Political conventions focus public attention on presidential politics like few other events. So it's not surprising that these quadrennial confabs also can produce significant movement in public opinion. Political scientist Tom Holbrook provides a useful history of convention bounces in this blog post.
A few notable points. First, all conventions are not "bounce"-producing events. But conventions can help candidates lagging in the pre-convention polls (such as Goldwater in 1964 or Gore in 2000) catch up. These bigger surges tend to occur when a candidate is underperforming in pre-election polls.
His research also suggests Obama may emerge with a larger bump. That's because the candidate with the earlier convention usually gets a bigger bounce:
The earliest convention tends to get a bigger bump, and there is some evidence that going appreciably earlier exacerbates this effect. One reason for this is that the first convention is held by the out-party, whose candidate [is] generally less familiar to the general public. Another possible reason is that opinions are generally less well-formed early in the campaign and may be more easily shaped by the first convention. In the data presented above, the first convention bump was the larger than the second in seven election cycles, smaller in three (1988, 200, 2004), and essentially tied in one (1980).
So, will a bigger Obama bounce prove fatal to McCain? Not necessarily. Holbrook has this caveat.
It should be clear that the magnitude of the convention bump is not a great predictor of election outcomes. For instance, Goldwater got a huge bump and went on to a miserable defeat, Nixon got a huge bump and narrowly won in 1968, and Reagan got a very small bump and still won the 1984 election by a wide margin. My sense is that the size of the bump doesn't matter so much as whether the candidate gets the bump he is expected to get.