DNA microarray usage in genetics is rapidly proliferating, generating huge amount of data. It is estimated that around 5-20% of measurements do not succeed, leading to missing values in the data destined for further analysis. Missing values in further microarray analysis lead to low reliability, therefore there is a need for effective and efficient methods of missing values estimation. This report presents a method for estimating missing values in SNP Microarrays using k-Nearest Neighbors among similar individuals. Usage of preliminary imputation is proposed and discussed. It is shown that introduction of multiple passes of kNN improves quality of missing value estimation.