Template-Type: ReDIF-Article 1.0 Author-Name: Patrick Royston Author-Workplace-Name: University College London Author-Email: j.royston@ucl.ac.uk Title: Power and sample-size analysis for the Royston–Parmar combined test in clinical trials with a time-to-event outcome Journal: Stata Journal Pages: 3-21 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Randomized controlled trials with a time-to-event outcome are usually designed and analyzed assuming proportional hazards (PH) of the treatment effect. The sample-size calculation is based on a log-rank test or the nearly identical Cox test, henceforth called the Cox/log-rank test. Nonproportional hazards (non-PH) has become more common in trials and is recognized as a potential threat to interpreting the trial treatment effect and the power of the log-rank test—hence to the success of the trial. To address the issue, in 2016, Royston and Parmar (BMC Medical Research Methodology 16: 16) proposed a “combined test” of the global null hypothesis of identical survival curves in each trial arm. The Cox/log- rank test is combined with a new test derived from the maximal standardized difference in restricted mean survival time (RMST) between the trial arms. The test statistic is based on evaluations of the between-arm difference in RMST over several preselected time points. The combined test involves the minimum p-value across the Cox/log-rank and RMST-based tests, appropriately standardized to have the correct distribution under the global null hypothesis. In this article, I introduce a new command, power ct, that uses simulation to implement power and sample-size calculations for the combined test. power ct supports designs with PH or non-PH of the treatment effect. I provide examples in which the power of the combined test is compared with that of the Cox/log-rank test under PH and non-PH scenarios. I conclude by offering guidance for sample-size calculations in time-to-event trials to allow for possible non-PH. Keywords: power_ct, randomized controlled trial, time-to-event outcome, restricted mean survival time, log-rank test, Cox test, combined test, treatment effect, hypothesis testing, flexible parametric model File-URL: http://www.stata-journal.com/article.html?article=st0510 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0510/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:3-21 Template-Type: ReDIF-Article 1.0 Author-Name: Jesús Otero Author-Workplace-Name: Universidad del Rosario Author-Email: jesus.otero@urosario.edu.co Author-Person: pot11 Author-Name: Christopher F Baum Author-Workplace-Name: Boston College Author-Workplace-Name: DIW Berlin Author-Email: baum@bc.edu Author-Person: pba1 Title: Unit-root tests based on forward and reverse Dickey–Fuller regressions Journal: Stata Journal Pages: 22-28 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In this article, we present the command adfmaxur, which computes the Leybourne (1995, Oxford Bulletin of Economics and Statistics 57: 559–571) unit-root statistic for different numbers of observations and the number of lags of the dependent variable in the test regressions. The latter can be either specified by the user or endogenously determined. We illustrate the use of adfmaxur with an empirical example. Keywords: adfmaxur, unit-root test, critical values, lag length, p-values File-URL: http://www.stata-journal.com/article.html?article=st0511 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0511/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:22-28 Template-Type: ReDIF-Article 1.0 Author-Name: Bastien Perrot Author-Workplace-Name: University of Nantes Author-Email: bastien.perrot@univ-nantes.fr Author-Name: Emmanuelle Bataille Author-Workplace-Name: University of Nantes Author-Email: emmanuelle.anthoine@chu-nantes.fr Author-Name: Jean-Benoit Hardouin Author-Workplace-Name: University of Nantes Author-Email: jean-benoit.hardouin@univ-nantes.fr Title: validscale: A command to validate measurement scales Journal: Stata Journal Pages: 29-50 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Subjective measurement scales are used to measure nonobservable respondent characteristics in several fields such as clinical research, educational sciences, or psychology. To be useful, the scores resulting from the questionnaire must be validated; that is, they must provide the psychometric properties validity, reliability, and sensitivity. In this article, we present the validscale command, which carries out the required statistical analyses to validate a subjective mea- surement scale. We have also developed a dialog box, and validscale will soon be implemented online with Numerics by Stata. Keywords: validscale, subjective measurements scales, score, psychometrics, validity, reliability File-URL: http://www.stata-journal.com/article.html?article=st0512 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0512/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:29-50 Template-Type: ReDIF-Article 1.0 Author-Name: Laura A. Gray Author-Workplace-Name: University of Sheffield Author-Email: laura.gray@sheffield.ac.uk Author-Name: Mónica Hernández Alava Author-Workplace-Name: University of Sheffield Author-Email: monica.hernandez@sheffield.ac.uk Title: A command for fitting mixture regression models for bounded dependent variables using the beta distribution Journal: Stata Journal Pages: 51-75 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In this article, we describe the betamix command, which fits mixture regression models for dependent variables bounded in an interval. The model is a generalization of the truncated inflated beta regression model introduced in Pereira, Botter, and