Let's be a little more specific. The regression line smooths things out (as it is designed to do), but note the change in the dots, the individual survey results. The biggest lurch in support over the course of the two year campaign occurs for Obama just after Edwards dropped out (when pollsters stopped including his name on vote preference questions). Just before the Edwards announcement, most polls showed Obama's support in the mid-30s. Just after, his support surged the mid-40s. Over the same period, Hillary Clinton's aggregate support held mostly steady.

Before Iowa? - Just after Penn's speculation about Iowa appeared, Tom Beaumont of the Des Moines Register produced results from the second choice question on the final Register survey conducted by pollster Ann Selzer:

The Des Moines Register's Iowa Poll, taken in the closing days of the caucus campaign, showed that in fact Obama was the second choice of more Edwards supporters than Clinton was. The numbers? Among Edwards' supporters, 41 percent said Obama was their second choice, compared to 25 percent who said Clinton was their second choice.

Since Penn's speculation was more about how the long Iowa campaign would have transpired had Edwards dropped out at the very outset (rather than in its final days), I asked Selzer about their earlier poll conducted in May 2007. The survey showed a very close race: Edwards ahead with 29% followed by Obama at 23% and Clinton at 21%. But had Edwards not been a candidate, his supporters would have split decisively for Obama. With the second choices recalculated into the total, Obama would have led Clinton by nine percentage points on that first Iowa poll.

Before New Hampshire? - Probably the least plausible hypothetical involves Edwards dropping just after Iowa and before the New Hampshire primary. But if he had, what might have become of the 17% of the New Hampshire vote he received? Of the four polls that provided raw, respondent level data to the Roper Archives, only the Fox News poll included a second choice question. Those who said they were supporting John Edwards on the final survey (n=94, conducted January 4-6, 2008) reported their second choices as follows: Obama 38%, Clinton 14%, Richardson 13%, Kucinich 4% with the rest choosing another candidate or unable to provide a second choice. Yes, that final round of New Hampshire polling notoriously understated Clinton's support, but this result is not exactly strong evidence that Edwards was "draining" more support from Clinton than Obama.