Unfortunately, when treatment effects are heterogeneous, the identified local average effect does not provide direct information about the wider population. This is problematic since treatment effects are likely to be heterogeneous in social science applications. In fact, this heterogeneity is one of the reasons why identifying causal effects is so difficult (individuals' self-selection into a treatment status based in part on anticipated treatment effects induces endogeneity problems).

A number of demographers have discussed the problem of extrapolating local average treatment effect estimates to the broader population. Greg Duncan, in his presidential address to the Population Association of America, stated that although causal inference is "often facilitated by eschewing full population representation in favor of an examination of an exceedingly small but strategically selected portion of a general population with the 'right kind' of variation in the key independent variable of interest.... a population-based understanding of causal effects should be our principal goal." Robert Moffitt writes that although "some type of implicit weighting is needed" to help us understand how to trade off internal and external validity, "this problem has not really been addressed in the applied research community." Some researchers have suggested using bounds for average treatment effects that are not point-identified (for example, Manski). Of course, the usefulness of bounding techniques depends on the tightness of the bounds, which in turn depends on what assumptions we are willing to impose - and it is exactly scholars' discomfort with prevailing assumptions (e.g., lack of correlation between the error and the treatment indicator) that drove the current focus on non-representative population subgroups. It seems to me that there is still work to be done to connect subpopulation causal estimates to broader population trends. I would be interested to hear of work in this area that you think is promising.

Networks are ubiquitous in science and have become a focal point for discussion in everyday life. Formal statistical models for the analysis of network data have emerged as a major topic of interest in diverse areas of science, as many scientific inquiries involve collections of measurements on pairs of objects. Probability models on graphs date back to 1959. Along with empirical studies in social psychology and sociology from the 1960s, these early works generated an active network community and a substantial literature in the 1970s. This effort moved into the statistical literature in the late 1970s and 1980s, and the past decade has seen a burgeoning network literature in statistical physics and computer science. The growth of the World Wide Web and the emergence of online networking communities such as Facebook and LinkedIn, and a host of more specialized professional network communities has intensified interest in the study of networks and network data. In this talk, I will review a few ideas that are central to this burgeoning literature. I will emphasize formal model descriptions, and pay special attention to the interpretation of parameters and their estimation. I will conclude by describing open problems and challenges for machine learning and statistics.

The setup is that there are many markets in which buyers and sellers are distinct types of actors, for example, the market for spouses has, until recently, been such a market (although I make no claim as to which side of the market is buying and which is selling). This market, in the form of college applications, was analyzed by Gale and Shapley in a famous 1962 paper in which they proved that there was a solution to this type of matching problem.

Unfortunately, this setup does not permit the applied researcher (or poor grad student) much traction for identifying the effect of being assigned to a particular residency program.

One solution comes from some work by Morten Sorensen on matching in venture capital. His idea is to model the decision process leading to investments by venture capitalists in early stage companies and at the same time to model his outcome of interest (company goes public) thus allowing for correlations between the respective error terms of the attractiveness / matching model and the outcome equation. Sorensen makes the point that this method makes use of the characteristics of other investors and investments in the market as instruments in order to address the fact that "better" investors may invest in "better" companies.

While in principle this method is attractive, it is computationally difficult and does not convince everyone--the faculty member I was talking to agreed that in principle this method is attractive, but that the results would be more credible with an instrumental variable that affects the probability of being assigned to a particular program. However, he also pointed out the value of these structural models--they provide estimates that may be valid over a broader range of values and can be used to do policy experiments that one may not be able to do with a model identified by instrumental variables.

Reading a few articles in the "physics of politics" as a political scientist, one has the sense of observing an alternate universe. For example: a paper on the effect of election results on party membership in Germany that has no references to work outside of physics; features many exotic (to me at least) terms like Wegscheider potentials, the Sznajd model, and the Kronecker symbol; and takes a time-series approach to causation that I suspect would be unacceptable to most reviewers in political science and economics these days.

In general, it's clear that physicists doing work on political phenomena (or "sociophysics" more generally) are primarily interested in exploring the individual-level social interactions that might underpin the macro-order we observe in, e.g., regularities in turnout or vote share distributions. As such, political institutions (which are the major preoccupation of political scientists) necessarily disappear from the model and are typically not even mentioned, even when they would seem to be of first-order importance in explaining a particular phenomenon. (Another example of the alternate universe: a paper that argues that party vote shares in Indonesia follow a power law, but which does not describe or mention the electoral system.) These omissions seem foolish on first reading, but it's clear that they reflect a different choice of explanatory variable: physicists seek their explanations in micro-interactions, and we seek them primarily in political institutions. It's probably both of course, but models can only be so complex.

