>Rob LeGrand recently experimented with simulations of repeated Approval >balloting. He did both cumulative and non-cumulative versions. He found >that when there is a CW, the non-cumulative version homes in on it quicker >than the cumulative version, but they both eventually reach it. When >there is no CW, then the cumulative version tends to give better results.
Why not split the difference and put in a decay function? The votes still accumulate from round to round, but the weight of old votes slowly declines, and reaches zero after some number of rounds. The larger this number is, the more stable your result is, but potentially the longer it takes to reach it. -Adam