Sandoval (2012, Communications in Statistics—Theory and Methods 41: 907–919) and the mixture beta regression model in Verkuilen and Smithson (2012, Journal of Educational and Behavioral Statistics 37: 82–113) for variables with truncated supports at either the top or the bottom of the distri- bution. betamix accepts dependent variables defined in any range that are then transformed to the interval (0, 1) before estimation. Keywords: betamix, truncated inflated beta mixture, beta regression, mixture model, cross-sectional data, mapping File-URL: http://www.stata-journal.com/article.html?article=st0513 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0513/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:51-75 Template-Type: ReDIF-Article 1.0 Author-Name: Jesse Wursten Author-Email: jesse.wursten@kuleuven.be Author-WorkPlace-Name: KU Leuven Author-Person: pwu145 Title: Testing for serial correlation in fixed-effects panel models Journal: Stata Journal Pages: 76-100 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Current serial correlation tests for panel models are cumbersome to use, not suited for fixed-effects models, or limited to first-order autocorrelation. To fill this gap, I implement three recently developed tests. Keywords: xtqptest, xthrtest, xtistest, serial correlation, panel time series, fixed effects, higher-order serial correlation File-URL: http://www.stata-journal.com/article.html?article=st0514 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0514/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:76-100 Template-Type: ReDIF-Article 1.0 Author-Name: Carlo Schwarz Author-Email: c.r.schwarz@warwick.ac.uk Author-WorkPlace-Name: University of Warwick Title: ldagibbs: A command for topic modeling in Stata using latent Dirichlet allocation Journal: Stata Journal Pages: 101-117 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In this article, I introduce the ldagibbs command, which implements latent Dirichlet allocation in Stata. Latent Dirichlet allocation is the most popular machine-learning topic model. Topic models automatically cluster text documents into a user-chosen number of topics. Latent Dirichlet allocation represents each document as a probability distribution over topics and represents each topic as a probability distribution over words. Therefore, latent Dirichlet allocation provides a way to analyze the content of large unclassified text data and an alternative to predefined document classifications. Keywords: ldagibbs, machine learning, latent Dirichlet allocation, Gibbs sampling, topic model, text analysis File-URL: http://www.stata-journal.com/article.html?article=st0515 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0515/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:101-117 Template-Type: ReDIF-Article 1.0 Author-Name: Martin Eckhoff Andresen Author-Workplace-Name: Statistics Norway Author-Email: martin.eckhoff.andresen@gmail.com Author-Person: pan546 Title: Exploring marginal treatment effects: Flexible estimation using Stata Journal: Stata Journal Pages: 118-158 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In settings that exhibit selection on both levels and gains, marginal treatment effects (MTE) allow us to go beyond local average treatment effects and estimate the whole distribution of effects. In this article, I survey the theory behind MTE and introduce the package mtefe, which uses several estimation methods to fit MTE models. This package provides important improvements and flexibility over existing packages such as margte (Brave and Walstrum, 2014, Stata Journal 14: 191–217) and calculates various treatment-effect parameters based on the results. I illustrate the use of the package with examples. Keywords: mtefe, margte, heterogeneity, marginal treatment effects, instrumental variables File-URL: http://www.stata-journal.com/article.html?article=st0516 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0516/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:118-158 Template-Type: ReDIF-Article 1.0 Author-Name: Oscar Barriga Cabanillas Author-Workplace-Name: University of California Davis Author-Email: obarriga@ucdavis.edu Author-Name: Jeffrey D. Michler Author-Workplace-Name: University of Saskatchewan Author-Email: jeffrey.michler@usask.ca Author-Person: pmi685 Author-Name: Aleksandr Michuda Author-Workplace-Name: University of California Davis Author-Email: amichuda@ucdavis.edu Author-Name: Emilia Tjernström Author-Workplace-Name: University of Wisconsin Author-Email: tjernstroem@wisc.edu Author-Person: ptj7 Title: Fitting and interpreting correlated random-coefficient models using Stata Journal: Stata Journal Pages: 159-173 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In this article, we introduce the community-contributed command randcoef, which fits the correlated random-effects and correlated random-coef- ficient models discussed in Suri (2011, Econometrica 79: 159–209). While this approach has been around for a decade, its use has been limited by the compu- tationally intensive nature of the estimation procedure that relies on the optimal minimum distance estimator. randcoef can accommodate up to five rounds of panel data and offers several options, including alternative weight matrices for estimation and inclusion of additional endogenous regressors. We also present postestimation analysis using sample data to facilitate understanding and inter- pretation of results. Keywords: randcoef, correlated random effects, correlated random coeffi- cients, technology adoption, heterogeneity File-URL: http://www.stata-journal.com/article.html?article=st0517 