November 20, 2007

Red State Blue State Article Published

Our (Andrew Gelman, Boris Shor, Joseph Bafumi, and David Park) "Rich State, Poor State, Red State, Blue State: What's the Matter with Connecticut?" paper has finally been published in the November 2007 Quarterly Journal of Political Science. You can access the paper here.

Here is the abstract:

For decades, the Democrats have been viewed as the party of the poor, with the Republicans representing the rich. Recent presidential elections, however, have shown a reverse pattern, with Democrats performing well in the richer blue states in the northeast and coasts, and Republicans dominating in the red states in the middle of the country and the south. Through multilevel modeling of individual-level survey data and county- and state-level demographic and electoral data, we reconcile these patterns. Furthermore, we find that income matters more in red America than in blue America. In poor states, rich people are much more likely than poor people to vote for the Republican presidential candidate, but in rich states (such as Connecticut), income has a very low correlation with vote preference.

Here are the blog posts relating to this project.

Here are some radio interviews and external blog posts on preliminary versions of the paper.

Posted by Boris at 11:35 AM | Comments (1) | TrackBack

November 6, 2007

Do the Democrats represent the rich?

Boris points to this post by Megan McArdle which discusses some of the political implications of the Democrats doing best among lower-income voters but winning the states and congressional districts where more of the higher-income Americans live. As McArdle puts it,

[Michael Franc] is actually making a good point: the constituency of the Democrats will force many of them to support the interests of the rich, even where they might ideologically prefer to oppose, because doing so is good for their district. Voters, especially poor voters, are highly influenced by local economic conditions. It is thus in Chuck Schumer's strong political interest to keep the financial services industry happy, whether or not they vote for him. Ditto Nancy Pelosi and Silicon Valley.

This does seem like a real tension: I'd only add that it's not just what the Democrats ideologically prefer, but also what their voters want. I haven't looked at the data from Nancy Pelosi's district, or for that matter at votes for Chuck Schumer, but where we have looked at voting (thanks to Henry Farrell for linking to our paper on this), the Democrats do better among the poor and the Republicans do better among the rich. It's not a perfect correlation by any means, but to the extent that Nancy and Chuck are listening to their party's supporters, they'd be listening to teachers, nurses, students, and, for that matter, unemployed people, not hedge fund managers.

McArdle writes,

Democrats indisputably represent more rich voters than Republicans; their constituency is the people in their district, not the people in their district who voted for them.

I'd respond to this with a Yes and No. In terms of the Constitution, I agree; for that matter, congressmembers also represent nonvoters and people such as children and noncitizens who are ineligible to vote, just as back in 1789 they were said to represent women, non-property-owners, and 3/5 of the slaves. On the other hand, the two parties are different, and voters generally have enough information about candidates to vote for the one who is closer to their preferences. So in that sense, congressmembers do actually represent the people who vote for them. After all, Democrats are much more liberal than Republicans in otherwise-comparable districts. (There's lots of evidence on this; see, for example, the graph on page 213 of our recent book.)

Another way to look at this is to flip it around and consider the Republicans, who represent richer voters but poorer states. A simple geographically-based analysis would suggest that the Republicans would be trying to raise taxes on the rich and raise benefits for the poor. But they're not. Arguably the Republicans' pro-business, low-tax policies are ultimately what's best for the poor (and also the rich), but they're certainly don't seem like the kind of populist notions that would make people in poorer districts happy.


The sweet spot for either party is spending that benefits its favored voters: rich people in poor states if you're a Republican, or poor people in rich states if you're a Democrat. This could be military contracts in the South (if you're a Republican) or mass transit in the Northeast (if you're a Democrat).

Now consider slopes. In the "red states," the slope is steep so there's not much of a motivation for R's to support measures that help poor people in poor states (if there is such a program). But in the "blue states," the slope is flat enough that there is a motivation for Chuck Schumer et al. to want to help out hedge fund managers (as well as to support programs such as Amtrak that benefit upper-middle-class types in the Northeast).

To put it another way, recall that the "red state, blue state" divide occurs among the rich, not among the poor. So you might expect the parties to have pretty consistent national policies on targeted benefits to the poor, but to be much more localized when considering benefits to the rich, with the Democrats favoring the financial and high-tech industries, and Republicans favoring agribusiness and small-business owners, for example. It would be interesting to see this studied more systematically.

The man-bites-dog factor

Another aspect of this is the idea that the Democrats are expected to be fighting the rich, and it's a surprise for things to go the other way. If it's the Republicans supporting the rich, this would not be news. To put it another way, Michael Franc's article is titled, "Democrats wake up to being the party of the rich," but on his terms (unwillingness to impose taxes on "mega-millionaires"), I assume the Republicans would be "the party of the rich" also.

