There were several good questions on today's analysis of Obama's minority turnout scenarios, so let me extract a couple of those here.
Q. I am curious why you use census estimates of turnout (which are self-reports) instead of exit poll estimates of turnout (which vary substantially across states). Might not matter much.
We played around with both, and we made a decision to use the Census Bureau numbers as those results have somewhat larger sample sizes in all but a couple of states. The self-reporting might be a bit of an issue, but then again, we've seen plenty of problems in the past couple of cycles with the way that exit polls determine their samples as well.
Q. The main problems I see with your analysis that should be considered is (1) white/Anglo counter-mobilization; and (2) diminishing returns. While the Republicans are unpopular now, the election will not occur in a vacuum, and there likely will be some countermobilization among whites and Anglos (everyone is energized now, and you are assuming the black + latino voters increase but not that white/Anglo turnout is higher). I could see this mattering in a state like Texas, which has a history of white countermobilization to increasing black registration.
I've actually seen some academic work that the presence of a black candidate on the ticket tends to increase black turnout -- but also tends to increase white turnout. So you may be on to something there. At the same time, the white conservative vote was pretty darn mobilized in 2004, and I'm not sure I see the same thing happening this year at a time when the incumbent, Republican president is extremely unpopular, and when John McCain is not particularly well liked by elements of that conservative base.
I still think the most instructive piece of evidence are the turnout figures from the Democratic primaries. Turnout among these groups has not just increased in absolute terms -- everyone's turnout has increased in absolute terms. It has also increased in relative terms; slightly so for black voters, and very substantially so for Latinos and young voters.
Q. Are there any newer estimates of population by race & ethnicity (w/ a voter screen) than 2004 CPS that would be helpful to estimate 08 turnout rates?
Yes, the Census Bureau puts out estimates of the racial composition of each state every year, but the differences only amount to a percentage point here and there. I think you guys may be overestimating the level of precision that I'm aiming for with this analysis. Unlike some of the other stuff I do here, this is not necessarily meant to be predictive. I'm not necessarily saying there will be big increases in turnout among these groups. Instead, it's meant to be illustrative of how the map would change if Obama did get higher turnout from these groups. The whole thing is kind of in the conditional tense.
Q. What accounts for black turnout decreasing in NY, MS, FL, CA, & OK between '04 and '08? Is it just population change?
It might just be random noise. However, in three of these states (NY, OK, FL), Obama made only a half-hearted effort to compete. In California, there was a huge surge in Latino turnout that swamped everything else. In Mississippi -- I'm not sure. Obama actually spent very little time on the ground there -- just a day of campaigning, I think -- and there was a pretty large Republican crossover vote.
Q. Do these estimates account for cases in which the young voter might also be African-American or Latino? In other words is there some double counting going on?
The double counting thing is definitely something I was aware of, but I'm not sure that there's an elegant solution. Certainly with the Latino vote, for instance, there is a fairly big generational divide. If Obama turns out younger Latinos, that vote might go for him 70:30 or 75:25, whereas for older Latinos, the vote will probably be closer to 50:50. Nevertheless, some sort of adjustment is probably warranted. But I stated above, this analysis is intended more to be descriptive than predictive.
Q: Poblano - your analysis is getting to be way way too biased and losing its usefulness - you have to realize that it is very difficult for a democrat to get more than 50% of the vote, it has not happened since 1976.
Sure, but look how the electorate has changed since then. In 1976, just 2 percent of the electorate was Latino. That number was 8 percent in 2004 and will probably be at least 10 percent in 2008. Just 27 percent were college graduates in 1976, versus 42 percent in 2004. There are some trends that tend to favor the Republicans too, like the population getting older.
Q. If this could be real, it has huge implications for Obama's strategy. Should he tack right or tack left for the general?
As I've written before, Obama has two fundamental ways he can win. First, he can attempt to unifty and turn out the Democratic base. If he does that, he'll win based on the Democrats' party identification advantage, unless he gets absolutely killed with independents. Secondly, he could write off certain of those Reagan/Clinton Democrats, and instead make more of an appeal to the sort of the libertarian-leaning investor class, which makes up a pretty high fraction of the independent voting pool. The former strategy -- consolidating Democrats -- is certainly less of an uphill climb. The more confident the Obama campaign is that it *can* achieve increases in turnout among traditionally Democratic-leaning groups, the more that looks like the right way to go.
