On the other hand, a confirmed Hindenburg Omen signal occurred on Jun 16th 2008, which would be a timely warning for the following events. On yet another hand, no word on how many such confirmed signals were false alarms historically.
Looking back at historical data, the probability of a move greater than 5% to the downside after a confirmed Hindenburg Omen was 77%, and usually takes place within the next forty-days. The probability of a panic sellout was 41% and the probability of a major stock market crash was 24%.
While the past performance is quite compelling, the criteria seem to be extremely arbitrary.
There's a table with all 22 confirmed signal clusters 1985-2005 and the following "crashes" along with their delays. Although the phrase "25% of these signals were followed by a market crash" is pretty impressive, when you look at the actual definitions of crash (>15% drop), and the delays (up to 4 months) it doesn't look as exciting anymore.