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0517/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:159-173 Template-Type: ReDIF-Article 1.0 Author-Name: Jonathan A. Cook Author-Workplace-Name: Public Company Accounting Oversight Board Author-Email: jacook@uci.edu Author-Name: Ashish Rajbhandari Author-Workplace-Name: The Vanguard Group Author-Email: ashish.rajbhandari@vanguard.com Author-Person: pra536 Title: heckroccurve: ROC curves for selected samples Journal: Stata Journal Pages: 174-183 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Receiver operating characteristic (ROC) curves can be misleading when they are constructed with selected samples. In this article, we describe heckroccurve, which implements a recently developed procedure for plotting ROC curves with selected samples. The command estimates the area under the ROC curve and a graphical display of the curve. A variety of plot options are available, including the ability to add confidence bands to the plot. Keywords: heckroccurve, receiver operating characteristic curves, ROC curves, classifier evaluation, sample-selection bias File-URL: http://www.stata-journal.com/article.html?article=st0518 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0518/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:174-183 Template-Type: ReDIF-Article 1.0 Author-Name: Helmut Herwartz Author-Workplace-Name: University of Goettingen Author-Name: Simone Maxand Author-Workplace-Name: University of Goettingen Author-Name: Fabian H. C. Raters Author-Workplace-Name: University of Goettingen Author-Email: raters@uni-goettingen.de Author-Name: Yabibal M. Walle Author-Workplace-Name: University of Goettingen Title: Panel unit-root tests for heteroskedastic panels Journal: Stata Journal Pages: 184-196 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In this article, we describe the command xtpurt, which imple- ments the heteroskedasticity-robust panel unit-root tests suggested in Herwartz and Siedenburg (2008, Computational Statistics and Data Analysis 53: 137–150), Demetrescu and Hanck (2012a, Economics Letters 117: 10–13), and, recently, Herwartz, Maxand, and Walle (2017, Center for European, Governance and Eco- nomic Development Research Discussion Papers 314). While the former two tests are robust to time-varying volatility when the data contain only an intercept, the latter test is unique because it is asymptotically pivotal for trending heteroskedas- tic panels. Moreover, xtpurt incorporates lag-order selection, prewhitening, and detrending procedures to account for serial correlation and trending data. Keywords: xtpurt, xtunitroot, panel unit-root tests, nonstationary volatility, cross-sectional dependence, inflation File-URL: http://www.stata-journal.com/article.html?article=st0519 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0519/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:184-196 Template-Type: ReDIF-Article 1.0 Author-Name: Matthew S. Gillman Author-Workplace-Name: King’s College London Author-Email: matthew.gillman@kcl.ac.uk Title: Some commands to help produce Rich Text Files from Stata Journal: Stata Journal Pages: 197-205 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Producing Rich Text Format (RTF) files from Stata can be difficult and somewhat cryptic. In this article, I introduce commands to simplify this process; one builds a table row by row, another inserts a PNG image file into an RTF document, and the others start and finish the RTF document. Keywords: initiatertf, insertimagertf, addrowrtf, endrtf, Rich Text Format, RTF, automation, PNG, tables, fonts File-URL: http://www.stata-journal.com/article.html?article=pr0068 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/pr0068/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:197-205 Template-Type: ReDIF-Article 1.0 Author-Name: Fernando Rios-Avila Author-Workplace-Name: Levy Economics Institute Author-Email: friosavi@levy.org Author-Person: pri214 Author-Name: Gustavo Canavire-Bacarreza Author-Workplace-Name: Universidad EAFIT Author-Email: gcanavir@eafit.edu.co Author-Person: pca311 Title: Standard-error correction in two-stage optimization models: A quasi–maximum likelihood estimation approach Journal: Stata Journal Pages: 206-222 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Following Wooldridge (2014, Journal of Econometrics 182: 226–234), we discuss and implement in Stata an efficient maximum-likelihood approach to the estimation of corrected standard errors of two-stage optimization models. Specif- ically, we compare the robustness and efficiency of the proposed method with routines already implemented in Stata to deal with selection and endogeneity problems. This strategy is an alternative to the use of bootstrap methods and has the advantage that it can be easily applied for the estimation of two-stage optimization models for which already built-in programs are not yet available. It could be of particular use for addressing endogeneity in a nonlinear framework. Keywords: maximum likelihood estimation, nonlinear models, endogeneity, two-step models, standard errors File-URL: http://www.stata-journal.com/article.html?article=st0520 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0520/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:206-222 Template-Type: ReDIF-Article 1.0 Author-Name: Daniel Gallacher Author-Workplace-Name: University of Warwick Author-Email: d.gallacher@warwick.ac.uk Author-Name: Felix Achana Author-Workplace-Name: University of Warwick Author-Email: F.Achana@warwick.ac.uk Title: Assessing the health economic agreement of different data sources Journal: Stata Journal Pages: 223-233 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In