Bugfix: adding rounding to calculation of unspecified sample size

[skirmer]

A proposed solution to #746. I ran tests like this to confirm it works across expected values:

for i in np.arange(0.01, 1.0, 0.0001):
    print(round(1-i, 6))

[jsignell]

This seems like a fine and concise solution to me.

[hristog]

Perhaps, the number 6 could be promoted to a named variable to avoid copy-and-paste bugs upon possible updates to this.

Also, I think for some users, the value 6 wouldn't be as effective, as it would for others. Perhaps, this warrants a consideration for introducing a configurable parameter. If such parameter is absent, some default value (eg, 6, as it has been the choice here) could be used as a fallback.