 # Confidence Intervals for the Erlang Distribution

Initializing live version Requires a Wolfram Notebook System

Interact on desktop, mobile and cloud with the free Wolfram Player or other Wolfram Language products.

This Demonstration shows confidence intervals obtained by simulation for the parameter in an probability distribution.

[more]

The probability distribution is defined as the distribution of the sum of k independent and identically distributed random variables , each distributed as (in Mathematica, ExponentialDistribution[λ]). In this case, the sum is sufficient to determine , that is, it contains all the information needed to compute any estimate of the parameter . In this Demonstration, the Clopper–Pearson method [2, 3] is used to produce interval estimates for , assuming a fixed sample size of 100, and their behavior is shown experimentally using simulation to produce random intervals. In this manner it may be seen that the method behaves rather well, since the relative frequency of the generated intervals that contain the true value of the parameter is very close to (and often higher than) the theoretical confidence level. Three different values (0.25, 0.45 and 0.65) are used for the experiment.

[less]

Contributed by: Tomas Garza (February 2020)
Open content licensed under CC BY-NC-SA

## Snapshots   ## Details

References

 Wikipedia. "Sufficient Statistic." (Feb 21, 2020) en.wikipedia.org/wiki/Sufficient_statistic.

 Wikipedia. "Binomial Proportion Confidence Interval." (Feb 21, 2020) en.wikipedia.org/wiki/Binomial_proportion_confidence_interval.

 L. D. Brown, T. Cai and A. DasGupta, "Interval Estimation in Exponential Families," Statistica Sinica, 13, 2003 pp. 19–49. www3.stat.sinica.edu.tw/statistica/oldpdf/A13n12.pdf.

## Permanent Citation

Tomas Garza

 Feedback (field required) Email (field required) Name Occupation Organization Note: Your message & contact information may be shared with the author of any specific Demonstration for which you give feedback. Send