Sunday, May 11, 2008
Q&A on Minority Turnout Model
Black, Youth and Latino Turnout, and Obama's Electoral Map
This analysis is prepared in conjunction with Progress Illinois, which has posted a separate article on the findings. The Progress Illinois blog is relatively new to the scene -- just as mine is. But it's extremely well designed and extremely well written, and I hope that you'll get in the habit of checking it regularly. Thanks to Josh and the rest of the gang for their assistance.
As the Democratic primaries come to their slow, if increasingly certain conclusion, the media narrative has tended to focus on the alleged inadequacies of each candidate: Hillary Clinton's lack of support among black voters, or Barack Obama's supposed inability to resonate with certain types of white voters. What has been lost, however, is a story that could turn out to have far more relevance for the general election campaign in the fall: the emergence of a "big tent" Democratic electorate that has increasingly begun to reflect the full diversity of America.
What follows is a table comparing the composition of the Democratic primary electorate in 21 states in which exit polling data is available in both 2004 and 2008. We focus on three particular groups: black voters, Latino voters, and young voters. As a fraction of the Democratic electorate, African-American turnout has increased from 19.8 percent to 21.5 percent -- a 7.8 percent increase. Latino turnout has increased from 5.3 percent to 7.5 percent -- a 41.9 percent increase. And turnout among voters aged 18-29 has increased from 9.0 percent to 13.7 percent -- a 52.4 percent increase.
Today, we will examine the effects that increased turnout among these groups might have on Barack Obama's general election prospects against John McCain.
African-American Turnout
It is something of a myth that African-American voters do not turn out to vote. In 2004, 87.4 percent of registered African-Americans cast a ballot in the Presidential election, according to statistics compiled by the US Census Bureau. This compares with 89.4 percent turnout among registered, non-Hispanic whites. However, voter registration rates lag somewhat behind in the African-American community. As of 2004, 68.7 percent of African-American citizens aged 18+ were registered to vote, as compared with 75.1 percent of non-Hispanic whites. Thus, Barack Obama's 50-state voter registration drive, when coupled with the historical nature of his candidacy, could produce big dividends within this group.
What would be the electoral impact of an increase in African-American participation of 10 percent, 20 percent, or more? Fortunately, we have the perfect tool to examine such scenarios in the form of the FiveThirtyEight.com polling averages and simulation engine. Suppose that we start with a baseline assumption wherein total turnout in each state is equal to what it was in 2004, and that this turnout is divided between John McCain and Barack Obama according to their present standing in the FiveThirtyEight.com polling averages. This is probably fairly close to what most pollsters are assuming, as they lean heavily on statistics from the previous elections in establishing their turnout models.
We can infer the number of African-American voters in each state based on Census Bureau Data. For example, in North Carolina in 2004, there were approximately 3.5 million votes cast in the general election, and the Census Bureau estimates that 21.5 percent of these were from African-Americans. This equals about 750,000 votes. So, a 10 percent increase in African-American turnout would represent 75,000 additional African-American votes, a 20 percent increase 150,000 votes, and so forth. We distribute 94 percent of these new votes to Barack Obama and 6 percent to John McCain, in accord with Obama's present advantage over McCain among black voters in recent polling. We then re-run our simulations with the new votes added in. Obama's results at various levels of turnout improvement are below.
For each 10 percent increase in African-American turnout, Obama gains approximately 13 electoral votes, and 1 percent in his popular vote margin against John McCain. Even a 10 percent increase is enough to take him from a slight underdog against McCain to a slight favorite, while at higher levels of turnout improvement, Obama becomes the strong favorite. Meanwhile, Obama's electoral map changes as follows:
Generally speaking, there are two regions where Obama stands to benefit from higher African-American turnout. The first is in the Rust Belt states of Ohio, Pennsylvania, Michigan, and perhaps Indiana. Although there are not enormous numbers of African-Americans in these states, there are certainly some, and given how closely these states have tended to poll, even fractional improvements in Obama's numbers could produce large dividends. The other area where Obama can gain is along the southern Atlantic coast. North Carolina and Virginia would potentially be extremely competitive with higher black turnout, and to a lesser extent so would South Carolina, Florida, and perhaps Georgia. Louisiana might also become viable, although states like Mississippi and Alabama are unlikely to be.
Youth Turnout
We can run through the same analysis for youth turnout. Specifically, we will be focusing on voters aged 18-24. Turnout in this group has tended to lag badly behind that of older voters. In 2004, for instance, 46.7 percent of citizens aged 18-24 turned out to vote, as compared with 63.8 percent of the electorate as a whole. But these voters have become very engaged by the 2008 campaign, and it is not difficult to imagine a turnout increase of 25 or even 50 percent.