Similarly, Fred Siegel writes that the Democrats are the party of the rich and that this is a trend since 1972. This may be the case but it doesn't show up in the polling data. Consider this graph (from this paper by David Park and myself) showing the difference in proportion of Republican vote, comparing voters in the upper third of income to voters in the lower third:


The Republicans have been doing consistently best at the higher end of the income scale. Again, I'm not disagreeing with Franc and Siegel about the geographic and fundraising bases for the Democrats' support; I'm just pointing out that with data such as shown above, it's no surprise that the Republicans too are going in that direction.

Based on survey data, most voters tend to place themselves to the right of the Democrats on economic and on social issues, and most voters tend to place themselves to the left of the Republicans in both dimensions; see, for example, this graph based on National Election Study data from 2004. Each dot represents where a survey respondent places him or herself on economic and social issues: positive numbers are conservative and negative numbers are liberal, and "B" and "K" represent the voters' average placements of Bush and Kerry on these scales:


Despite all the push by rich funders on both parties, the Hollywood parties and the oil money, this is where things stand. Larry Bartels has a story of why this is, but in any case, it doesn't quite fit into a simple story of the Democrats being the party of the rich. At least not yet. They have to go a ways before they catch up to the Republicans on that one.

Posted by Andrew at 7:56 PM | Comments (1) | TrackBack

November 5, 2007

Income, religious attendance, and voting: recent patterns and trends since 1992

I can't say I have much of an explanation for this, but it's interesting:


Church attendance is a strong predictor of how high-income people vote, not such a good predictor for low-income voters.

There's lots of talk about religion and income and voting, but people don't always know that interactions are important.

Here are some time trends (from this paper with David Park). The graphs below show the difference in Republican vote between rich and poor, religious and non-religious, and their interaction (that is, the difference in differences), computed separately for each presidential election year:


As others have noted (although not, as far as I know, looking at interactions), it all started in 1992. We heard a lot about the Moral Majority back in 1980, but it doesn't seem to have started showing up in voting patterns until Clinton.

You can read more about interactions in the linked article. The key points are that (a) higher-income voters support the Republicans and have done so for awhile; (b) more recently, churchgoers have supported the Republicans, (c) the difference between churchgoers and non-churchgoers is much greater for the rich than the poor.

P.P.S. I posted the top graph several months ago but the recent interest in these religiosity/income graphs and these state voting maps motivated me to repost.

Posted by Andrew at 12:17 AM | Comments (7) | TrackBack

November 4, 2007

Religiosity and income in the U.S.

David noticed this article by Dan Mitchell reporting the well-known fact that people in richer countries tend to be less religious. What about states in the U.S.? We (that is, David Park, Joe Bafumi, Boris Shor, and I) look at it two ways.

First, here's a scatterplot of the 50 states, plotting average religious attendance vs. average income. (Religious attendance is on a -2 to 2 scale, from "never" to "more than once a week," and average income was originally in dollars but has been rescaled to be centered at zero.):


States that voted for Bush in 2004 are in red and the Kerry-supporting states are blue. You can see that people in richer states tend to be less religious, although the relation is far from a straight line. There is also some regional variation (more religious attendance in the south, less in the northeast and west).

Second, here's a plot showing the correlation of religious attendance and individual income within each state. We get a separate correlation for each state, and so we can plot these. Here we plot the correlations vs. state income, using the same color scheme:

Again, there's quite a bit of variation from state to state, but overall we see a positive correlation between income and religiosity in poor states and a negative correlation in rich states: To put it another way, in Mississippi, the richer people attend church more. In Connecticut, the richer people attend church less.

(See also here for more on income and voting by state, and here for more on income, voting, and church attendance.)

P.S. Typos fixed (thanks to commenters Derek and Sandapanda).

P.P.S. Colors of Iowa and New Mexico fixed (thanks to commenter David).

Posted by Andrew at 6:33 AM | Comments (14) | TrackBack

November 2, 2007

Comparing red states and blue states: more pretty graphs

"Like upscale areas everywhere, from Silicon Valley to Chicago's North Shore to suburban Connecticut, Montgomery County [Maryland] supported the Democratic ticket in last year's presidential election, by a margin of 63 percent to 34 percent." -- David Brooks, 2001.

Some of the discussions of our red-state, blue-state maps picked up on the differences between where national journalists live (the mid-Atlantic states and California) and other parts of America. The income-voting pattern is different in the red states and the blue states. We have some more thoughts on this (scroll down for the pretty graphs).

