The challenges in statistics and data science are rapidly growing because access to a multitude of data types continues to increase, as well as the sheer quantity of data. Analysts are now presented with multivariate data, sometimes measured repeatedly, and often requiring the ability to model nonlinear relationships and hierarchical structures. In this article, I present the merlin command, which

In this article, we describe jackknife2, a new prefix command for jackknifing linear estimators. It takes full advantage of the available leave-one-out formula, thereby allowing for substantial reduction in computing time. Of special note is that jackknife2 allows the user to compute cross-validation and diagnostic measures that are currently not available after ivregress 2sls, xtreg, and xtivregress

In this article, we describe the two new commands cngcode and cnaddress, which can be used to link Chinese addresses to locations defined by their longitudes and latitudes through Baidu Map API v3.0 (http://api.map.baidu.com), an online map and navigation system widely used in China. cngcode transfers Chinese addresses to locations, whereas cnaddress does the opposite. These two commands make it easier

When considering multiple-hypothesis tests simultaneously, standard statistical techniques will lead to overrejection of null hypotheses unless the multiplicity of the testing framework is explicitly considered. In this article, we discuss the Romano–Wolf multiple-hypothesis correction and document its implementation in Stata. The Romano–Wolf correction (asymptotically) controls the familywise error

In this article, I build on the work of Abadie and Gardeazabal (2003, American Economic Review 93: 113–132) and Abadie, Diamond, and Hainmueller (2010, Journal of the American Statistical Association 105: 493–505), extending the synthetic control method for program evaluation—implemented in Stata via the community-contributed command synth—to the case of a nonparametric identification of the synthetic

In this article, we introduce the Stata (and R) package rdmulti, which consists of three commands (rdmc, rdmcplot, rdms) for analyzing regression-discontinuity (RD) designs with multiple cutoffs or multiple scores. The command rdmc applies to noncumulative and cumulative multicutoff RD settings. It calculates pooled and cutoff-specific RD treatment effects and provides robust biascorrected inference

Data collection and cleaning workflows implement highly repetitive but extremely important processes. In this article, we introduce iefieldkit, a package developed to standardize and simplify best practices for high-quality primary data collection across the World Bank’s Development Research Group Impact Evaluations department. iefieldkit automates error-checking for electronic Open Data Kit-based

In cross-sectional time-series data with a dichotomous dependent variable, failing to account for duration dependence when it exists can lead to faulty inferences. A common solution is to include duration dummies, polynomials, or splines to proxy for duration dependence. Because creating these is not easy for the common practitioner, I introduce a new command, mkduration, that is a straightforward

The popularity of GitHub is growing, among not only software developers but also statisticians and data scientists. In this article, I discuss why social coding platforms such as GitHub are preferable for developing, documenting, maintaining, and collaborating on statistical software. Furthermore, I introduce the github command version 2.0 for Stata, which facilitates building, searching, installing

Researchers often want to examine the relationship between a variable of interest and multiple related outcomes. To avoid problems of inference that arise from testing multiple hypotheses, one can create a summary index of the outcomes. Summary indices facilitate generalizing findings and can be more powerful than individual tests. In this article, we introduce a command, swindex, that implements the

In this article, we describe the xtfesing command. The command implements a generalized method of moments estimator that allows exploiting singleton information in fixed-effects panel-data regression as in Bruno, Magazzini, and Stampini (2020, Economics Letters 186: Article 108519).

In this article, we describe the implementation of fitting partially linear functional-coefficient panel models with fixed effects proposed by An, Hsiao, and Li [2016, Semiparametric estimation of partially linear varying coefficient panel data models in Essays in Honor of Aman Ullah (Advances in Econometrics, Volume 36)] and Zhang and Zhou (Forthcoming, Econometric Reviews). Three new commands xtplfc

Two commands in official Stata, foreach and forvalues, provide structures for looping through lists of values (variable names, numbers, arbitrary text) and repeating commands using members of those lists in turn. These commands may be used interactively, and none is restricted to use in Stata programs. They are explained and compared in some detail with a variety of examples. In addition, a self-contained

Stata users produce graphs (often called figures) for their presentations and publications. Many such figures are composites with two or more separate panels, so that figure 1 is a composite of figure 1a, 1b, 1c, and 1d. There are two main ways to create such composites in Stata: using a by() option or using graph combine on previously created graphs. There are also commands such as graph matrix whose

To compare distributions of ordinal data such as individuals’ responses on Likert-type scale variables summarizing subjective well-being, we should not apply the toolbox of methods developed for cardinal variables such as income. Instead, we should use an analogous toolbox that accounts for the ordinal nature of the responses. In this article, I review these methods and introduce a new command, ineqord

In this article, we introduce a new command, sfcount, to fit count-data stochastic frontier models. Although originally designed to estimate production and production-cost functions, this new command can be used to estimate mean regression functions when count data are suspected to be underreported or over-reported.