this article, we present a simple-to-use framework for assessing the agreement of cost-effectiveness endpoints generated from different sources of data. The aim of this package is to enable the rapid assessment of routine data for use in cost-effectiveness analyses. By quantifying the comparability of routine data with “gold-standard” trial data, we inform decisions on the suitability of routine data for cost-effectiveness analysis. The rapid identification of informative routine data will increase the opportunity for economic analyses and potentially reduce the cost and burden of collecting patient-reported data in clinical trials. Keywords: heabs, heapbs, health economic agreement, cost-effectiveness analysis File-URL: http://www.stata-journal.com/article.html?article=st0521 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0521/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:223-233 Template-Type: ReDIF-Article 1.0 Author-Name: Matias D. Cattaneo Author-Workplace-Name: University of Michigan Author-Email: cattaneo@umich.edu Author-Person: pca473 Author-Name: Michael Jansson Author-Workplace-Name: University of California at Berkeley Author-Email: mjansson@econ.berkeley.edu Author-Person: pja19 Author-Name: Xinwei Ma Author-Workplace-Name: University of Michigan Author-Email: xinweima@umich.edu Title: Manipulation testing based on density discontinuity Journal: Stata Journal Pages: 234-261 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: In this article, we introduce two community-contributed commands, rddensity and rdbwdensity, that implement automatic manipulation tests based on density discontinuity and are constructed using the results for local-polynomial density estimators in Cattaneo, Jansson, and Ma (2017b, Simple local polyno- mial density estimators, Working paper, University of Michigan). These new tests exhibit better size properties (and more power under additional assump- tions) than other conventional approaches currently available in the literature. The first command, rddensity, implements manipulation tests based on a novel local-polynomial density estimation technique that avoids prebinning of the data (improving size properties) and allows for restrictions on other features of the model (improving power properties). The second command, rdbwdensity, imple- ments several bandwidth selectors specifically tailored for the manipulation tests discussed herein. We also provide a companion R package with the same syntax and capabilities as rddensity and rdbwdensity. Keywords: rddensity, rdbwdensity, falsification test, manipulation test, regression discontinuity File-URL: http://www.stata-journal.com/article.html?article=st0522 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0522/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:234-261 Template-Type: ReDIF-Article 1.0 Author-Name: Nicholas J. Cox Author-Workplace-Name: Durham University Author-Email: n.j.cox@durham.ac.uk Author-Person: pco34 Title: Speaking Stata: Logarithmic binning and labeling Journal: Stata Journal Pages: 262-286 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Histograms on logarithmic scale cannot be produced by an option like xscale(log). You need first to transform the variable concerned with a loga- rithm function. That raises small choices: how to select bin start, bin width, and informative axis labels and titles? Problems and solutions are discussed here in detail. In contrast, for logarithmic scales on other graphs, options xscale(log) and yscale(log) may do most of what you want. But there is usually still scope for “nicer” axis labels than are given by default and indeed scope for differing tastes on what “nice” means. This column introduces the niceloglabels command for helping (even automating) label choice. Historical notes and references are sprinkled throughout. Keywords: niceloglabels, logarithms, axis scales, axis labels, binning, his- tograms, quantile plots, transformations, graphics File-URL: http://www.stata-journal.com/article.html?article=gr0072 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/gr0072/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:262-286 Template-Type: ReDIF-Article 1.0 Author-Name: Alexander Koplenig Author-Workplace-Name: Institute for the German language Author-Email: koplenig@ids-mannheim.de Title: Stata tip 129: Efficiently processing textual data with Stata’s new Unicode features Journal: Stata Journal Pages: 287-289 Issue: 1 Volume: 18 Year: 2018 Month: March File-URL: http://www.stata-journal.com/article.html?article=dm0093 File-Function: link to article purchase Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/dm0093/ Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:287-289 Template-Type: ReDIF-Article 1.0 Author-Name: Editors Author-Email: editors@stata.com Title: Software updates Journal: Stata Journal Pages: 290-291 Issue: 1 Volume: 18 Year: 2018 Month: March Abstract: Updates for previously published packages are provided. Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/dm0078_3/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0279_2/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0336_1/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0337_1/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0351_1/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0378_1/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0493_1/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0496_1/ Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj18-1/st0508_1/ Note: Windows users should not attempt to download these files with a web browser. Handle:RePEc:tsj:stataj:v:18:y:2018:i:1:p:290-291