David Brooks, the New York Times op-ed columnist and author of Bobos in Paradise and On Paradise Drive, explored the differences between Red and Blue America in an influential article, "One Nation, Slightly Divisible,'' in the Atlantic Monthly shortly after the 2000 election. Sometimes described as the liberals' favorite conservative, Brooks embodies the red-blue division within himself. He has liberal leanings on social issues but understands the enduring appeal of traditional values---"today's young people seem happy with the frankness of the left and the wholesomeness of the right,'' and his economic views are conservative but he sees the need for social cohesion among rich and poor. His Atlantic article compared Montgomery County, Maryland, the liberal, upper-middle-class suburb where he and his friends live, to rural, conservative Franklin County, Pennsylvania, a short drive away but distant in attitudes and values, with "no Starbucks, no Pottery Barn, no Borders or Barnes & Noble,'' plenty of churches but not so many Thai restaurants, "a lot fewer sun-dried-tomato concoctions on restaurant menus and a lot more meatloaf platters.

Brooks lives in a liberal, well-off area. It is characteristic of the east and west coasts that the richer areas tend to be more liberal, but in other parts of the country, notably the south, the correlation goes the other way. A comparable journey in Texas would go from Collin County, a suburb of Dallas where George W. Bush received 71% of the vote, to rural Zavala County in the southwest, where Bush received only 25%.


The graph above shows the pattern: Collin and Zavala (the dark circles on the scatterplot) are the richest and poorest counties in Texas, and there is a clear pattern that poor counties supported the Democrats while the Republicans won in middle-class and rich counties.

When we showed this to a political scientist, he asked about the state capital, noted for its liberal attitudes, vibrant alternative rock scene, and the University of Texas: "What about Austin? It must be rich and liberal.'' We looked it up. Austin is in Travis County and makes up almost all its population. Travis County has a median household income of $45,000 and gave George W. Bush 53% of the vote, putting it about midway between Collin and Zavala counties in the graph.

By comparison, the next graph shows the counties of Brooks's home state of Maryland: here there is no clear pattern of county income and Republican vote. We have indicated Montgomery County, the prototypical wealthy slice of Blue America, in bold, and it is not difficult to find poorer, more Republican-supporting counties nearby as comparisons. Rich and poor counties look different in Blue America than in Red America.


We can also look at income and voting for individual voters in each state. In Texas, there is a strong relation between income and voting:


In Maryland, the pattern is much weaker:


And here, by popular demand, is the notorious Kansas:


P.S. Just to be clear, I think Brooks's observations about cultural differences between red and blue America are interesting and important; you just have to be careful when aligning these with income or wealth.

Posted by Andrew at 8:39 AM | Comments (8) | TrackBack

October 30, 2007

More precision on income and voting?

Jeff writes,

Some questions of interest, picking up from your trio of income/state winners graphs:

At what income cutoff ($) would Dems and Repubs tie in electoral votes? What national income percentile is this?

What if you take the top x% within each state by income? (How low do you have to go before the Dems can win?)

My reply: I imagine the threshold would be close to the 50th percentile, just by symmetry since each party got about half the vote, and when we last looked, the electoral college had little partisan bias (i.e., the seats-votes curve goes close to 50/50; see here)..

But I'm wary of trying to get a more precise answer because this would lean too heavily on the assumed linearity of the income predictor in the model. Linearity fits reasonably well, but still, this is the sort of modeling exercise I wouldn't trust. I certainly wouldn't trust the linear model on theoretical grounds, given that the categories are just the arbitrary divisions used by NES.

Posted by Andrew at 12:57 AM | Comments (0) | TrackBack

October 25, 2007

Some cool graphs of rich states and poor states

I'll take advantage of Paul Krugman's recent link to our paper on income and voting by putting up some cool scatterplots that we made recently. It started with our maps of which states Bush and Kerry would've won if only the votes of the poor, middle-income, and rich were counted:




We noticed that the familiar red-blue pattern (rich northeast and west coast supporting the Democrats, rest of the country supporting the Republicans) showed up clearly among rich voters, but not among the poor or middle class.

Here are the data shown another way: for each income category, we show Bush's vote share for each state, plotted along with the state's income. For poor voters, there is no systematic difference between rich and poor states. But for middle-income and especially for rich voters, there is a very strong pattern of rich states supporting the Democrats and poor states supporting the Republicans.




Thus, the familiar red-blue divide of cosmopolitan coastal Democrats and heartland-state Republicans shows up among the rich but not the poor.

