Empirical Legal Studies

Transforming "Vertical" Regression Output Into a "Horizontal" Table Format

A recent Statalist discussion (here) walks readers through the coding necessary to transform the following (traditionally "vertical") regression output:

-----------------------------------------
                               mpg       
-----------------------------------------
Weight (lbs.)                      -0.006
                       [-0.009    -0.003]
                                     0.00
Displacement (cu. in.)              0.006
                       [-0.014     0.025]
                                     0.57
Turn circle (ft.)                  -0.139
                       [-0.496     0.219]
                                     0.44
Intercept                          43.588
                       [33.688    53.489]
                                     0.00
Number of observations                 74
-----------------------------------------

Into a "horizontal" output format:

-------------------------------------------------------------
                       Coefficient       95% CI       p-value
-------------------------------------------------------------
Weight (lbs.)               -0.006 [-0.009    -0.003]    0.00
Displacement (cu. in.)       0.006 [-0.014     0.025]    0.57
Turn circle (ft.)           -0.139 [-0.496     0.219]    0.44
Intercept                   43.588 [33.688    53.489]    0.00
-------------------------------------------------------------

Options for Small and Unbalanced ("Rare Events") Data Sets

While relogit is a standard "go-to" Stata command when a data set includes "rare events," a threat of bias is enhanced if rare events derive from a "small sample." While bootstraping may be an option for some, a recent Stata listserv discussion (here) emphasizes a pair of commands -- firthlogit and exlogit -- that might make sense for others. Relatedly, Prof. Williams (ND-sociology) helpfully delves into the challenge a bit more comprehensively (here).

"T-Testing" Group Differences at Various Percentiles

While the standard t-test compares means, somewhat less clear is what to do if one wants to test, e.g., whether group differences at various percentiles achieve statistical significance. In a recent Statalist discussion (click here), the specific question posed involves an effort to determine whether “Black-White wealth differences at p10 (10^th percentile) and p90 (90^th percentile)” systematically vary.

Possible options, described in the responses, range from using the qreg and ttest commands.

SCOTUS Database--Updates

The Supreme Court Database, motivated in part by Prof. Harold Spaeth (1930-2017), remains a leading source for Court and judicial decisionmaking scholars. Indeed, "virtually all systematic analyses of the contemporary Supreme Court and its members have relied on it." Given the Database's scholarly prominence, I wanted to pass along a few, brief updates.

First, the Database, which includes information (247 variables) on every SCOTUS decision since the "beginning" (1791), has now been updated to include information on all SCOTUS cases through the 2023 Term. Second, the Database's "home" has migrated from Washington University and, starting with the current (Oct. Term 2024), will be archived at Penn State University (click here).

From PACER to SCALES: Access to Federal Court Data

Even basic research questions on Art.III courts and federal litigation typically confront consequential barriers to needed data (e.g., federal court records). While the federal government's PACER platform and a few third-party operations provide some relief, both possess their own respective shortcomings and limitations (including, but not limited to, cost).

Initial fruits of a new collaborative effort based at Northwestern University, SCALES, have emerged recently. SCALES is an online platform that seeks to "assemble federal court records, systematically organize them and extract key information, and—most importantly—make them freely available to the public." What exists now includes access to information and records for all federal cases initiated in 2016 and 2017. As SCALES' mission includes "to make court records freely accessible to the public," the platform aspires to, in the future, expand coverage to include "all years."

In a recent paper, The SCALES Project: Making Federal Court Records Free, the authors, David Schwartz (Northwestern) et al., explain the SCALES initiative in greater detail. As well, the project also benefits from its own website (click here).

Modeling Panel Data: More Options

While panel data bring with them important benefits, standard modeling challenges necessarily lurk. For example, one can estimate fixed-effects models to control for endogeneity, but at the potential cost of forgoing studying time-invariant variables. Alternatively, one could estimate a random-effects model, but introduce potential bias.