Artificial effect-size magnification (ESM) may occur in underpowered studies, where effects are reported only because they or their associated p-values have passed some threshold. Ioannidis (2008, Epidemiology 19: 640–648) and Gelman and Carlin (2014, Perspectives on Psychological Science 9: 641–651) have suggested that the plausibility of findings for a specific study can be evaluated by computation

In this article, we describe and implement the local Whittle and exact local Whittle estimators of the order of fractional integration of a time series.

Philips, Rutherford, and Whitten (2016, Stata Journal 16: 662–677) introduced dynsimpie, a command to examine dynamic compositional dependent variables. In this article, we present an update to dynsimpie and three new adofiles: cfbplot, effectsplot, and dynsimpiecoef. These updates greatly enhance the range of models that can be estimated and the ways in which model results can now be presented. The

In this article, I propose a new test for power-law behavior. The statistical test, pwlaw, is locally optimal if the possible alternative distributions are contained in the Pareto type (IV) family. After deriving the test, I examine four classical datasets: the frequency of unique words in an English text (Moby Dick); the human populations of U.S. cities; the frequency of U.S. family names; and the

In this article, we describe the use of ivmediate, a new command to estimate causal mediation effects in instrumental-variables settings using the framework developed by Dippel et al. (2020, unpublished manuscript). ivmediate allows estimation of a treatment effect and the share of this effect that can be attributed to a mediator variable. While both treatment and mediator can be potentially endogenous

In this article, I describe the escount command, which implements the estimation of an endogenous switching model with count-data outcomes, where a potential outcome differs across two alternate treatment statuses. escount allows for either a Poisson or a negative binomial regression model with lognormal latent heterogeneity. After estimating the parameters of the switching regression model, one can

Nonparametric regressions are powerful statistical tools that can be used to model relationships between dependent and independent variables with minimal assumptions on the underlying functional forms. Despite their potential benefits, these models have two weaknesses: The added flexibility creates a curse of dimensionality, and procedures available for model selection, like crossvalidation, have a

A few years ago, we developed metaan, a package to perform fixedor random-effects meta-analysis. In terms of random-effects meta-analysis, it offered a wide choice of models, including maximum likelihood, profile likelihood, or restricted maximum-likelihood, in addition to the established DerSimonian–Laird method available in metan or Cochrane’s RevMan software. Other unique features included a wide

In this article, we introduce a command, tssreg, that conducts nonparametric series estimation and uniform inference for time-series data, including the case with independent data as a special case. This command can be used to nonparametrically estimate the conditional expectation function and the uniform confidence band at a user-specified confidence level, based on an econometric theory that accommodates

The mslt command calculates the functions of a multistate life table and plots a graph of conditional and unconditional life expectancies by time. The command provides linear and exponential solutions to estimate the number of individuals, transitions, probabilities, person-years, and years of life in a given cohort and state of occupancy. The input data are time-specific transition rates (or survivorship

Whether a variable is in fact constant—so that it takes on exactly the same value in different observations—is of common concern in statistical work. The question may arise for all the observations in a dataset or for different subsets of the dataset. It may arise because constancy is desirable or because constancy is undesirable, but either way we often need to check simply and quickly. In this column

gr0066_2. Speaking Stata: Multiple bar charts in table form. N. J. Cox. Stata Journal 17: 779; 16: 491–510.