Most polling has shown Obama with a 3:2 or 2:1 advantage over John McCain among voters in the 18-29 age range. We will assume that Obama's advantage is slightly larger toward the younger end of this range (18-24) and assign him 70 percent of the new votes, with the balance going to John McCain. The resulting scenarios are below:
Unlike the African-American vote, which tends to be concentrated in certain regions, there is not that much difference in the number of young voters from state to state. However, some areas do warrant a mention. There is a strong tradition of youth turnout in the Upper Midwest, which could help Obama to ensure victories in Minnesota, Wisconsin, and Iowa. Alaska is an extremely young state and could become a swing state with higher youth turnout. Texas and Georgia are also quite young and could become competitive with a strong youth turnout coupled with an improvement in Hispanic and black turnout, respectively.
Latino Turnout
Because Hillary Clinton has tended to do better with Latinos in the primaries, there is a perception that this group is not a strength of Barack Obama's. In fact, however, Obama held leads over John McCain by margins of 57-33 and 51-41 among Hispanic voters in recent sets of Gallup polling. Increasing the share of the electorate that is Latino would definitely be to Obama's benefit -- albeit not quite to the same extent of the other two groups. We will assume that Obama gets 60 percent of any new Latino votes, and John McCain the other 40 percent. As just 44.1 percent of adult Latino citizens turned out to vote in 2004, improvement within this group could be comparatively easy to achieve.
Obama's popular vote share increases only fractionally as a result of new Latino votes. However, these votes tend to be concentrated in electorally significant states. In particular, an increase in Latino turnout could all but assure an Obama victory in New Mexico, while also improving his chances in Colorado and Nevada.
Because they have polled so closely, this group of three states is among the most important in the country. Assume that Obama starts with the states that John Kerry won in 2004, plus Iowa where he is currently favored, but minus New Hampshire where he is currently the underdog. This gets him to 254 electoral votes, whereas he needs 270 to win. Winning those three states would get him to 273 electoral votes, just getting him over that threshold. In other words, if Obama wins these states, he would probably not need to carry Ohio or Florida to win the election.
Putting it Together
Finally, we can run a couple of scenarios that combine the effects of turnout improvements among these different groups. The first scenario is what I call the "40/20 Plan": increasing youth (18-24) turnout by 40 percent, and African-American turnout by 20 percent, but not focusing specifically on Latinos. The second is the "40/30/20 Plan": aiming for a 40 percent increase in youth turnout, a 30 percent increase in Latino turnout, and a 20 percent increase in African-American turnout. The last is what I'm simply calling the "Best Case Scenario". This would be a 50 percent increase in youth turnout, a 50 percent increase in Latino turnout, and a 40 percent increase in African-American turnout. Although this latter scenario is unlikely to develop, it should help to provide some context for where a strong ground game could make the most difference for Obama.
As you can see, these effects are quite powerful when combined. The 40/20 Plan would gain Obama about 48 electoral votes, and improve his win percentage to 68.3 percent. Adding Latinos to this plan would improve his win percentage further to 71.7 percent. And under his best case turnout scenario, Obama becomes a prohibitive favorite to win the election, as states like Texas and Georgia could turn blue.
The ability to bring new voters to the polls remains Barack Obama's most significant electoral advantage, both relative to Hillary Clinton and John McCain. Indeed, current polling may already be underestimating Obama's strength against McCain if it does not account for improved turnout among Democratic-leaning groups like young voters and African-Americans, who have participated in record numbers in this year's primaries. If Obama can parlay that advantage with a strong ground game, he very much could redraw the electoral map.
Tuesday, May 6, 2008
African-American turnout in North Carolina, Part II
As I noted earlier, the Public Policy Polling blog reports that African-Americans represented 32 percent of North Carolina's Democratic primary electorate in 2004. This figure undoubtedly plays a role in the fact that the vast majority of pollsters have settled on a number in the 32-33% range in forecasting black turnout time around. However, there are a couple of questions that we need to be asking about this approach.
Firstly, has African-American turnout increased as a share of the presidential primary electorate? The answer is that it has increased a little bit. Below is a table comparing the African-American turnout share in 2004 and 2008 in 19 states that (i) are at least 5 percent black, and (ii) have exit polling data available from the Democratic primary in both years.