Posted by Andrew at 10:48 PM | Comments (15) | TrackBack

February 27, 2007

State incomes over time: the rich stay richer, the poor stay poorer (but less so than before)

When looking at voting and state income (red states and blue states, etc.), we realized that, although many of the geographic patterns of voting in the U.S. are relatively recent (for example, New England used to be strongly Republican, now is solidly Democratic), the rankings of states as rich and poor has been steady for quite awhile. The rich states now are, by and large, the states that had factories and large cities 50 or 100 years ago. Here are some graphs (using Census data that Justin Phillips gave me):


Apparently this isn't just a U.S. phenomenon. Diego Comin, WIlliam Easterly, and Erick Gong find that the wealth of nations was determined in 1000 B.C. Their paper is interesting and has some cool maps, but the graphical presentation could be improved a bit. I'll offer some suggestions on the chance that they'll have an opportunity to revise:

Figures 1,2,3: Put all the maps next to each other (in a vertical row, there's room once you remove Antartica!) so the comparison is clearer. Also, make the latitude/longitude lines much much lighter. They're overwhelming the plote entirely. Finally, I can't understand what relevance the current political borders (e.g., between the U.S. and Mexico) have in 1500 A.D.

Figures 4-7: Too many countries to be readable. Break each into a few (e.g., 4 plots), breaking up by geographical regions. Then there will be space, you can spell out the country names (use caps and lower-case, not all caps) and remove the dots (just center each country name on its point). Also show numbers for per capita income, not logs (6,7,8,etc, which are uninterpretable). Displaying on log scale is fine but use interpretable labels.

Also, show a parallel-coordinate plot (like my first two plots above)!

Get rid of table 3. These are binary variables. You can just say in the text, "45% of the 113 data points in 1000 B.C. had ..., 73% in the year 0, ..."

Tables 4 and 5: These should be plotted as time series.

Tables 7-12. You should graph these too. I know you won't want to, but see here for some inspiration. You've done the work, why not make the paper special?

Anyway, lest I seem to critical . . . I like the paper which is why I'm taking the time to make these suggestions.

Posted by Andrew at 12:36 AM | Comments (0) | TrackBack

January 30, 2007

What's the Matter with Connecticut, in Connecticut


Posted by Andrew at 11:46 AM | Comments (0) | TrackBack

January 3, 2007

Income, religious attendance, and voting

We've been extending our work on income and voting to include religion as well. For example:


MS, OH, and CT represent poor, middle-income, and rich states, respectively, and the red, blue, and gray lines on each plot represent frequent church attenders, occasional church attenders, and nonattenders.

Rch people vote more Republican and church attenders vote more Republican, but in addition, the difference between church attenders and nonattenders is greatest among rich people in poor states (as in the Mississippi graph above).

To get more understanding of the patterns of income and religion by state, here's state average religious attendance vs. state average income, with the colors indicating states that went for Bush or Gore in 2000:

There's a negative correlation, but also regional patterns, with the western states (except for Utah), some northeastern states, and some others below the main line.

And here are the within-state correlations between income and religious attendance (again plotted vs. state average income):

Religious attendance is positively correlated with income in Mississippi (for example) but negatively correlated in Connecticut. Thus, the zero correlation between income and Republican voting in Connecticut ("What's the matter with Connecticut") is partly explained by the fact that poor people in Connecticut are more religious than rich people in Connecticut. (But this doesn't tell the whole story, as we can see from the graphs at the top of this entry.)

Anyway, we're thinking more about this--other factors to consider are religious denomination, urban/suburban/rural, and ethnicity. Our original goal was to understand the pattern that richer voters go Republican, but richer states support the Democrats, but now there are many more patterns to figure out.

Posted by Andrew at 11:24 AM | Comments (7) | TrackBack

December 21, 2006

Voting patterns by state among the poor, middle class, and rich

Playing around a bit with the income-voting data (see here for a couple pictures and links to our paper, or here for an example of journalistic confusion, or here for lots more), we made the following maps, which show our estimates of what would have happened in the 2000 election if they had only counted the votes of people in different income categories:

rb by income.png

The left column of maps above shows our estimate of the states supporting Bush and Gore based on the voters in each of 5 income categories. The most striking pattern is that, unsurprisingly, Gore does better if the vote is restricted to lower-income voters, and Bush does better at the high end.

The next pattern--which I think is really cool--is that the "red state, blue state" pattern of the coasts vs. the south and center of the country basically disappears for the poorest voters. At that extreme, it's just not true that the rich states support Gore and the poor states support Bush. For rich voters, however, the pattern is clear: Gore wins in California and a few rich northeastern states, and Bush wins the rest. These graphs dramatize that the "red and blue state" patterns are most relevant for the richest voters.

The column of graphs on the right shows which states support Bush and Gore more than the national average within eachincome category. Again, the pattern for the richest states is similar to the national map (with the Pacific coast and northeast/upper-midwest being blue), but with the states showing a different pattern at the low incomes.

