The Impute Missing Genotypes process imputes numeric missing marker genotypes (

0, 1, or

2) for diploid organisms using the

k-nearest neighbor imputation (

kNNi) or the linkage disequilibrium

k-nearest neighbor imputation (

LD-kNNi) methods

^{1}. LD between markers is computed (using the SAS PROC ALLELE), distances between samples are computed (using the SAS PROC DISTANCE), and

k-nearest neighbor samples is computed (using the SAS PROC MODECLUS)

^{2}.

One SAS data set is required: An input data set with one column per each numeric coded marker (0 for the homozygous major allele,

1 for the heterozygous, and

2 for the homozygous minor allele).

Output from this process is accessed from a Results window. Refer to the

Impute Missing Genotypes output documentation for detailed descriptions and guides to interpreting your results.