Just in case some of this silly stuff comes up again . . . (click here)

We have a nice review in the latest Library Journal. This magazine is what librarians consult in making their purchasing decisions.

Below are 50 little graphs (from chapter 5 in the Red State, Blue State book) showing the 90th percentile and 10th percentile in income, within each state, for the past forty years. The patterns are pretty striking: the high end has increased pretty consistently in almost all the states, and the low end increased a lot in poor states, especially for the first half of the series. I don’t really know what more to say about this–we made the graphs because we are trying to understand the differences between rich and poor states in the past 20 years, and what has made them into “blue” and “red” states–but the graphs are full of interesting patterns. Incomes are inflation-adjusted and presented on a logarithmic scale (with a common scale for all the graphs), and the states are ordered from poorest to richest.

OK, here’s the picture:

The states above are ordered from poorest to richest.

And here are the trends since 1981, plotted vs. avg income within states:

In poor states, the poor have been doing better; in rich states, the rich have been doing better.

Income inequality between states

All states have been getting richer over the decades (as measured by average real incomes). Up until about 1980, income inequality between states decreased, then since then it’s increased slightly (which is consistent with the above scatterplots). Here’s the key picture:

Further discussion is here.

I’ll be speaking on Red State, Blue State this Wed, 17 Sept, 12-1:30, in the Government Dept at Harvard. It’s at 1737 Cambridge St., Room K-354. If you live in the Boston area, this is your chance to come and ask your questions and give your suggestions.

John Sides criticizes Alan Brinkley for writing, “for the past 40 years, close and unpredictable elections have increasingly become the norm.” I agree with John that it’s possible to quibble about the boundaries here (the past 40 years just barely exclude the Johnson-Goldwater landslide and the Kennedy-Nixon squeaker). But the general point–that close elections are common now and didn’t used to be–is correct.

Here’s a list of all the U.S. presidential elections that were decided by less than 1% of the vote:

1880
1884
1888
1960
1968
2000

Funny, huh? Other close ones were 1844 (decided by 1.5% of the vote), 1876 (3%), 1916 (3%), 1976 (2%), 2004 (2.5%).

Four straight close elections in the 1870s-80s, five close elections since 1960, and almost none at any other time.

Why is this? One theory is that national elections are more important now than they were in earlier periods. In the post-1896 era, for example, the Democrats had the solid South and big-city machines. It wasn’t such a loss for them to (usually) not have a decent shot at the Presidency.

P.S. I have no criticism of the substance of John’s entry linked to above. It’s just that by looking at all elections rather than focusing on the frequency of close ones, I think he’s missing something. Even in an evenly-divided electorate such as America’s in the past 50 years, you will have some uneven contests (depending on economic conditions). But we do seem to be in an unusual period in which extremely close elections are the norm or departure point.

P.P.S. John adds this pretty graph of popular vote victory margins since 1950:

There’s been some discussion of the idea that poll results have to be adjusted for party identification. In general, party ID is pretty stable over time. Vote preference varies a lot more. For a small amount of data on this, see Figures 1 and 10 of our 1993 paper.

You can adjust surveys by smoothing out party ID to get more stable
estimates over time, as we showed in this 2001 paper.

But I don’t know anything in particular about what’s going on in 2008.

I can see why political operatives want to look at these daily polls
but these horse-race numbers seem pretty irrelevant to me. Wherever
the polls stand, both parties have to go all out between now and the
election, both parties have to campaign in the swing states, to take
their best shots, etc. This is all true whether McCain is up by 5 or
Obama is up by 5.

If you’re in D.C., you should stop by. . . . I’m speaking in the statistics department at George Washington University on the topic of interactions. Here’s the powerpoint and here’s the abstract:

As statisticians and practitioners, we all know about interactions but we tend to think of them as an afterthought. We argue here that interactions are fundamental to statistical models. We first consider treatment interactions in before-after studies, then more general interactions in regressions and multilevel models. Using several examples from our own applied research, we demonstrate the effectiveness of routinely including interactions in regression models. We also discuss some of the challenges and open problems involved in setting up models for interactions.

The talk will be today, Wed 10 Sept, at 3pm, I think. I don’t yet know the room but you can call the department (202-994-6356) and they should be able to give you directions.

Tomorrow (Thurs) I’ll be speaking with Boris at noon at the Cato Institute on Red State, Blue State. It’s not too late to sign up for that.

See here and here.

We have some graphs that extend earlier estimates of Brooks and Manza to show some of the trends in voting by occupation category over the past fifty years:

Professionals (doctors, lawyers, and so forth) and routine white collar workers (clerks, etc.) used to support the Republicans more than the national average, but over the past half-century they have gradually moved through the center and now strongly support the Democrats. Business owners have moved in the opposite direction, from close to the national average to being staunch Republicans; and skilled and unskilled workers have moved from strong Democratic support to near the middle.

These shifts are consistent with the oft-noted cultural differences between Red and Blue America. Doctors, nurses, lawyers, teachers, and office workers seem today like prototypical liberal Democrats, while businessmen and hardhats seem like good representatives of the Republican party. The dividing points were different 50 years ago. The Republicans still have the support of most of the high-income voters, but these are conservatives of a different sort. As E. J. Dionne noted in analyzing poll data from 2004, the Democrats’ strength among well-educated voters is strongest among those with household incomes under $75,000—”the incomes of teachers, social workers, nurses, and skilled technicians, not of Hollywood stars, bestselling authors, or television producers, let alone corporate executives.”

We tried to take our analysis further by regressing on income within occupation groups, but we didn’t find anything exciting; there wasn’t much evidence of different rich/poor voting gaps in different occupation categories. This Teixeira and Abramowitz article adds something to this picture because they talk about how the relative sizes of these different groups are changing. They write:

Dramatic shifts have taken place in the American class structure since the World War II era. Consider education levels. Incredible as it may seem today, in 1940 three-quarters of adults 25 and over were high school dropouts (or never made it as far as high school), and just 5 percent had a four-year college degree or higher. . . . by 2007, it was down to only 14 percent. . . . In 1940, only about 32 percent of employed US workers held white collar jobs (professional, managerial, clerical, sales). By 2006, that proportion had almost doubled to 60 percent . . . we [Teixeira and Abramowitz] discuss these shifts in the class structure and analyze their political implications, primarily by focusing on the decline of the white working class.

Boris and I will be speaking on the book at the Cato Institute in Washington, D.C., next Thurs (11 Sept) at noon. The event will be moderated by Will Wilkinson; see the description here of the event on his blog.

All are welcome to come, but you should register online for the event. We’ll be having a panel discussion with Michael McDonald (Brookings Institution and George Mason University) and Brink Lindsey of the Cato Institute. I’m curious what they have to say about our work, especially some of the stuff at the end of chapter 9 about the connections between public opinion and policy.