Have an idea?

Visit Sawtooth Software Feedback to share your ideas on how we can improve our products.

rfc with same products

when I add in a rfc simulation the same product one would expect that the sum of the two products would be the SoC of the single product before.

If that is not the case, what could be the reason?
asked Oct 4, 2012 by anonymous
retagged Apr 21, 2014 by Walter Williams
could you be more specific about your simulation scenarios and scale of share inflation you encountered?
I've just checked on one of my projects and obtained very small inflation of shares for 4 identical products. As far as I remember RFC is share of preferences method with sampled FC as input for preferences so you certainly will encounter inflation adding more identical products, thou it should be negligible from practical standpoint. A size of this inflation depends on number of attributes you have with correlated errors - if you exclude some inflation is grater. In fact it could be very large if you exclude many attributes.

2 Answers

0 votes
I believe the reason lies with the fact that you are adding another player to a 100% universe, thus changing the game
answered Oct 4, 2012 by Bahadir Ozkurt Gold (16,980 points)
hmm..the help section about  Randomized First Choice it sais it would be the same...
0 votes
Double check your Method Settings in the simulator. If correlated error is being applied to all attributes and the product variability is zero then you should see share splitting. A higher product variability results in share inflation where the two similar products start stealing share from other products rather than just splitting the share of the original product.
answered Oct 4, 2012 by Jeff Forkner Bronze (2,875 points)