I computed the mutual information matrix for syn.data using the Miller–Madow estimator (34) using the build.mim function in the minet R package .

data(syn.data) estimator = "mi.mm" mim <- build.mim(discretize(syn.data,"equalwidth",10), estimator)

why the mutual information >1

         CDC11      SWI4     CDC10     SPT16 SWI4_SWI6

CDC11 0.000000 1.5475858 1.5011079 0.4529100 1.5247844 SWI4 1.547586 0.0000000 1.5634253 0.5557569 1.6529561 CDC10 1.501108 1.5634253 0.0000000 0.5302061 1.4391632 SPT16 0.452910 0.5557569 0.5302061 0.0000000 0.5215617 SWI4_SWI6 1.524784 1.6529561 1.4391632 0.5215617 0.0000000