Weighted local least squares imputation method for missing value estimation

Abstract

Missing values often exist in the data of gene expression microarray experiments. A number of methods such as the Row Average (RA) method, KNNimpute algorithm and SVDimpute algorithm have been proposed to estimate the missing values. Recently, Kim et al. proposed a Local Least Squares Imputation (LLSI) method for estimating the missing values. In this paper, we propose a Weighted Local Least Square Imputation (WLLSI) method for missing values estimation. WLLSI allows training on the weighting and therefore can take advantage of both the LLSI method and the RA method. Numerical results on both synthetic data and real microarray data are given to demonstrate the effectiveness of our proposed method. The imputation methods are then applied to a breast cancer dataset.