John Side posts this graph from Lee Drutman of lobbying expenditures and bailout funds for several financial firms:
This is fun, and I recognize that this graph, in John’s words, “a back of the envelope analysis” and “only subjective,” but . . . isn’t there a problem with selection bias here–you’re only considering cases that had bailouts. I’d like to see a lot more data points here: firms with many different levels of lobbying but zero bailout.
But the graph raises an interesting theoretical point: larger firms will be giving more total lobbying dollars and thus may be more likely to be bailed out? Even beyond any “too big to fail” argument based on economics.
It seems to me, that if you were to toss out the AIG outlier, you would get a horizontal line.
But would more data points really solve the problem of one extremely influential outlier that is responsible for almost all the resulting correlation?
I would probably just draw a horizontal line with an intercept of about 0.01.
I found the analysis here and perhaps the x-axis should be "Lobby Expenditures as Proportion of Total Assets" since the y-axis is also a ratio relative to total assets. You might see a relationship there.
You would definitely see a relationship to absolute bailout size relative to absolute lobby expenditures, but that is because lobby expenditures and bailout size are directly related to total assets. Which is why you'd want to divide total assets out of the explanation.
Yes, there is definitely a problem of selection bias. Unfortunately, at this point, we only know of one big firm — Lehman — who tried to get a bailout and was denied. I included them in this graph and it is certainly worth noting that they were an under-investor in lobbying. Ideally, when all the post-mortems are done on this bailout, we will have better information on who applied for what when, and we'll be able to see how much lobbying greased the wheels of government assistance. But until then…
I completely agree with the two previous posters. Absent the AIG data point, the graph is actually striking for its absence of a correlation between bailout size and contributions. And perhaps insurance companies have fewer assets and hence the ratio of bailout/assets is higher.
I agree with Jon – drawing a non-horizontal line seems rather dependent on a single outlier.
Can anyone fill us in on the leverage of the AIG datapoint?
Including AIG:
y = 4.93208E-09x – 8.56423E-04
R² = 0.44513
0.493% per million dollars spent lobbying in 2008
Excluding AIG:
y = 3.49268E-10x + 8.66187E-03
R² = 0.03452
0.035% per million lobbying
AIG is a distant outlier in Bailout as % of Assets (almost 9% compared to a range of 0% to