Notice that the attempt to remove crosstalk is only partly successful. Interestingly, unlike in Figure 1, the crosstalk retains its original polarity, because of the strong noise. Imagine that the noise dominated everything: then we would be minimizing something like .Assuming the noises were uncorrelated and sample sizes were infinite, then , and the best would be zero. In real life, samples have finite size, so noises are unlikely to be more than roughly orthogonal, and the predicted in the presence of strong noise is a small number of random polarity. Rerunning the program that produced Figure 3 with different random noise seeds produced results with significantly more and significantly less estimated crosstalk. The results are dominated more by the noise than the difference between and .More about random fluctuations with finite sample sizes will follow in chapter .