African-American turnout improved in 13 of these 19 contests. The average African-American turnout in these states has been 24.7% this year, as compared with 22.7% in 2004; that represents an increase of 8.6%. If you took North Carolina's 2004 black turnout as a baseline and increased it by 8.6%, you would get to 35% -- which as it happens is the number that PPP eventually settled on.
However, there is one other problem with this. North Carolina held a Democratic primary in 2004. But it did not hold a Democratic Presidential primary. (Instead, it held a Presidential caucus, which John Edwards won even though he had long since dropped from the race). The primary was for its governorship and one of its Senate seats.
Do African-Americans turn out more for Presidential primaries than they do in non-Presidential years? The truth is that we just don't know because nobody bothers to do exit polling in primaries when there is no Presidential nomination to be had. However, we can perhaps draw an analogy by comparing African-American turnout in the 2004 general election with the 2006 midterms.
Below are all the states that held (i) a contested race for governor or Senate in 2006 and (ii) have an African-American population of at least five percent.
In 10 of the 19 states, African-American turnout constituted a smaller share of the electorate in 2006 than it did in 2004. It increased in six states, and was unchanged in three others. Overall, African-American turnout was 8.2% smaller as a share of the electorate.
So, if we were trying to form a turnout estimate for North Carolina based on its 32% black turnout in its 2004 primary, we might approach the problem as follows. First, increase that figure by 8.2% to account for the fact that North Carolina's 2004 primary was not for President, and African-American turnout appears to make up a a larger share of the electorate when there is a Presidential contest on the ballot. And second, increase that result by a further 8.6% to account for the fact that black turnout has increased this year as a share of the Presidential primary electorate. If you do those two things, you come up with an estimate in the range of 37-38%, which are the numbers I have been advocating for.
Monday, May 5, 2008
North Carolina Prediction: Obama by Double Digits
In Pennsylvania and Indiana, the previous times that we conducted this exercise, the results from our regression model were closely in line with the composite polling averages in those states. In North Carolina, however, while most polls show a tightening, single-digit race, our model steadfastly forecasts a solid, double-digit victory for Barack Obama.
If you'll recall, the way that I produce these projections is to rely purely on demographic data from previous primaries. So the unstated assumption is this: if voters in North Carolina behave like demographically-aligned voters in other states, this is about what we should expect. On the other hand, if something has changed in the way that some groups of voters view the candidates -- our model may be inaccurate.
There does appear to me to be some evidence that Hillary Clinton is overperforming the position she has generally held throughout most of the recent primaries. But there is also some strong evidence that the current polling in North Carolina may be understating Barack Obama's support in that state.
But let's set that discussion aside for a moment and first look at the model's projections on a Congressional District by Congressional District basis.
CD-1 (Northeast / Albermarle): Without meaning to sound reductionist, this is one distrct where you can pretty much tell who somebody is going to vote for when you see them walk through the door. Most voters will be African-American, as the black population exceeds 50 percent in the district. However, the white population is impoverished and tends to be fairly old. The delegate split will almost certainly be 4-2 in Obama's favor. Prediction: Obama 68.1, Clinton 31.9; Obama 4-2 Delegate Win.
CD-2 (East Central / Raleigh): The Congressional Districts in North Carolina tend to be a little amorphous, as the major cities are divided up between two or three CD's. CD-2 includes the Raleigh city center, but then spiders out into some of the poorer areas of the state. However, it's an equal opportunity kind of poor, as their are plenty of blacks, plenty of whites, and a decent number of Hispanics. It should be a safe Obama win, but it will be a close battle to see whether he can get 4 out of 6 delegates. The model notes that CD-2 is the youngest district in the state and the most male and gives him the delegate majority. Prediction: Obama 61.5, Clnton 38.5; Obama 4-2 Delegate Win.
CD-3 (East / Cape Hatteras): The North Carolina coastline tends to be rugged and difficult to navigate, so you do not have so many of the wealthy, resort-type towns like you get in SC-1. Nevertheless, the white population in NC-3 is far more middle-class than the two Inner Banks districts that we just finished describing, and the district tends young and male, which should help Obama to make up for a relatively small black population. Overall, it's one of the more heterogeneous regions in the state and should track the state's returns fairly closely. Heavily Republican area, so expect a low turnout. Prediction: Obama 56.3, Clinton 43.7; 2-2 Delegate Split.