When confronting such a trade-off with panel data, my initial default position is to run two separate models (FE and RE) and assess whether any key results are model-specific. However, other empirical strategies have emerged relatively recently. While I am unsure whether similar coding possibilities exist in R, SAS, or SPSS, Stata's correlated random-effects model (CRE) allows one to estimate both time-varying and time-invariant effects while controlling for endogeneity that arises when variables correlate with unobserved panel-level characteristics. That is, CRE models allow researchers to, in essence, "have it both ways at the same time" by controlling for any endogeneity by including the panel means of time-varying variables as additional controls in the model. For a brief introduction and helpful examples and videos, click here, here, and here.

A Brief Introductory Primer on DiD Models

While treatment effect research designs continue to grow in popularity in various empirical literatures, too many researchers (as well as non-specialists) remain unclear about their objectives. To this end, a recent addition to Stata's instructional video archive includes a brief primer (here) on Stata's DiD commands as well as an easy-to-understand visual explication of what treatment effects models set out to accomplish. This particular video (one in a series) focuses on Stata's two core DiD commands--didregress and xtdidregress;the former command is appropriate for repeated cross-sectional data and the latter for panel data.

Improving Stata Performance When Processessing "Large" Amounts of Data

"Big Data" projects that involve processessing larger and larger data sets impose increased loads onto soft/hardware performance. When it comes to moving large amounts of data through various Stata commands, a recent discussion (here) identifies a few quite easy methods for improving computational performance.

Customizing Stata Tables

While delving into Stata graphics and output (e.g., tables) manipulation is not for the faint-of-heart, as it relates to the latter things recently became a bit easier with Stata's tables command. A three-part video series (click here for Part 1, Part 2; and Part 3) provides some helpful instruction and context. Additional resources also exist (e.g., here and here).

Power Testing

Too often I read papers that consider various explanations for a null result save for an obvious one: sample size. That is, a null result may simply be an artifact of a too small sample. And in some research settings, notably many experimental settings, an ex ante power calculation can inform researchers on the necessary sample size before experiments are executed. A few resources (e.g., here, here, and here) provide some general introductory context and examples.

Periodic General Resources Update-Statistical Analyses

This is another periodic--if too infrequent--reminder to readers about the array of on-line resources available that provide increasingly sophisticated information on a wide variety of questions that span multiple software platforms (e.g., Stata, SPSS, R, MPlus, etc.). One of the major "first-movers" in this space is UCLA's OARC site (click here) which has been a "go-to" of mine for years, especially early on. Resources exist (here) even for those who simply want to more effectively "consume" or interpret various standard statistical output.

Where "vce(cluster var)" and "vce(robust)" Differ and Where They Do Not

A recent discussion on the StataList (here) identifies something of an anomaly when it comes to how "vce()" operates for the xtreg,fe command versus other commands.

As the unfolding discussion notes, when using the xtreg,fe command, vce(cluster var) and vce(robust) operate similarly. With other commands, by contrast, they generally operate differently. The difference emerges because where vce(robust) requires that observations are independent in order for it to be valid, vce(cluster var), by contrast, accommodates and adjusts for correlation of observations within values of groupvar (or "cluster var").

Generating Lagged Variable Values

The need for lagged variables is not uncommon, particularly in the finance and statutory intervention areas or whenever the effective timing of any exogenous event of interest is unclear. How to manipulate an existing variable to generate lagged variants--as well as some common pitfalls--are discussed in a recent StataList discussion (here).

Various Tests for Fixed- v. Random-Effects Model Decision

When assessing whether a model warrants fixed- or random-effects, threats posed by, among other factors, autocorrelation and heteroscedasticity typically loom large. A recent discussion of this topic emerged on the StataList (click here) and considers various approaches.

