Empirical Legal Studies

"heckman" v. "etregress"

Two-stage modeling if not uncommon in ELS and relevant Stata coding has become quite specialized for subtly distinct contexts. A recent discussion on the Statalist (click here) provides a helpful (if brief) clarity.

The question posed sought modeling advice on estimating "the effect of having a female director on board on earnings management. I have a continuous variable for earnings management as the dependent variable. I want to first predict the probability of having a female board member versus having an all-male board. I am doing this to mitigate the sample selection bias."

The discussion elicits a distinction between the proper use of the "heckman" and "etregress" two-stage commands. While the "heckman" command is used when you observe outcomes for only the treated variable of interest, " the "etregress" command, by contrast, is used when "some outcome is observed for all units."

Advances in Data Selection: Evaluating Police Conduct

While agreement on a common set of metrics facilitates longitudinal studies as well as comparisons across studies, these benefits should not deter fresh new thinking about new sources of data that inform lingering research questions. A new paper by Aurelie Ouss (Penn--criminology) and John Rappaport (Chicago), Is Police Behavior Getting Worse? The Importance of Data Selection in Evaluating the Police, illustrates this point nicely. In it, the authors' analysis of police conduct draws from traditional data sources, including litigation levels and municipal settlement payouts, as well as a relatively new data source: liability insurance claims.

Exploiting 23 years worth of liability insurance data, involving 350 law enforcement agencies and a single insurance carrier, the paper finds that "while lawsuits and [settlement] payouts have trended upwards over the past decade, insurance claims have declined." What the authors conclude is that: "... police behavior is not getting worse; rather, public responses to policing harms are intensifying."

Stata Graphic "Trick" of the Day

For too many (myself included), Stata graphics can be among the more complicated coding tasks. Thus, concrete coding tips for some of the more "exotic" graphics capabilities invariably warrant attention (even if only to satisfy curiosity). In this spirit I pass along a brief discussion concerning coding requirements for a "fan" chart in Stata (here). In an example of what is possible (below), the presentation of a standard "line" chart is graphically enhanced with +/- 1, 2, and 3 standard error "cones."