CD-4 (Central / Research Triangle): Among the best educated districts in the country, but also having a decent-sized African-American population and lots of collegians, the rapidly-growing Research Triangle area around Durham and Chapel Hill is Obama's best opportunity to run up the score. The district has nine delegates and turnout should be in the 170,000 voter range; Obama will get the lion's share of both, but a 7-2 delegate split looks unlikely. Prediction: Obama 69.8, Clinton 30.2; Obama 6-3 Delegate Win.
CD-5 (Northwest / Boone): White and lower-middle class, this Appalachian region most certainly favors Clinton, but the demographics aren't nearly as extreme as the neighboring regions in Tennessee. I have a hunch that she'll outperform our popular vote projection, but Clinton has no realistic chance to hold Obama to fewer than two delegates. Prediction: Clinton 55.9, Obama 44.1; Clinton 3-2 Delegate Win.
CD-6 (Central / Asheboro): With otherwise average demographics but a black population below 10%, this district leans Clinton, but Obama could steal the odd-numbered delegate from her if he does well with unaffiliated voters, as this is the least Democratic district in the state. Prediction: Clinton 51.8, Obama 48.2; Clinton 3-2 Delegate Win.
CD-7 (Southeast / Wilmington): Once fairly rough and tumble, this is a rapidly-growing district that is beginning to look something like suburban Atlanta, with an emphasis on service-sector employment. It has a high enough black population to lean Obama, but with an even number of delegates, we are most likely looking at a split. Prediction: Obama 52.8, Clinton 47.2; 3-3 Delegate Split.
CD-8 (South Central / Kannapolis): With a 30% African-American population, Obama will almost certainly win CD-8, but the white population is relatively working-class. It should break down about 60:40, almost exactly in line with a 3-2 delegate split. Prediction: Obama 60.7, Clinton 39.3; Obama 3-2 Delegate Win.
CD-9 (Charlotte - Gastonia): CD-9 comprises the ritzy and professional suburban areas immediately south of Charlotte. That is a demographic that has favored Obama over the course of most of this primary season, but performed less well for him in Pennsylvania. The model is giving Obama a 4-2 delegate win on the strength of independent voters, but I'd feel a little more comfortable for him if the African-American population were slightly larger. Prediction: Obama 60.2, Clinton 39.8; Obama 4-2 Delegate Win.
CD-10 (West / Hickory): The demographics are nearly identical to CD-5, and so naturally our model expects a nearly identical result. Prediction: Clinton 55.6, Obama 44.4; Clinton 3-2 Delegate Win.
CD-11 (West / Asheville): Artsy and eccentric, the Asheville/Smoky Mountains area is different from anything else in the state. Although the black population is small, there would otherwise be enough of a latte liberal crowd to keep things fairly balanced, except for the fact that the high quality of life tends to attract a large retirement community. As such, Clinton is bound to win, and will be right on the brink of winning a 4-2 delegate split. Prediction: Clinton 57.6, Obama 42.4; 3-3 Delegate Split.
CD-12 (I-85 Corridor): This gerrymandered district hugs Interstate 85 and includes portions of Charlotte, High Point and Winston-Salem. It's predominately middle class, but nearly half the district is African-American, which heavily favors Obama. In fact, we have this as his best district in the state, with the voting margins lining up almost exactly with a 5-2 delegate win. Prediction: Obama 70.6, Clinton 29.4; Obama 5-2 Delegate Win.
CD 13 (North / Greensboro): The demographics here are similar to some of Obama's better districts in Virginia, with a mix of blacks and relatively well-educated whites in Greensboro and suburban Raleigh. On a good day, Obama is within reach of the 64.3% vote share he'd need to take a fifth delegate from this district. Prediction: Obama 63.4, Clinton 36.6; Obama 4-3 Delegate Win.
Statewide Results
(Note: Typographical error fixed in table -- statewide popular vote totals were neglecting to include CD-12 and CD-13).
The model expects Barack Obama to pick up 66 delegates to Clinton's 49. Relative to Indiana, the delegate situation is a little more fluid: we are very close to the delegate thresholds in CD-6, CD-9, CD-11 and CD-13, and a delegate could also easily change hands in CD-2.
However, at this point it's not the delegate math that counts so much as the margin of victory, and that's showing up impressively for Barack Obama: a 17-point win, which would net him approximately 150,000 in excess of 200,000 popular votes.
From a 30,000-foot level, it should not be so difficult to see how the model might come up with results like these. Obama won by 29 points in South Carolina and 28 points in Virginia, the two states that share a long border with North Carolina. Although North Carolina is somewhat whiter than South Carolina, and somewhat less wealthy than Virginia, this projection nevertheless looks perfectly reasonable next to those numbers.