Nesting v. Clustering: Hospital Data

Both an interesting--and instructive (that is, the response)--brief discussion incident to a question about whether to nest or cluster health care data in a hospital setting emerged recently in the StataList. That a single patient may have been admitted into multiple hospitals over time is yet another complicating wrinkle that warrants attention. One take-away from the discussion is that every detail involving how to structure an analysis requires careful consideration.

New Thinking About an Old Problem: Selection Effects

Keith Hylton (Boston Univ.) and Sanghoon Kim (Buffalo--econ.) distill their recent paper's challenge nicely. When it comes to much of empirical work on legal (and court) outcomes, the full potential of multiple regression "has not been realized, largely because of one reason: the information contained in court opinions comes from a selected sample."

For all the obvious reasons, much of empirical legal research exploits court outcomes as data. One challenge, however, is that the comparatively smaller subset of formal legal disputes that persist to a judicial outcome almost assuredly systematically differs from the much larger subset of legal disputes that privately settle. My former mentor and colleague, Ted Eisenberg, frequently reminded me that "one cannot over-state the importance of selection effects in empirical legal research."

While the challenge endures, solutions are not entirely obvious. In Trial Selection and Estimating Damages Equations, Hylton and Kim develop an interesting suggestion. Specifically, they articulate a structural econometric model that, they argue, better accounts for litigant selections in the appellate context. The paper's abstract follows.

"Many studies have employed regression analysis with data drawn from court opinions. For example, an analyst might use regression analysis to determine the factors that explain the size of damages awards or the factors that determine the probability that the plaintiff will prevail at trial or on appeal. However, the full potential of multiple regression analysis in legal research has not been realized, largely because of the sample selection problem. We propose a method for controlling for sample selection bias using data from court opinions."

Side-By-Side vs. Overlayed Plots

At the risk of delving too deeply into Stata's graphics coding "weeds," two different ways to present the same graphs help illustrate graphing possibilities.

By convention, a "side-by-side" presentation of two distinct, though related, plots (with confidence intervals) in Stata looks like the following:

If the plots are snug enough in how they relate, however, additional coding can produce a single "overlayed" graph:

For those intrigued, the coding underneath these two possibilities is included here.

New Stata Graphing "Toys"

While Stata's graphing capabilities are robust, coding remains complex in places. While the coding "load" has come down a bit over the years, the "bells & whistles" have remained relatively stagnant over the years. One recent change on the "bells & whistles" front involves an increased capacity to "colorize" standard graphs. While the example (below) illustrates how levering color in graphics can enhance (and/or clarify) what the data are telling you, I remain curious about how journals (and their publishers) will choose to deal with the increased production costs associated with color in published papers.

Any potential cost issues aside, a recent Stata newsletter (click here) explains and illustrates (with sample coding) how one can transform a standard twoway scatter plot from this:

To this:

Plotting Coefficients

As I'm seeing more examples of coefficient plots [coefplot command] in the literature (see, e.g., below), I thought the following links might interest some readers. For brief discussions and examples (including Stata coding) click here, here, here, and here.

Plotting Kernal Density Estimates as Colored Areas

By default, kernel density estimates are plotted as lines, meaning curves:

According to recent StataList discussions (see here and here), however, plotting kernal density estimates as "areas" has become the standard in some fields. While for publication purposes the coding requires color, if such a possibility exists the resultant information conveyed is quite helpful as the following example illustrates.

Fixed Effects vs. Random Effects

While debates persist, how fixed- and random-effect estimators differ and what they seek to accomplish, however, remain somewhat muddled in the various empirical literatures. A recent discussion on StataList, however, provides a rare moment of clarity (here) by nudging us to think about fixed- and-random effects as involving different tradeoffs (or preferences) between consistency and efficiency. As one commentator helpfully notes:

"The -fe- estimator is always consistent but inefficient if -re- is the way to go.
 The -re- estimator is inconsistent if -fe- is the way to go."