Just to be clear: I'm not claiming that these patterns are, or should be, some kind of surprise. Rather, I'm pointing out that many of the familiar distinctions between red and blue states are most relevant for the richest voters. It doesn't have to be this way, and I don't think it was that way before 1992, but this is what we're seeing now, and it's a way to understand the pattern that we discussed in our paper, that income is more predictive of Republican vote in poor states than in rich states.

Posted by Andrew at 12:39 AM | Comments (8) | TrackBack

November 13, 2006

Income and voting in 2006

Somebody asked us about our "red-state, blue-state" results (the pattern that we found in the 2000 and 2004 elections, in which income and Republican voting are highly correlated in poor states such as Mississippi, moderately correlated in medium states such as Ohio, and not at all correlated in rich states such as Connecticut--hence the title of our paper, "What's the Matter with Connecticut"; also see pretty picture here), and whether anything similar happened in 2006.

We're still looking for raw polling data; the closest we could find were these House exit poll results from, which are broken down by income and region. Here are the results:


It's tougher to see this since we don't have the individual states, but income is indeed more correlated with Republican vote in the South and Midwest, and less so on the coasts, which fits our "red state, blue state" story.. (The income categories from the poll are 0-15,000, 15-30,000, 30-50,000, 50-75,000, 75-100,000, 100-150,000, and 150-200,000, and 200,000+; for sample size reasons we combined the two highest categories.)

Posted by Andrew at 7:00 AM | Comments (1) | TrackBack

October 19, 2006

What makes a good radio interview?

Leonard Lopate interviewed me today on local rado to talk about my paper, Rich State, Poor State, Red State, Blue State: What's the Matter with Connecticut (coauthored with Boris Shor, Joe Bafumi, and David Park). I've been a fan of Lopate for awhile (ever since hearing his interview with the long-distance swimmer Lynne Cox), but I have a much better sense of what makes him a good interviewer, now that I've been interviewed myself.

The trick is that he had a series of questions. If he had let me just ramble on for five minutes, I would've come off horribly, but I was able to answer the questions one at a time and explain things clearly. At the same time, the interview was live, and I didn't see the questions ahead of time, so things were spontaneous. (I only wish I had remembered to mention that we found similar patterns in Mexican elections.)

It was interesting to get this insight into interviewing techniques.

And, of course, I can't resist posting the superplot again:


Posted by Andrew at 12:02 AM | Comments (0) | TrackBack

April 20, 2006

Sorry, but . . . more on red and blue states

Atiba Pertilla writes,

I read your paper "Rich state, poor state, red state, blue state" with a great deal of interest. I think it's very important to cut through facile generalizations about income levels and voting behavior.

That said, I would like to know if you've ever thought of looking at
housing costs as one way of controlling for variation in economic
conditions from one part of the country to another. In other words, a
$60,000 salary can provide you a lot more house in Laramie, Wyoming
than it does in Marin County, California. I know that your argument is
in part about people's perception of their income relative to those
richer and poorer than them, but it seems important to note that the
standard of living provided by a certain income is likely to vary
considerably from one part of the country to another regardless of how
people perceive their income relative to the folks in the next
subdivision over.

Data that might help you investigate this possibility could be taken
from HUD's studies of fair market rent conditions around the country.

My reply:

Yes, people have raised this issue, in particular when I spoke on the paper at the family policy seminar in the social work school here. I don't think cost of living could explain things all by itself: the difficulty is that, if the cost of living is high in Calif. (and thus, people in the top income category aren't so "rich"), then people in the lowest income category will be even worse off. So the cost of living, by itself, doesn't change the relative difference between rich and poor. There's a related argument, that the subjective difference between rich and poor is greater in Mississippi than in Connecticut, but this would require some differential effect.

Posted by Andrew at 12:27 AM | Comments (3) | TrackBack

April 4, 2006

Red/blue and religion

James Stamey writes,

I thought about some things I have seen on your blog as I was reading through another website I keep up with, (The website is run by several media members who happen to be religious with the premise that in general the media does not "get" religion.) Anyway, the red/blue state ideas come up all the time and recently the conversation was about people who economically benifit from democrat policies voting republican and people who economically would benifit from republican policies, voting democrat. A couple of the comments were:
I am one of those people who generally fares better economically under Democrats, but generally votes Republican due to, yes, abortion. While I have certainly voted for Dems, even pro-choice Dems, under specific circumstances, the murder of unborn children trumps my bank account in the grand scheme of things.


I’m one of those people would generally fares better economically under Republicans, but my wife and I vote for Democrats because of social issues. . . . If you are concerned about poverty, the death penalty, just war, a foreign policy based on human rights, a humane immigration policy, and policies which promote toleance and diversity, we put our economic needs aside and vote for Democrats.

My reply: I have two thoughts on this. First, I find it interesting that these people associate economic voting with the idea of voting for personal gain. Theory and data both suggest that people vote for what they think is good for the country economically, not necessarily what they think is good for them. I'd be curious what opinions the people quoted above would have about national economic policies.