And indeed, this projection did match the polling data until relatively recently. On April 22, the morning before the Pennsylvania primaries, Obama led Clinton 51-36 in the Real Clear Politics average in North Carolina, a 15-point margin that matches our regression output almost perfectly.
If North Carolina were North Dakota, I'd probably just caveat this as "Clinton may presently be outperforming her long-term demographic trends" and leave it at that. However, North Carolina is a Southern state -- and pollsters have had an awful lot of trouble polling the South. Let me bring up two interesting facts.
Interesting Fact #1: The polls have significantly underestimated Barack Obama's margin of victory in Southern states with substantial black populations.
That is a graph I drew up a few weeks ago comparing the actual results in a state to the final Pollster.com averages. As you can see, Obama outperformed his polling averages in almost all Southern states: by 3 points in Tennessee, 5 in Florida, 6 in Missouri, 9 in Mississippi, 11 in Virginia, 15 in Alabama, 18 in South Carolina, and 22 in Georgia (the only exception among Southern states that received widespread polling was in Texas). Moreover, the discrepancies appear to be related to the number of African-Americans in the population. In North Carolina, which is about 22 percent African-American, the regression line would forecast an underestimate of about 10 points. Add those 10 points to the 6- or 7-point lead that Obama presently holds in the North Carolina polling consensus -- and you get right to my model's estimate of a 17 point win.
Interesting Fact #2: Early voting data in North Carolina suggests that the pollsters may be significantly underestimating the proportion of African-Americans in the voting population.
As we discussed over the weekend, we have a unique wealth of data in North Carolina the likes of which I don't recall seeing ever having seen before. The state's Board of Elections has not only released the number of early voters, but also provided significant information about their demographics. According to the
The difference between these two estimates is significant. As you've probably found if you've played around with our North Carolina prediction tool, an increase of 1 percent in the fraction of the electorate that is African-American translates to roughly a 1-point increase in Barack Obama's margin over Hillary Clinton. So -- if the pollsters are assuming 33% black turnout when it will actually be 40%, that would add 7 points to Obama's margin -- putting us in the 13-14 point range, again fairly close to my model's estimates.
As Blumenthal notes, the Obama campaign has tended to place more of an emphasis on early voting -- and so it's possible that his voters are just getting to the polls sooner. On the other hand, studies in other states suggest that people who vote early tend to be of higher socioeconomic status -- whereas black voters as a group tend to be of lower socioeconomic status, particularly in a state like North Carolina. Moreover, 61% of the early voters are female, which is not typically an Obama demographic. (Although, there are a couple of alternate hypotheses for this: the black electorate tends to be disproportionately female, so this could be another reflection of the higher African-American turnout. Also, men tend to procrastinate.)
But fundamentally -- would 40% black turnout be a reasonable number in North Carolina? Or is it just completely out-of-bounds? The short answer is that yes, 40% is a perfectly defensible estimate -- and very probably a better estimate than 33%.
I had worked on this problem a little bit before, attempting to estimate African-American turnout as a proportion of the state's underlying African-American population. But I recognized that there is one alternate metric that might be helpful in this regard too: the proportion of a state's John Kerry voters who were African-American. This is reasonably easy to infer based on 2004 exit polling data.
Below are a set of statistics for each state that has held a primary so far and in which at least 5% of that state's population is African-American (I exclude the disputed contests in Florida and Michigan). This compares the size of the African-American electorate in the primary against (i) the percentage of African-Americans in that state's population, and (ii) the percentage of Kerry voters in that state who were African-American.
Note that in North Carolina, 52 percent of John Kerry's voters were African-American. While 40 percent black turnout sounds high compared to a 22 percent population baseline, it does not sound so high compared to this figure.
In fact, by running a simple regression model, we can come up with a relatively good estimate of African-American turnout based on these two figures. The regression model finds that it's helpful to draw from both sources of data, and comes up with the following best-fit equation:Turnout = .65 * Population + .57 * Kerry
If you run these numbers through for North Carolina, you come up with African-American turnout of 44% (you also come up with 15% in Indiana).
Now, I don't necessarily expect that African-American turnout is going to be quite that high -- and I should point out that the standard error of the forecast is fairly large (roughly +/- 5 points). But it does seem to me that 40 percent -- which falls within that standard error interval -- is a pretty reasonable estimate. I am not so sure about 33 percent. That would imply turnout of approximately 63 percent of the black share of the Kerry vote. Only one other st
10 comments
Post a Comment