Skewed Data, Histograms & Axis "Breaks"

While skewed data distributions (e.g., a large proportion of zeros) invite an array of well-known methodological complications, they also complicated data presentation needs. For example, a standard histogram for a distribution that includes approx. 85% zeros looks something like the following:

Setting aside the methodological complications imposed by such skewed data, as it narrowly relates to descriptive data presentation needs one "dissenting" approach is to insert axis "breaks" (discussion here) that generates the following histogram:

Such a strategy may provide the optimal tradeoff between the visualization of "extreme" data and compression of the non-extreme data. This approach also has the virtue of keeping the underlying data in their raw rather than a transformed scale.

"Heatplots" for Correlation Coefficients Graphs

While I've never used one myself, I detect an upward trend in "heatplots" (example below) for basic descriptive correlation coefficient graphs.

A helpful discussion (along with coding suggestions) on what is possible with Stata's heatplot command is found here.

Importing Non-Stata Data Sets Into Stata

While perhaps old-hat for some (many), a quick new Stata tutorial video (click here) walks viewers through some of the basics incident to data importation. For old-time users (including those who may reflexively turn to StatTransfer programs for conversions), increasingly easy--and a wider array of--data transfer options remain much-welcome news.

A Quick Refresher on T- vs. F-Tests

While I haven't thought about this since grad school, a recent discussion on the StataList (here) provides a helpful, quick refresher on when F- and T-Tests converge and when they do not (and why).

An Online Resource of Note

For those new to ELS, and even those with more sophisticated questions, UCLA's statistical consulting site, festooned with an array of resource links (here), remains quite helpful. While the site continues to evolve over time, some well-organized and useful links will help orient and guide those engaged in ELS-related work. Examples include a quick reference chart on "choosing the correct statistical test" (which includes command syntax for SAS, Stata, SPSS, & R), illustrated examples of how to interpret annotated output for standard commands, and robust "FAQ" links that are, again, program-specific (complemented by a "general FAQ" link (here)).

Interpreting DID Output

While one may quibble about how the questioner designed her DID estimation, the question itself--how to understand and interpret standard DID output (in Stata)--elicited some helpful replies in a recent StataList discussion (here).

Poisson Tutorial Videos

The good folks at Stata recently posted a series of video tutorials focusing on how to fit various Poisson regression models which assist when modeling count data. The various videos take up a Poisson model with: a) continuous predictors (here); b) categorical predictors (here); and c) Poisson models that include both continuous and categorical variables (here).

A Small--But Important--Logistical Matter Incident to Dataset Merging

Those who have merged (or appended or crossed) datasets may have inadvertently bumped into a not uncommon problem--where the two separate datasets share a variable with the identical variable label name. For relatively smaller datasets, and where the researcher is aware of this hurdle ex ante, one can always, by hand, rename variables prior to combining the datasets. For larger datasets with many more variables, however, while this may not be practical it nevertheless remains critical.

A recent discussion of how to manage this nettlesome problem is found here. The comments' leading suggestion references Daniel Klein's -elabel- package, available from SSC (as it involves user-written code). Put briefly, the elable command allows a user to add a suffix (e.g., "_1") to every variable name in "dataset1." An analogous manipulation to datast2 can add another unique suffix (e.g., "_2") to every variable name in dataset2. And so forth. The end result includes datasets with distinct variable label names that can then be combined.

Helpful Statistics Resources

On the better late than never front, I just stumbled across a wonderfully rich "one-stop" resource for statistics novices. Germán Rodríguez (Princeton) hosts a site (here) that includes tutorials for both Stata and R. As to the tutorials' scope, the Stata tutorial, e.g., ranges from a "gentle introduction" to coding examples for customizable tables. Many--especially students--may find this resource helpful.

Law School Curriculum: Reform, Assessment, and Research Design

While age-old complaints persist about the basic structure of the first-year law school curriculum, few law schools have dared to experiment with meaningful reforms. Fewer still study these reforms coherently. The "Curriculum B" experiment at Georgetown Law School, as well as a recent paper by David Hyman et al. (Georgetown), Does the 1L Curriculum Make a Difference?, are important and interesting exceptions.