Second, when I went over to, I noticed this entry by Terry Mattingly, who writes,

The middle class, for the most part, continues to vote (some would say against its economic interests) for the Republican Party — primarily because of moral and social issues. Meanwhile, a rising percentage of the rich, especially along the coasts, has been voting (against its economic interests) for the Democratic Party — primarily because of moral and social issues.

He seems to be making the "red state, blue state" fallacy of associating rich coastal states with rich coastal voters. Richer people continue to support the Republicans. Yes, richer people in the coasts support the Republicans less, and richer people in the "red states" support the Republicans more, but nationwide, the correlation between income and Republican vote is still there. But I am receptive to his main point--that "social issues," including religion, are relevant in understanding income-and-voting patterns.

Posted by Andrew at 12:27 AM | Comments (0) | TrackBack

March 15, 2006

E.J. Dionne's column summarizes our red-blue paper

Boris Shor writes:

An article by EJ Dionne about our red-blue paper ("Rich state, poor state, red state, blue state: What's the matter with Connecticut?") appeared today in the Washington Post. Dionne had called me on Friday to talk about the paper, and we had a nice conversation -- he's a very sharp guy and really understood what we were trying to explain.

A couple of thoughts about the paper...

0. The article is nicely written, and gets our major points across clearly. Kudos to Dionne, and I wish we academics could write so crisply. The following are a bunch of quibbles that academics like myself can't help themselves from generating:

1. The title of the column ("What Kind of Hater Are You?") is strange, at least as it relates to our paper. The title of the syndicated column ("Class Warfare and Political Polarization") was closer to the mark, but still off. I guess the article had a point beyond highlighting our paper (gasp!), but the new headline seems needlessly provocative. Does the Post title op-eds, or only news stories?

2. Dionne loved our title, as do I -- great job Andy. He asked if I had any children (not yet!), because the the title of our paper sounded to him like something written by a parent. I think that hit it on the head. Looks like Zacky's (Andy's kid) first research contribution! :)

3. Dionne doesn't mention (not that he needed to) that we show a rather important shift in recent American political history: for the first time, wealthy states _and_ counties are now voting Democratic (see figures 1 and 5 from the paper). That is new (since 2000), and something to think about.

4. I'm not sure the intellectual leap from seeing an income component to voting to "class war" is self-obvious. That's one interpretation, but another could simply be that the weights individuals assign to various voting factors differ by region/state/county.

5. He quotes the line "In poor states, rich people are very different from poor people in their political preferences. But in rich states, they are not." A brilliant one -- so simple, yet so profound! I wonder who wrote it ...

6. Again, the result of varying slopes of income may not necessarily mean that the country is even more "polarized" or "divided". It could just mean that people vote differently across the United States.

7. People love Andrew's point about the availability bias leading to journalists' extrapolation of the "rich Democrat" meme to larger patterns. I admit, I was skeptical on including it in the paper, so there you go...

8. I'm not sure I understand this paragraph: "Gelman and his colleagues help us understand why Southern Democrats such as Bill Clinton and John Edwards may be more attuned to the power of populism than northern Democrats such as John Kerry -- and, perhaps, Hillary Rodham Clinton. Their paper also helps explain why Southern Republicans such as President Bush pursue policies that are hugely beneficial to their wealthy base even as they try to diminish the political impact of class warfare by shifting the argument to other subjects: religion, values or national security."

We show (figure 6, page 13) that, in the South (except for VA, WV, AR, TN, and FL), rich counties generally support Republican candidates, while that doesn't seem to be so for other regions (figures 7-9). Of course, the sparsity of data at the county level mean our coefficient estimates are noisy, but these broad patterns seem to come through. Also, figure 13 on page 19 shows that southern states like MS, AR, LA, AL have a high estimated slope coefficient for income (incidently, so do NM, WV, ME, not solidly red states).

I'm not sure about the link to populism, or governing/campaign strategy. Is Dionne saying that politicians from the South imbibe the local political culture of a high effect of income on voting, and then go out and campaign and govern accordingly? Given the necessity of cobbling a highly diverse winning electoral college coalition, I'm not sure this is a very powerful strategy. If true, wouldn't the corollary of the argument implie that Democrats like Kerry should have paid no mind to economic issues, since in Maine, rich and poor counties don't differ in their presidential vote?

9. Is it right to dichotimize voters as living in "two different political universes"? That's the common thing to do, and we fall prey to the temptation ourselves, but I think there's more of a continuum of regions and individuals than there are dichotomies (see figure 13, for example). Maybe our primitive brains naturally tend to draw sharp distinctions and thinking in continuous terms is unnatural, but I think the data support the latter.

