Monthly Archives: July 2016

Palisade @Risk7 RiskPERT comparison

On the first worksheet of the SPERT-Beta download (for version 0.2, Build 2), I’ve added a worksheet that does a comparison of nine different, right-skewed uncertainties.  The skewing ranges from mild to severe.  What I wanted to learn is how this version of SPERT-Beta compares with a Monte Carlo simulation of Palisade’s @Risk7 using the RiskPERT function in that add-in program.

I compared both SPERT-Beta and the SPERT-Normal edition (which uses the normal distribution), which is the original edition of Statistical PERT, already released and available for download and use.

I used two different subjective opinions within the SPERT worksheets.  For SPERT-Beta, I chose High Confidence and Medium-High Confidence in the most likely outcome.  For SPERT-Normal, I chose Medium and Medium-High Confidence in the most likely outcome.  These subjective choices approximate what a Monte Carlo simulation would give using the RiskPERT function in @Risk7.

You wouldn’t expect SPERT-Normal to give very similar results to RiskPERT since SPERT-Normal uses a symmetrical curve to model a asymmetrical uncertainties.  And yet, the results, even for severely skewed uncertainties, were not too far from the RiskPERT results.

I don’t recommend using SPERT-Normal for estimating uncertainties that are more than moderately skewed (to the left or right).  Using SPERT-Beta will give more accurate results in those cases because SPERT-Beta can build an implicit, skewed curve, whereas SPERT-Normal can’t.

New SPERT-Beta release for July 2016!

It’s been a long time since I played around with the next edition of Statistical PERT:  SPERT-Beta, which will use the beta distribution functions inside Microsoft Excel.

I’ve retooled the SPERT-Beta template so it’s simpler with fewer choices.  More importantly, I’ve changed the philosophy I used to create the initial SPERT-Beta template.  This new pre-release template of SPERT-Beta uses ratio scales that more accurately create a skewed probability curve, placing the most likely outcome — the mode — at or very near the top of the curve.  In my earlier version of SPERT-Beta, the mode was often nowhere near the top of the curve for many of the most likely confidence choices.  Now, choosing any of the most likely confidence choices will still place the mode in its proper place:  at the top of the mountain.

With this new version, choosing “Medium Confidence” in the most likely outcome will yield probabilistic results that closely mirror what you would get by running a Monte Carlo simulation using Palisade’s @Risk7 (specifically, the RiskPERT function).

I ran a comparison between SPERT-Beta and @Risk7’s RiskPERT, and the results were very often very close, even for skewed uncertainties.

As always, feel free to download and use, but be aware that this is a development version and may still contain serious flaws anywhere in the spreadsheet.