Since 1991, Georgetown Law School has offered an "alternative" Curriculum B along side a standard, more traditional first-year curriculum. Curriculum B was designed to provide “critical” perspectives on the law and respond to important changes in legal practice and theory in the years since the standard 1L curriculum was first developed decades earlier. At Georgetown, students elect into Curriculum B and, when demand exceeds supply, student assignment to Curriculum B is determined by lottery.

For assessment purposes, the quasi-randomized control trial aspect of student assignment to Curriculum B provides a way to overcome selection bias. That is, Hyman et al. compare student outcomes for those who opted into Curriculum B (the treatment group) with student outcomes from those students who wanted to receive the "treatment" (Curriculum B) but, due to excess demand and random selection (lottery), were instead assigned the "placebo" (that is, to the standard, traditional first-year curriculum).

Aside from careful attention to research design, a few of the paper's warrant note. When it comes to students' overall law school academic performances, for example, the authors find that "Curriculum B leads to a mean preserving contraction in students’ overall grades. At the same time, we find that it leads to diminished performance in two key business law electives (Corporations and Securities Regulation)."

Everything You Wanted to Know About Tables (in Stata)

Throughout the second-half of 2021, the Stata Blog ran a 7-part series on generating various tables. A single link to the 7-part series is here.

A "Guide" on how to Interpret Empirical Corporate Governance Scholarship

While empirical work continues to proliferate across an growing array of legal "silos," lawyers (and some law professors) increasingly need to engage with these studies to understand their implications for legal practice and policy implications. This is especially true for corporate governance scholars (and practitioners). As empirical corporate governance work reaches a wider audience, the work intersects with an ever-increasing number of individuals "not trained in econometrics and statistical methods."

This is a problem, and a recent paper endeavors to contribute to a solution. In A Lawyer's Guide to Empirical Corporate Governance, Ofer Eldar (Duke) sets out to provide a general guide that overviews "key empirical strategies for evaluating the relationship between governance and shareholder value, and to demonstrate to lawyers how they can engage with their weaknesses." Critically, the paper identifies a set of three key comparisons that dominate empirical corporate governance scholarship: "(1) comparing firms with and without the governance provisions, (2) evaluating the value of firms before and after adoptions or removals of governance provisions, and (3) evaluating what happens to shareholder value after a legal change."

While papers like these may not be standard empirical legal scholarship, they nonetheless contribute to the field more generally by helping to make empirical scholarship a bit more accessible to those lacking formal empirical training. The abstract follows.

"Empirical studies in corporate law have proliferated in the last two decades, and have had a major impact on legal practice and policy relating to corporate governance. As a result, lawyers increasingly engage with these studies in order to understand their implications for legal practice and policy. This is often challenging because most lawyers are not trained in econometrics and statistical methods, and thus, there is a risk that they misinterpret these studies and their implications. These studies, while critical for evaluating different corporate governance regimes, suffer from well-known weaknesses. The purposes of this guide are to provide an overview of the key empirical strategies for evaluating the relationship between governance and shareholder value, and to demonstrate to lawyers how they can engage with their weaknesses. The main theme of the guide is that largely all empirical strategies are based on three key intuitive comparisons: (1) comparing firms with and without the governance provisions, (2) evaluating the value of firms before and after adoptions or removals of governance provisions, and (3) evaluating what happens to shareholder value after a legal change. By identifying these basic comparisons and the roles they play in the key methodologies for evaluating shareholder value, lawyers will be better positioned to assess empirical studies and evaluate their implications for legal policy."

Graphics, Options, and Color

While Stata's graphics options (and related coding) have always struck me as unnecessarily complex, others seem to be inspired by them. While in the past "color options" involved monochromatic versus gray-scale, journals increasingly permit actual "color" options. Thus, to this end, I want to pass along a pair of related, though distinct, StataList discussions describing (with helpful coding)  various basic color options for box-plots and histograms.