10. Dionne, in his phone conversation, mentioned that we might be getting some funky results for Southern states for 1968 due to the Wallace vote (since we define Republican vote as a proportion of the two-party results), which sounds right. See, for example, Alabama's 1968 vote by counties. In many of the counties, the proportion of the electorate voting for the Humphrey or Nixon tickets is very low, so the Republican proportion of the two-party vote may not be telling us what we want. Of course, this wouldn't change our results.

11. It's nice that the column is the most emailed, and the most viewed, on the Post today!

12. I've tried to collect all the press/blog mentions of the paper.

13. Why would a Washington Post column appear earlier in syndicated form, than in the original paper? The column was published in the SF Chronicle, for example, yesterday.

14. Could it be true that the Post collects comments at an AOL address?! (

15. Why is it impossible to buy a Washington Post in Chicago? "We don't carry out-of-town papers", the local Barnes and Nobles tells me. Those coastal hotshots can keep their elite opinions to themselves!

Posted by Aleks at 12:17 PM | Comments (2) | TrackBack

November 30, 2005

Rich state, poor state, red state, blue state: What's the matter with Connecticut?

We finally finished the paper (and here's the earlier blog posting with link to a powerpoint).


Posted by Andrew at 7:53 AM | Comments (3) | TrackBack

November 7, 2005

Income matters a lot in "red states," not so much in "blue states": What's the matter with Connecticut?

There's been some debate in the media and among social scientists about the relation between income and voting. On one hand, the states that support the Democrats--the so-called "blue states"--are richer, on average, than the Republican-leaning "red states." On the other hand, richer voters continue to support the Republicans--not so much as an economic determinst might suspect (even in the lowest income category, Bush in 2004 still got 36% of the vote) but the correlation is there.

Awhile ago, we made this plot, which shows how the Republicans can simultaneously have the support of poor states, and richer voters within states:


Mississippi is the poorest state, Ohio is in the middle, and Connecticut is the richest state. Within each state, the line shows the probability of supporting Bush for President for each of five income categories, and the five open circles represent the relative proportion of adults in that state in each category. The black circles show the average income and probability of supporting Bush for each state.

The above plot was fit with a model (a varying-intercept logistic regression) that restricted the slopes in the states to be essentially parallel. We then expanded the model to allow the slopes to vary also, so that the coefficient for income could differ in richer or poorer states. The figure below shows the result:


Income clearly matters much more in "red states" like Mississippi than in "blue states" like Connecticut. We also see this pattern in 2004, and somewhat in 1992 and 1996, but not really before the 90s.

My talk at George Mason University

I spoke on this last week at the economics department at George Mason University (at the invitation of Alex Tabarrok). Here are the slides. (We're still finishing up the paper and will post it soon.)

The audience was lively and raised many good points. One thing they emphasized is that, although the relation between income and vote preference is there, it is much weaker than one might expect based on an economic-determinism argument. I think that our second graph (above) helps focus this point: voting in Mississippi is much closer to economically-determined than voting in Connecticut, with states like Ohio somewhere in between. The other comment they made was that income is correlated with demographic-type variables such as ethnicity, education, and church attendance, and so a correlation between income and Republican voting shouldn't be interpreted as a causal effect. I defnitely agree with that comment but defended our analysis by saying that we actually are interested in the descriptive patterns. Who are these Democrats, and who are these Republicans? I've learned something by finding that there are big income gaps between Democrats and Republicans in the red states, not so much in the blue states. This finding is interesting in itself, because it's important to have a sense of who are the supporters of different political candidates and parties.

Finally, I had some arguments from cognitive psychology for why journalists could be confused about the red/blue patterns. (See near the end of the slides, also this blog entry on the second-order availability bias.) The audience wasn't convinved about my application of psychology research to this problem. I don't think they thought I was wrong, they just weren't convinced. Which is fair--I just wanted to present a reasonable explanation. The main thing is that, without multilevel modeling, it would be hard to see these patterns at all. When journalists (and social scientists) look at poll data, they tend to see just one aspect at a time (for example, journalists seeing the differences between states, and social scientists running regressions on demographic predictors). When only seeing part of the data, it is easier to inappropriately generalize.

Just for fun . . .

Here's one more plot, raw data from 2000 and 2004 exit polls (thanks to Bob Shapiro for pointing me to the data):


Posted by Andrew at 12:46 AM | Comments (8) | TrackBack

April 11, 2005

Rich state, poor state, red state, blue state: who's voting for whom in Presidential elections?

Higher-income states support the Democrats, but higher-income voters support the Republicans. This confuses a lot of people (for example, see here and here).

