Imputation Methods: An Overview

Imputation involves replacing an incomplete observation with complete information based on an estimate of the actual value of the unobserved variable using any spatial or temporal interpolation method. This chapter provides a general overview of methodologies that can be used to imputation missing data. Li and Heap (A review of spatial interpolation methods for environmental scientists. Geoscience Australia, Record 2008/23, 137 pp 2008) have classified spatial interpolation methods into three categories: (1) non-geostatistical methods, (2) geostatistical methods, and (3) combined methods. Other methods include temporal interpolation, universal function approximation, and machine learning-based methods.