Studying is good, drugs are bad, and the Surge isn't working

Economics is very concerned with causal inference. Here’s three recent examples of papers whose identification strategies are more interesting than their (unsurprising) results.

This is not to say that we shouldn’t keep honing the methodological toolkit – good evidence for your presuppositions is better than bad evidence. Plus, every now and then, a clever empirical strategy also turns out to lead to a counter-intuitive result.

The Causal Effect of Studying on Academic Performance
Todd Stinebrickner & Ralph Stinebrickner 
Despite the large amount of attention that has been paid recently to understanding the determinants of educational outcomes, knowledge of the causal effect of the most fundamental input in the education production function – students’ study time and effort – has remained virtually non-existent. In this paper, we examine the causal effect of studying on grade performance using an Instrumental Variable estimator. Our approach takes advantage of a unique natural experiment and is possible because we have collected unique longitudinal data that provides detailed information about all aspects of this experiment. Important for understanding the potential impact of a wide array of education policies, the results suggest that human capital accumulation is far from predetermined at the time of college entrance.

Why Parents Worry: Initiation into Cannabis Use by Youth and  Their Educational Attainment
Jan Van Ours & Jenny Williams    
In this paper we use individual level data from the Australian National Drug Strategy Household Survey to study the relationship between initiation into cannabis use and educational attainment. Using instrumental variable estimation and bivariate duration analysis we find that those initiating into cannabis use early in life are much more likely to dropout of school compared to those who start later on. Moreover, we find that the reduction in years of schooling depends on the age at which initiation occurs, and that it is larger for females than males.

Is the “Surge” Working?  Some New Facts 
Michael Greenstone 
There is a paucity of facts about the effects of the recent military “Surge” on conditions in Iraq and whether it is paving the way for a stable Iraq.  Selective, anecdotal and incomplete analyses abound. Policy makers and defense planners must decide which measures of success or failure are most important, but until now few, if any, systematic analyses were available on which to base those decisions. This paper applies modern statistical techniques to a new data file derived from more than a dozen of the most reliable and widely-cited sources to assess the Surge’s impact on three key dimensions:  the functioning of the Iraqi state (including violent civilian casualties); military casualties; and financial markets’ assessment of Iraq’s future.  The new and unusually rigorous findings presented here should help inform current evaluations of the Surge and provide a basis for better decision making about future strategy.  The analysis reveals mixed evidence on the Surge’s effect on key trends in Iraq.  The security situation has improved insofar as violent civilian fatalities have declined without any concurrent increase in casualties among coalition and Iraqi troops.  However, other areas, such as oil production and the number of trained Iraqi Security Forces have shown no improvement or declined.  Evaluating such conflicting indicators is challenging. There is, however, another way to assess the Surge.  This paper shows how data from world financial markets can be used to shed light on the central question of whether the Surge has increased or diminished the prospect of today’s Iraq surviving into the future.  In particular, I examine the price of Iraqi state bonds, which the Iraqi government is currently servicing, on world financial markets. After the Surge, there was a sharp decline in the price of those bonds, relative to alternative bonds. This decline signals a 40% increase in the market’s expectation that Iraq will default.  This finding suggests that, to date, the Surge is failing to pave the way toward a stable Iraq and may in fact be undermining it.

This entry was posted in From the Frontiers. Bookmark the permalink.

4 Responses to Studying is good, drugs are bad, and the Surge isn't working

  1. Bruce Bradbury says:

    I’m always suspicious of IV papers where they don’t tell us in the abstract what the instrument is 🙂

    Having skim-read the cannabis paper, I’m not convinced that they are able to provide much evidence for their ‘unsurprising result’. They use commencement of cigarette smoking as their main instrument. In the paper they state “The crucial econometric assumption underlying identification is that the early use of cigarettes has no impact on educational attainment”. However one could easily imagine that children growing up in dysfunctional families will be more likely to start smoking earlier, and also have poorer outcomes due to their family environment. Such a link via family background will be confounded with any causal link their results.

  2. ChrisPer says:

    And the test of the ‘Surge’… how many metrics did they cross-check? One of the most important is the LOCAL stock market. I can only access the abstract, so I will merely say that the headline shows the purpose is not assessment of Iraq’s up-and-down potentials, but assessment of the effects of US policy.

    Given that the news about the surge is generally positive (it has reduced deaths), there is a strong market for countering information among the extremely broad demographic who are heavily invested in a doctrine of US failure.

  3. boredinHK says:

    “This decline signals a 40% increase in the market’s expectation that Iraq will default. ”
    But what is the expectation /risk of default ? 1% ? so we have a a 40% increase of a 1% risk ?
    The abstract lacks sufficient information upon which any such conclusion could be made.
    Alternative( sovereign or junk?) bonds declined but what were conditions in global bond markets as a benchmark over the same period ?
    “The security situation has improved insofar as violent civilian fatalities have declined without any concurrent increase in casualties among coalition and Iraqi troops. ” That is a definite positive.
    “However, other areas, such as oil production and the number of trained Iraqi Security Forces have shown no improvement or declined” Did the surge – reported as a localised , Baghdad focused security arrangement ever try to boost such parameters? This study seems to be starting with a reasonable aim but is poorly considered once the areas to be examined were decided on.

  4. Sinclair Davidson says:

    Why do you never cover important research like this?

    Controlling for a wide set of individual- and family-level observables available in the National Longitudinal Study of Adolescent Health, ordinary least squares (OLS) estimates show that sexually active adolescents have grade point averages that are approximately 0.2 points lower than virgins. However, when information on the timing of intercourse decisions is exploited and individual fixed effects are included, the negative effect of sexual intercourse disappears for females, but persists for males. Taken together, the results of this study suggest that while there may be adverse academic spillovers from engaging in intercourse for some adolescents, previous studies’ estimates are overstated due to unmeasured heterogeneity. (JEL I10, I21, I18)

    So I can now tell my parents I did better at school than I would have liked too. 🙂

Comments are closed.