This method produces almost instantaneous results with reasonable accuracy for more than 10 failures. This method assumes B-lives for input percentages are normally distributed. For example, B10 is the point where 10% of the population is expected to fail. This method produces full plot (extrapolated) bounds.

This method is accurate for more than 30 failures and is useful for MLE analysis with suspensions. It produces full plot (extrapolated) bounds.

This method evaluates each failure occurrence. While this method is available when calculating confidence bounds for a data set, it is unavailable when calculating confidence bounds in the Summary Calculator. For more information, see Summary Calculator. You can use this method only to analyze each data point in the data set. When you use it for this purpose, the binomial method gives more conservative results than the modified Fisher matrix method; however, it requires more calculation time.