Boris presented our paper on the topic at the Midwest Political Science meeting last weekend. Here's the presentation (we're still working on the paper).

Here's the abstract for the paper:

For decades, the Democrats have been viewed as the party of the poor with the Republicans representing the rich. In recent years, however, a reverse pattern has been seen, with Democrats showing strength in the richer "blue" states in the Northeast and West, and Republicans dominating in the "red" states in the middle of the country. Through multilevel analysis of individual-level survey data and county- and state-level demographic and electoral data, we reconcile these patterns. We find that there has indeed been a trend toward richer areas supporting the Democrats--but within states and counties, and overall, the Democrats retain the support of the poorer voters. This pattern has confused many political commentators into falsely believing that Republicans represent poorer voters than Democrats.

And here are some cool quotes that illustrate the ambiguities of the relation between income and political preference:

I never said all Democrats are saloon-keepers. What I said is that all saloon-keepers are Democrats. - Horace Greeley, 1860

Pat doesn't have a mink coat. But she does have a respectable Republican cloth coat. - Richard Nixon, 1952

I come from Huntington, a small farming community in Indiana. I
had an upbringing like many in my generation--a life built around
family, public school, Little League, basketball and church on Sunday. My brother and I shared a room in our two-bedroom house. - Dan Quayle, 1992

Clinton displays almost every trope of blackness: single-parent
household, born poor, working-class, saxophone-playing, McDonald’s-and-junk-food-loving boy from Arkansas. — Toni Morrison, 1998

Like upscale areas everywhere, from Silicon Valley to Chicago's
North Shore to suburban Connecticut, Montgomery County supported the
Democratic ticket in last year's presidential election, by a margin
of 63 percent to 34 percent. - David Brooks, 2001

A lot of Bush's red zones can be traced to wealthy enclaves or sun-belt suburbs where tax cuts are king. - Matt Bai, 2001

But in the Ipsos-Reid surveys, 38 percent of voters in "strong Bush" counties said that they had household incomes below $30,000, while 7 percent said that their families earned at least $100,000. In "strong Gore" counties, by contrast, only 29 percent of voters pegged their household income below $30,000, while 14 percent said that it was above $100,000. - James Barnes, 2002

P.S. Typo in first sentence of this entry fixed (thanks to Jody's comment).

Posted by Andrew at 12:57 AM | Comments (5) | TrackBack

October 22, 2004

Red State/Blue State Paradox


In recent US presidential elections we have observed, at the macro-level, that higher-income states support Democratic presidential candidates (eg, California, New York,) and lower-income states support Republcan presidential candidates (eg, Alabama, Mississippi). However, at the micro-level, we observe that higher-income voters support Republican presidential candidates, and lower-income voters support Democratic presidential candidates. What explains this apparent paradox?

Journalistic Explanation

Journalists seem to argue with the second half of the paradox, namely, higher-income voters support Republican presidential candidates, and lower-income voters support Democratic presidential candidates.

Brooks (2004) points out that a large class of affluent professionals are solidly Democratic. Specifically, he notes that 90 out of 100 zip codes where the median home income was above $500,000 elected liberal Democrats.

Barnes (2002) find that 38% of voters in "strong Bush" counties had household incomes below $30,000, while 7% earned only $100,000; and 29% of voters in "strong Gore" counties had household incomes below $30,000, while 14% was above $100,000.

Wasserman (2002) also finds similar trends. Per capital income in "Blue" states was $28,000 vs. $24,000 for "Red" states. Eight of the top 10 metropolitan areas with the highest per capital income were from "Blue" states; and 8 of the top 10 metropolitan areas with the lowest income levels were from "Red" states.

The journalistic explanation is that higher-income individuals, and as a result, wealthly areas are Democratic; and lower-income individuals, and as a result, lower-income areas are Republican. Therefore, journalists would argue that there is no paradox.

Are Journalists Right?

McCarty, et al. (2003) in their examination of political polarization and income inequality show that partisanship and presidential vote choice have become more stratified by income. It was true that income was not a reliable predictor of political beliefs and partisanship in the mass public. Partisanship was only weakly related to income in the period following World War II. According to McCarty et al. (2003), in the presidential elections of 1956 and 1960, respondents from the highest quintile were hardly more likely to identify as a Republican than respondents from the lowest quintile. However, elections of 1992 and 1996, respondents in the highest quintile were more than twice as likely to identify as a Republican than were those in the lowest quintile.

If the Journalists are Wrong, What Explains the Paradox?

One possible explanation. Lower-income individuals in higher-income states turnout in higher rates; and higher-income individuals in lower-income states turnout in higher rates producing the Red State/Blue State paradox. In short, an aggregation problem.

So how do we prove this? To be continued...

Posted by at 5:08 PM | Comments (1)