This paper focuses on statistical independence of multiple variables from the viewpoint of linear algebra. While information granules of statistical independence of two variables can be viewed as determinants of 2 times 2- submatrices, those of three variables consist of several combination s of determinants. However, this combination can be viewed as a linear sum over the all combinarial pairs of 2times2 -matrix, where 2times2 matrix form can be viewed as a fundamental granule for statistical independence.