In this article, we describe how to fit panel-data ordered logit models with fixed effects using the new community-contributed command feologit. Fixed-effects models are increasingly popular for estimating causal effects in the social sciences because they flexibly control for unobserved time-invariant heterogeneity. The ordered logit model is the standard model for ordered dependent variables, and

In this article, we present a new command, qcte, that implements several methods for estimation and inference for quantile treatment-effects models with a continuous treatment. We propose a semiparametric two-step estimator, where the first step is based on a flexible Box–Cox model, as the default model of the command. We develop practical statistical inference procedures using bootstrap. We implement

In this article, we present the eqregsel command, which estimates and provides bootstrap inference for sample-selection models via extremal quantile regression. eqregsel estimates a semiparametric sample-selection model without an instrument or a large support regressor and outputs the point estimates of the homogeneous linear coefficients, their bootstrap standard errors, and the p-value for a specification

Coefficient plots are a popular tool for visualizing regression estimates. The appeal of these plots is that they visualize confidence intervals around the estimates and generally center the plot around zero, meaning that any estimate that crosses zero is statistically nonsignificant at least at the alpha level around which the confidence intervals are constructed. For models with statistical significance

markdoc is a general-purpose literate programming package for generating dynamic documents, dynamic presentation slides, Stata help files, and package vignettes in various formats. In this article, I introduce markdoc version 5.0, which performs independently of any third-party software, using the mini engine. The mini engine is a lightweight alternative to Pandoc (MacFarlane [2006, https://pandoc

Cluster randomized trials, where clusters (for example, schools or clinics) are randomized to comparison arms but measurements are taken on individuals, are commonly used to evaluate interventions in public health, education, and the social sciences. Analysis is often conducted on individual-level outcomes, and such analysis methods must consider that outcomes for members of the same cluster tend to

In this article, we describe how to test for the presence of measurement error in explanatory variables. First, we discuss the test of such hypotheses in parametric models such as linear regressions and then introduce a new command, dgmtest, for a nonparametric test proposed in Wilhelm (2018, Working Paper CWP45/18, Centre for Microdata Methods and Practice, Institute for Fiscal Studies). To illustrate

In this article, I describe the lclogit2 command, an enhanced version of lclogit (Pacifico and Yoo, 2013, Stata Journal 13: 625–639). Like its predecessor, lclogit2 uses the expectation-maximization algorithm to fit latent class conditional logit (LCL) models. But it executes the expectation-maximization algorithm’s core algebraic operations in Mata, so it runs considerably faster as a result. It also

Vector autoregression (VAR) estimation is a vital tool in economic studies. VARs, however, can be dimensionally cumbersome and overparameterized. The vgets command allows for a general-to-specific estimation of VARs— overcoming the potential overparameterization—and provides tests for Granger causality, estimates of the long-run effects, and the cumulative impulse–response of each variable in the system;

Self-reported survey data are often plagued by the presence of heaping. Accounting for this measurement error is crucial for the identification and consistent estimation of the underlying model (parameters) from such data. In this article, we introduce two commands. The first command, heapmph, estimates the parameters of a discrete-time mixed proportional hazard model with gammaunobserved heterogeneity

In this article, we introduce the commands twexp and twgravity, which implement the estimators developed in Jochmans (2017, Review of Economics and Statistics 99: 478–485) for exponential regression models with two-way fixed effects. twexp is applicable to generic n × m panel data. twgravity is written for the special case where the dataset is a cross-section on dyadic interactions between n agents

A previous column (Cox, 2009, Stata Journal 9: 137–157) gave a review of methods for working rowwise in Stata. Here rows means observations in a dataset, and the concern is calculations in each observation with a bundle of variables. For example, a row mean variable can be generated as the mean of some numeric variables in each observation. This column is an update. It is briefly flagged that official

dm0048_4: Finding variables. N. J. Cox. Stata Journal 15: 605; 12: 167; 10: 691; 10: 281–296.

Date: Thursday, July 30, and Friday, July 31, 2020

The editors of the Stata Journal are pleased to invite nominations for their 2020 prize in accordance with the following rules. Nominations should be sent as private email to [email protected]com by July 31, 2020.