Despite my overall sense of disorientation in reading these papers, there were also somewhat surprising moments of familiarity. Physics heavily influenced economics in an earlier period of colonization, and much of what we read in economics and political science descended from those models. In reading these newer physics papers, there is therefore a sense of distant kinship, the knowledge of a common ancestor several generations back.

I wonder about the scope for collaboration between physicists and social scientists. Based on my admittedly very cursory reading of one area in which physicists have ventured, it's hard to know whether the potential gains from trade are sufficient to overcome the apparent difference in goals. For all I know there already is a lot of productive collaboration going on -- if you know of something interesting, share it in the comments!

Identifying the sources of randomness underlying our data is important, because they have implications for our analysis. Särndal, Swensson, and Wretman show that the variance of a parameter from a ordinary regression model estimated using sample data can be decomposed into two elements, one based on the sampling design and one based on the model. In the case of a census, the extra variance introduced from the design is zero, and thus the total variance of the estimated parameter is the variance of the "BLUE" estimator. Otherwise, accounting for the sampling design in the analysis should improve inference.

I am probably overly skeptical and I am very sympathetic to heroic attempts to solve difficult problems of causal inference to answer important questions. Still, it seems that having multiple instruments can become an embarrassment of riches. A good instrument is so hard to come by that having too many starts to lend evidence against an empirical argument rather than for it.

While a copy on your computer is very handy, a desk copy of this book is essential if you are interested in machine learning or data mining. The book is also a sight to behold. You can buy a copy at Amazon or Springer.

Despite their popularity, conventional propensity score estimators (PSEs) do not take into account the estimation uncertainties in the propensity score into causal inference. This paper develops Bayesian propensity score estimators (BPSEs) to model the joint likelihood of both the outcome and the propensity score in one step, which naturally incorporate such uncertainties into causal inference. Simulations show that PSEs treating estimated propensity scores as if they were known will overestimate the variation in treatment e_ects and result in overly conservative inference, whereas BPSEs will provide corrected variance estimation and valid inference. Compared to other direct adjustment methods (E.g., Abadie and Imbens 2009), BPSEs are guaranteed to provide positive variance estimation, more reliable in small samples, and more flexible to contain complex propensity score models. To illustrate the proposed methods, BPSEs are applied to evaluating a job training program.

This has received attention from the social science community and others. Even Paul Krugman, mentioned in Coburn's press release as an example of (wasteful? political?) NSF funding, has something to say about it. There's no need to rehash the arguments here, which ever-so-nicely point out that Senator Coburn doesn't really know what he's talking about nor do his arguments make a whole lot of sense.

Regardless of the arguments, I just wanted to put a graph up to put all of this in perspective. In the 111th Congress, Coburn has had very little success with his amendments:

Seven of the rejections are instances when Coburn's amendment was tabled without discussion. Most of the rejections have been of proposed budget cuts or banning funds from certain projects And this is just in this year. Out of all the roll call votes on Coburn-sponsored amendments in the Senate over his tenure, only 8 out of 68 have actually passed.

I understand trying to tackle his critiques, as they track with an internal debate already in the discipline. But I think it may be a tad knee-jerk to start letter-writing campaigns to our Senators. Tom Coburn knows that putting out no-win amendments is a great way to take positions in the Senate without committing to anything. Minority amendments are a costless signal of the blandest kind--even a political scientist can see that.

They find that 10 year olds that ate candy daily were much more likely to be convicted of a violent crime at age 34 than those who did not eat candy daily. They cite this as evidence that childhood diet has an effect on adult behavior. One of their hypothesized mechanisms is that using candy as a reward for children (e.g. for behavior modification) inhibits the child's ability to delay gratification. And there is evidence that children that posses problems with delayed gratification tend to score lower on a host of measures, including the SATs (see also: the marshmallow studies).

The longitudinal data gives them leverage. For instance, the authors are able to control for parenting style at age 5 along with other variables, such as various scales of behavior problems or mental abilities at age 5 (some of these were discarded in the final analysis because of their variable selection rules). These ease my main concern that "problem children" might lead to a certain type of parenting and also indicate a propensity for violent adult behavior. Their controls help to eliminate this possibility (though, I will say that I am not familiar with this literature and they use fairly complicated scales to measure these concepts).

Strangely, at least to me, they do not seem to control for parental income or socio-economic class. I have a few ideas as to why this might matter. First, candy is relatively cheap compared to a good diet, thus poorer families might be forced to choose the cheaper option when feeding their children. Second, financial pressures lead to time pressures, which could force parents to take shortcuts--feeding their children junk food because it is quick or using it to induce behavior because it is easy. Thus, parental income may matter greatly for candy intake and it also may increase propensity to commit violent crimes. I am not certain this is true, but it seems plausible and unmentioned in the paper. Even if the finding is not causal, however, it is still interesting.