Marginal Effects

While journals have traditionally focused on a key variable's direction and statistical significance, over time an increasing number of journal editors (and reviewers) ask for explications of a variable's substantive and "practical" influence. This trend is unlikely to abate anytime soon. And this is precisely where marginal effects (and Stata's margins command) come into play.

While no longer a new topic, I want to pass along the following resource, Using Stata’s Margins Command to Estimate and Interpret Adjusted Predictions and Marginal Effects, by Richard Williams (Notre Dame--sociology). The document is, at once, accessible, thorough, and yet not over-bearing as it walks readers through the basics of the  margins command. The presentation is greatly enhanced by step-by-step illustrations and the necessary coding. In all, quite a helpful resource for those seeking a quick tutorial.

Visual Displays of Uncertainty

A recent post on Gelman's Stats blog (by Jessica Hullman) nicely merges a few critical threads. One involves Tufte's classic push to display data in creative and informative ways (see, e.g., Tufte's classic). Another relates to a detectable nudge towards emphasizing results' "uncertainty" rather than a "false" sense of "precision" through, say, point estimates. While Jessica's discussion dwells on election forecast uncertainty--and interesting ways to visually convey it--the basic point includes obvious spill-over implications. As well, even if one is persuaded that visually conveying uncertainty is a worthwhile objective, the question about whether withholding point estimates a good idea is not easily answered.

Ways to Approach (and "Interpret") Null Results

"Null" results are a species of output that remains comparatively under-explored. Or, more accurately, how much analytic weight null results can plausibly bear (and/or how to "interpret" null findings) quickly invite complex questions that frequently derail into other, related lines of inquiry (the very concept of "yes/no" statistical "significance", power testing, etc.) As is often the case, at bottom some level of judgment and discernment is required. This general topic was the subject of a recent StataList discussion (here).

Potential Research Projects

While The De-licensing of Occupations in the United States: A Shifting Trend?, by Robert Thornton (Lehigh—Business) et al., is a brief and purely descriptive paper, it identifies a timely topic and, in so doing, also identifies possible future empirical projects.

While a traditional focus for economists, “occupational licensing has begun to attract a growing and sometimes vocal stream of critics.” The standard set of criticisms are relatively well-rehearsed. “It has been alleged that too many occupations now require a license to practice and that the requirements for attaining a license in terms of costs and length of training are often excessive. Complaints have also been made that higher prices for the services provided by licensed practitioners are too often the result, and that the benefits to consumers in terms of higher quality are either small or nonexistent. Finally, it has been charged that excessive licensing has resulted in adverse effects on employment opportunities, intergenerational mobility, and worker mobility, especially for those with lower levels of education.”

While the state legislatures have been slow to respond to such critiques, since 2011 state legislative responses have accelerated. “The result has been that 35 occupations have become delicensed in a total of seven states over the past five years.” While this paper only sets out to identify where de-licensing efforts have succeeded, the paper’s sourcing also identifies possible avenues of empirical research down the road assessing, e.g., the costs and benefits incident to occupational licensing requirements and delicensing.

"Count" Variables & Dispersion

In many ELS contexts, count data are noted over-dispersion. In many legal settings this issue presents in the form of a "zeros-problem." When such a "skewed, count" dependent variable arises, various approaches include: negative binomial, Poisson, and zero-inflated regression estimations. A recent discussion of this general topic on the StataList (here) includes a robust back-and-forth about the relative strengths and weaknesses of various approaches. The claim that Poisson regression is not inappropriate when there is overdispersion in the dependent variable is forcefully defended. (For an earlier discussion of this general topic click here.)

Multi-Level (Mixed) Modeling v. Regress & Cluster

When it comes to decisions between, e.g., a "-mixed- or a -regress and cluster- approach," what is increasingly clear (to me, anyway--and reflected in a helpful StataList discussion here) is that no firm, hard rules exists. What is clear, however, is that model specification decisions need to pivot on a granular understanding of the data and their underlying structure.

