Imputation Analysis
M. T. Nwakuya, JC Nwabueze

Paper Summary

The study compared different ways to estimate missing data in scientific research. They looked at four methods and found that the Adjusted Minimum Mean Square Error estimator performed the best in terms of accuracy. This means that when data is missing, using this method can give more reliable results.

Related papers

Theme background image
Mathematics
4 years ago

New Estimators Outperform Traditional Methods in Regression Model MSE Performance.

Missing Data
Regularization Methods
1 view
Theme background image
Mathematics
8 years ago

New estimator reduces errors in multivariate linear models for better predictions.

Multicollinearity
Dimensionality Reduction
Chemometrics
1 view
Theme background image
Mathematics
8 years ago

New biased regression estimator outperforms least squares in error comparisons.

Multicollinearity
Regularization Methods
System Identification
1 view