Random forests (Breiman, 2001, Machine Learning 45: 5–32) is a statistical- or machine-learning algorithm for prediction. In this article, we introduce a corresponding new command, rforest. We overview the random forest algorithm and illustrate its use with two examples: The first example is a classification problem that predicts whether a credit card holder will default on his or her debt. The second

In this article, I extend the theory of added-variable plots to three panel-data estimation methods: fixed effects, between effects, and random effects. An added-variable plot is an effective way to show the correlation between an independent variable and a dependent variable conditional on other independent variables. In a multivariate context, a simple scatterplot showing x versus y is not adequate

Recentered influence functions (RIFs) are statistical tools popularized by Firpo, Fortin, and Lemieux (2009, Econometrica 77: 953–973) for analyzing unconditional partial effects on quantiles in a regression analysis framework (unconditional quantile regressions). The flexibility and simplicity of these tools have opened the possibility to extend the analysis to other distributional statistics using

In this article, we present ppmlhdfe, a new command for estimation of (pseudo-)Poisson regression models with multiple high-dimensional fixed effects (HDFE). Estimation is implemented using a modified version of the iteratively reweighted least-squares algorithm that allows for fast estimation in the presence of HDFE. Because the code is built around the reghdfe package (Correia, 2014, Statistical

Errors-in-variables (EIV) regression is a standard method for consistent estimation in linear models with error-prone covariates. The Stata commands eivreg and sem both can be used to compute the same EIV estimator of the regression coefficients. However, the commands do not use the same methods to estimate the standard errors of the estimated regression coefficients. In this article, we use analysis

Receiver operating characteristic (ROC) curves are commonly used to evaluate predictions of binary outcomes. When there is a small percentage of items of interest (as would be the case with fraud detection, for example), ROC curves can provide an inflated view of performance. This can cause challenges in determining which set of predictions is better. In this article, we discuss the conditions under

We introduce the command xtserialpm to perform the portmanteau test developed in Jochmans (2019, Cambridge Working Papers in Economics No. 1993, University of Cambridge, Faculty of Economics). The procedure tests for serial correlation of arbitrary form in the errors of a linear panel model after estimation of the regression coefficients by the within-group estimator. The test is designed for short

In this article, we introduce the evalue package, which performs sensitivity analyses for unmeasured confounding in observational studies using the methodology proposed by VanderWeele and Ding (2017, Annals of Internal Medicine 167: 268–274). evalue reports E-values, defined as the minimum strength of association on the risk-ratio scale that an unmeasured confounder would need to have with both the

In this article, we introduce lassopack, a suite of programs for regularized regression in Stata. lassopack implements lasso, square-root lasso, elastic net, ridge regression, adaptive lasso, and postestimation ordinary least squares. The methods are suitable for the high-dimensional setting, where the number of predictors p may be large and possibly greater than the number of observations, n. We offer

Concatenation, or joining together, of strings or other values, possibly with extra punctuation such as spaces, is supported in Stata by addition of strings and by the egen function concat(), which concatenates values of variables within observations. In this column, I discuss basic techniques for concatenating values of variables over observations, emphasizing simple loops that can be tuned to suit

st0399_1: Estimation of mean health care costs and incremental cost-effectiveness ratios with possibly censored data. S. Chen, J. Rolfes, and H. Zhao. Stata Journal 15: 698–711.

The editors of the Stata Journal are delighted to announce the award of the Editors’ Prize for 2019 to Matias D. Cattaneo.

Lewbel (2012, Journal of Business and Economic Statistics 30: 67–80) provides a heteroskedasticity-based estimator for linear regression models containing an endogenous regressor when no external instruments or other such information is available. The estimator is implemented in the command ivreg2h by Baum and Schaffer (2012, Statistical Software Components S457555, Department of Economics, Boston

Many applications involve a censored dependent variable, an endogenous independent variable, or both. Chernozhukov, Fernández-Val, and Kowalski (2015, Journal of Econometrics 186: 201–221) introduced a censored quantile instrumental-variable (CQIV) estimator for use in those applications. The estimator has been applied by Kowalski (2016, Journal of Business & Economic Statistics 34: 107–117), among

Royston et al.’s (2011, Trials 12: 81) multiarm, multistage (MAMS) framework for the design of randomized clinical trials uses intermediate outcomes to drop research arms early for lack of benefit at interim stages, increasing efficiency in multiarm designs. However, additionally permitting interim evaluation of efficacy on the primary outcome measure could increase adoption of the design and result

In this article, I introduce the medadhere command, which computes medication adherence rates for two commonly used measures in research and practice: the medication possession ratio and the proportion of days covered. medadhere computes adherence rates for a single medication or multiple medications, and its options provide great flexibility to support the specific needs of the user.