One classic context that frequently gives rise to such a decision involves efforts to assess student-level educational outcomes given hypothesized varied influences at the classroom- and school-levels into which the individual students nest. While a regression and clustering specification may yield results similar to a multi-level specification under certain circumstances (e.g., "if intraclass correlations at the school and class levels are very close to zero"), as the comments note: "The -regress- approach, even with -vce(cluster ...)- does not adjust for potential confounding due to systematic differences among classes or schools. The -mixed- model does so."

Data Familiarization/Visualization

A recent post by Jessica Hullman (here) served as my most recent periodic reminder about the enduring need for folks (myself included) to take a few, basic, simple steps to become more familiar with the underlying structure of and relationships among critical data points. Tukey's elegant tables and figures notwithstanding, what is perhaps more important is what follows from Tukey's general impulse: Sometimes simple data plots can unlock key analytic insights. And even if such insights aren't necessary for the researcher, readers' (and journal editors') interests should not be taken for granted.

In trying to explain why researchers might ignore--or bypass--simple initial data visualization/familiarization steps, Hullman points to "latent beliefs that plotting data is somehow inferior to anything that feels more like math. And because making plots for the sake of checking what the data look like or discovering things you didn’t expect seems disconnected and even distracting from the ultimate goal of fitting some model." That such beliefs may be entirely understandable, however, does not detract from their potential harm. It remains awfully difficult to overestimate the value of simple, Tukey-inspired data familiarization/visualization efforts.

Another Neat Stata Output "Trick"

A long-time ELS Blog reader, Jeff Yates (SUNY-Binghamton), alerted me to another under-appreciated command that can make life a bit easier for those needing/desiring to convert Stata results into Word docs.  asdoc is a Stata program that makes it easy to send output from Stata to MS Word by creating publication-ready tables from such Stata commands as summarize, correlate, tabstat, cross-tabs, regressions, t-tests, flexible table, as well as others. More information can be found here. To access (or update) the command:

ssc install asdoc, update

Some Stats Humor

(Thanks to: https://xkcd.com/2048/)

"Listening" to Data

Prior to embarking on any sophisticated analyses I invariably urge my students (and, frankly, colleagues as well) to take some time to get "underneath" and "a feel for" the data and how they distribute. For decades this typically included the standard suite of the related line, scatter-plot, box-plot, histograms, etc., commands.

While the original version has been around for a while, a user-written Stata command, stripplot, was recently updated. According to Nick Cox, "[t]he aim is to compare distributions and a variety of displays is possible, including linear and stacked dot and strip plots, with in conjunction box plots or confidence intervals." An example follows:

The example above includes a hybrid box and quantile plot, with the reference lines indicating medians. A more detailed description (with additional examples and coding) is found here.

Stata Graphics Resource

Given the "degree of difficulty" users confront when working with Stata's notoriously complex graphic commands--something I've long-complained about--it is difficult to overstate my delight at stumbling upon an extraordinarily helpful resource: Maarten Buis' (Univ. Konstanz) the "Graphics in Stata" website (click here). This is an exceedingly helpful resource that speaks to a wide array of common (and more sophisticated) practical Stata graphing challenges. What makes this resource especially useful is that it includes the actual coding (with public data) necessary to make concrete changes to graphs. For example, it walks readers through the coding needed to change these side-by-side graphs:

into this unified graph:

A Quick "Margins" and "Marginsplot" Primer

Editors and referees (including, though with far less frequency, student law review editors) increasingly ask for more intuitive (and, frankly, visual) displays of empirical results. What presently dominates in the Stata world include the margins and marginsplot commands. And for anyone interested in seeing a few examples that illustrate how these two commands can, in Chuck Huber's words, "revolutionize" the presentation of regression (or other) results, I haven't come across anything more helpful than this quick video.

