equalizedPMFBreakPoints

This function is similar in purpose to the similarly named function in PDFModeler. The primary difference is that this function ensures that the returned break points are unique because a set of probability values may map to the same value for a discrete distribution.

Computes breakpoints for the distribution that ensures (approximately) that the expected number of observations within the intervals defined by the breakpoints will be equal. That is, the probability associated with each interval is roughly equal. In addition, the expected number of observations will be approximately greater than or equal to 5. There will be at least two breakpoints and thus at least 3 intervals defined by the breakpoints.

If the sample size sampleSize is less than 15, then the approximate expected number of observations within the intervals may not be greater than or equal to 5. Note that the returned break points do not consider the range of the CDF and may require end points to be added to the beginning or end of the array to adjust for the range of the CDF.

The returned break points are based on the natural domain of the implied CDF and do not account for any shift that may be needed during the modeling process.