Tag Archives: descriptive inference

How much does it cost to run for Congress?

Leave a reply

Chris Cillizza writes on WashingtonPost.com yesterday:

It costs a lot of money to run for office. But how much exactly?

A great infographic from Good magazine — with data from the good people at Maplight — helps answer that question.

According to their calculations, in the two years prior to taking office the average Senator raised $6.4 million ($8,700 a day!) while the average House Member raised $1.2 million ($1,700 a day).

So this magazine says it is 6.4 million for the Senate, and 1.2 million for the House. Note that these must be challengers, not incumbents, because it says “prior to taking office.”

Now let’s compare these figures to the paper by Stephen Ansolabehere, Erik Snowberg, and James Snyder from 2005, published in the journal Public Opinion Quarterly (and available for free online here).

According to Table 1, Senate challengers spent an average of $864,813, and House challengers spent an average of $149,902. That’s much less than the magazine’s numbers, but note we are now talking about expenditures versus money raised. I suppose one explanation for the difference could be that challengers keep the rest for future campaigns.

In keeping with the goal of the paper, Ansolabehere, Snowberg and Snyder also find that the average spending by Senate candidates as reported in the news media was $12.7 million; for House candidates it was about $1.2 million.

Another fun thing about that paper: they surveyed the public and found that the public generally overestimated the amount of money raised:

To gauge the degree of misperception, we conducted a national survey of 1000 adults and asked how much money they thought the typical U. S. House incumbent raised for reelection. The average estimate among survey respondent was that House incumbents spend $5.8 million to win reelection. In reality, the average U. S. House incumbent raises and spends approximately $780,000.

To the extent that the paper and the magazine report disagree with one another, I (obviously) would believe the paper. If you read the infographic linked to in Cillizza’s post, you’ll see that it is produced by the campaign finance reform advocacy group RootStrikers (Lawrence Lessig’s group I believe) and are asking people to sign an “anti-corruption” petition; they don’t tell you how they got their numbers or what the data sources is. In contrast, the academic paper documents where the data come from (the Federal Election Commission) and explains any decisions made about, for example, how to classify different types of donation.

Food deserts dessert

Leave a reply

At his blog, Andrew Gelman relays some concerns a correspondent has with the recent research in the New York Times on food deserts.

The concern boils down to whether the studies claiming there are no food deserts are classifying grocery stores correctly. The correspondent claims that the coding scheme lumps in convenience stores with grocery stores. Two commenters (1, 2) argue this objection is faulty: that the coding rules make sense.

Well…at least now we’re arguing about the right things! And using data as the basis for argument. (Though note a lot of the commenters at the post seem to be relying on personal anecdotes.)

How to measure media coverage?

3 Replies

A wise man once said that even causal inference involves description, since ultimately what one is doing is describing patterns in a data set. Indeed without description it is hard to know what the important questions are. For example, suppose we want to know whether having a black president makes the media pay less attention to the black unemployed. Before we even think about the design, how would we go about measuring media attention?

This is exactly what Washington Post blogger Eric Wemple struggles with in this post.

Wemple describes two experts who ask this question and reach opposite conclusions. Here is all the information given about how the conclusions are reached, from only one side:

I had a tough time finding good data specifically on coverage of issues such as black unemployment — as opposed to, say, unemployment or the economy more broadly. So I spent a lot of time talking to journalists, and others who closely follow and speak to issues of concern in the African American community, about whether they’ve noticed a significant change in national media coverage since the election of the nation’s first black president.

Yikes. You mean even with Google Trends, the Project for Excellence in Journalism, and scores of newspaper databases online, the best we can do to quantify media attention is to talk to some activists?

In fact I’ve run into this problem before, when as an RA this summer I was asked to see how much different policy options had been discussed, relative to one another, in the press over the past few decades. There was no apparent off the shelf solution and it wasn’t crucial enough that I should code something up myself. Here’s what I ended up doing:

1. Do a lexis nexis search for the keyword of interest, restricting sources to the new york times
2. Exported the search results to endnote, an online citation service. Since it’s a citation service all I can export is meta data–title, date, author, page number.
3. From endnote, save the list of citations as a tab separated file, which means we can throw it into excel, stata, r, or whatever stats package we want.
4. In r, count the number of articles per year. Simple way: table(year). Can save this table as a new dataset.
5. Repeat the above steps for each additional keyword of interest.
6. Merge all the counts together into one dataset, and line plot away.

There must be an easier way! Anyone know of one?

Do economists oppose further stimulus?

Leave a reply

That might be the conclusion you draw from this Associated Press piece, reporting on the results of a survey of economists (no details about the survey beyond that are given):

WASHINGTON — The best cure for the economy now is time.

That’s the overwhelming opinion of leading economists in a new Associated Press survey. They say the Federal Reserve shouldn’t bother trying to stimulate the economy — and could actually do damage if it did.

Only one economist is quoted in the article, John Silva of Wells Fargo:

What the economy needs most, says John Silvia, chief economist at Wells Fargo, is time. Consumers must further shrink debts amassed in the mid-2000s, and the depressed housing market needs time to recover.

“There are no magic bullets,’’ Silvia says. “A lot of this stuff just really needs to be dealt with. It’s not a question of stimulus.’’

Ok, so not a causal question, but still a question of inference…

See also David Leonhardt’s column in the New York TImes today:

When Joe Biden convened debt ceiling negotiations with Congressional leaders on May 5, the experts were saying that the economy was on an upswing. They’re not saying that anymore.

Consumer spending has weakened. Hiring has slowed. Stocks have slid. As tends to be the case in the long aftermath of a financial crisis, the economy once again needs help.