All About Multilevel Modelling Resources

With an admitted bias for "one-stop" resource sites, I recently came across a very thorough (and thoroughly helpful) site sponsored by the University of Bristol's (UK) Centre for Multilevel Modeling (here). Multilevel modelling's usefulness for many ELS research projects is as acute as it is obvious. The site teems with an array of focused resources, including a deep pool of useful online instructional videos (here). For anyone interested in a brief overview of multilevel modelling, this quick explanatory video (here) might be one place to start; a series of PowerPoint presentations (found here) is another.

A Research Request

Prompted partly by an earlier post (here) remarking on how the COVID-19 crisis "and the near-universal (and simultaneous) reaction of U.S. law schools to turn to on-line instruction may provide quasi-experimental research design opportunities," two loyal ElsBlog readers, John Bliss (Denver) and David Sandomierski (Western Ontario), who are launching a research project relating to law school grading policy changes, asked that I share the following survey research request, which I am happy to do:

"We write to ask for your help filling out a brief, anonymous research survey. Many law schools have recently changed their grading schemes in response to COVID-19, suspending their normal grading system in favor of pass/fail or honors/pass/fail systems. Our survey asks what considerations went into your choice of grading scheme and how you expect this change to impact your students.

The survey is anonymous and will be reported anonymously. You may complete the survey by clicking on this link: https://uwo.eu.qualtrics.com/jfe/form/SV_9H4HYsRjqVq3LUN?Source=pers&ID=JB.

We thank you for considering this and look forward to sharing the results!

Many thanks,"

Professor John Bliss (University of Denver Sturm College of Law)

Professor David Sandomierski (University of Western Ontario Faculty of Law)

The Empirics of Legal Education: Australia 2000-2016

A forthcoming book chapter by Alex Steel (Univ. New South Wales), Imperatives for Legal Education: Then, Now and Tomorrow, surveys empirical studies focusing on various aspects of legal education in Australia. In so doing, the chapter also sheds indirect light on two other broader themes. One is the growing internationalization of empirical legal studies, broadly understood. A second is an increasingly self-conscious turn to submit legal education to rigorous empirical study. It is one thing for empirical legal scholars to explore legal theory, doctrine, and institutions from an empirical perspective. Deploying this perspective inward--and assessing whether and, if so, how, legal education achieves its various objectives--warrants note. On a related--though distinct--point, my sense is that the external shock imposed by the COVID-19 crisis and the near-universal (and simultaneous) reaction of U.S. law schools to turn to on-line instruction may provide quasi-experimental research design opportunities. The paper's abstract follows.

"Recent decades have seen a growing understanding that legal education can be improved and informed by empirical analysis of curriculum design, teaching approaches, student learning strategies and broader contextual factors. However, access to that analysis has been impeded by a lack of broad awareness of its existence and difficulty in locating publications.

This chapter provides a review of empirically based studies into Australian legal education from 2000–2017. The analysis demonstrates a significant rise in empirically based publications and an increasing sophistication with empirical methods. The chapter highlights trends in subjects examined empirically, the most commonly used methods, and publications where such analyses are most commonly found.

In order to make this research more available, in appendixes the chapter also lists the full database of empirical legal research publications on which the analysis was based."

Turning a Typical Stata Work Session Into A Do-File

Maybe others already knew this; I did not. As a multi-decade Stata user I've periodically had to transfer various past commands from my active window to a particular project's do-file. Doing so archives my analytical work on a project, helps me recall how I generated a specific set of results/tables/graphs, etc., and, concurrently, facilitates subsequent replication efforts (by me or anyone else). Until now to do so I've simply, and in an admittedly plodding-like and wholly inefficient manner, essentially hand "cut-and-paste" from the active window onto a separate do-file window. What I did not know--until a few hours ago--is that Stata has "buried" a way to accomplish all of this seamlessly and with a few mouse-clicks. This short Stata YouTube video (click here) shows how it's done.