Introducing Guesstimate, a Spreadsheet for Things That Aren’t Certain
Ozzie Gooen
1.3K34

Are you assuming a normal distribution for the cells with the confidence limits at roughly +/-2 sigma? Perhaps there should be a caveat that a Monte Carlo analysis done in this way cannot handle exceptional events with very large implications for the output, and that not all distributions are normal. There are many use cases where this is not a problem, but a lot of “interesting” problems have skewed distributions or far outlier values.

Show your support

Clapping shows how much you appreciated M Bacon’s story.