Abstract
1 Prize announcement
The editors of the Stata Journal are delighted to announce the award of the Editors’ Prize for 2020 to
The aim of the prize is to reward contributions to the Stata community in respect of one or more outstanding articles published in the Journal in the previous three calendar years. For the original announcement of the prize and its precise terms of reference, see Newton and Cox (2012), which is accessible at the following website: http://www.stata-journal.com/sjpdf.html?articlenum=gn0052.
Daniel Klein was born in 1981 in Mainz, near Frankfurt, Germany. He grew up in nearby Wörrstadt, a small town with a population of about 8,000, and attended upper secondary school (gymnasium) in Alzey (population about 18,000) from 1992 to 2001. Klein chose civilian service over military service and worked as a paramedic from 2002 to 2006 (also in Wörrstadt and Alzey). In 2006, he moved to Bamberg in Bavaria, where he studied sociology with a focus on empirical social research methods (with minor subjects in philosophy and statistics) at the Otto-Friedrich-University, receiving his diploma (MA equivalent) in 2012.
Klein moved to the University of Kassel in 2012 to work as a research assistant at the Chair of Methods of Empirical Social Research. From 2017 to 2020, he was a research assistant at the International Centre for Higher Education Research Kassel (INCHER-Kassel). He still works as a research assistant at the same university, although now at the Chair for Health Studies. He expects to complete his PhD in 2021. Some notable publications on his research are listed in the References.
His research interests include social inequality, theoretical models of decisions, and (perhaps most of all) quantitative methods of empirical social research and econometrics. As with many of us, his work morphs into his play: he enjoys programming in Stata and lately also in Python, working out at the gym, and hiking, a recent new hobby. Beyond the articles honored here, he has been active in the Stata community over several years. As of October 2020, he is the single or joint author of 48 packages on the Statistical Software Components archive, which were averaging a total of about 7,000 downloads per month in the summer of 2020. Klein is also a highly active contributor to the Statalist forum (over 2,400 posts from March 2014 to October 2020 alone) and a frequent attender at Stata Users Group meetings.
The award recognizes specifically two outstanding articles by Daniel Klein (2018, 2019a): Implementing a general framework for assessing interrater agreement in Stata. Stata Journal 18: 871–901. Extensions to the label commands. Stata Journal 19: 867–882. We turn now to detailed comments on those articles. Each combines the introduction of a major new Stata command with a thorough but accessible account of the associated principles and substantial examples.
Despite its well-known weaknesses, researchers continuously choose the kappa coefficient (Cohen 1960; Fleiss 1971) to quantify agreement among raters. Part of kappa’s persistent popularity seems to arise from a lack of available alternative agreement coefficients in statistical software packages such as Stata. Klein (2018) reviews Gwet’s (2014) recently developed framework of interrater agreement coefficients. This framework extends several agreement coefficients to handle any number of raters, any number of rating categories, any level of measurement, and missing values. The article introduces the
Coefficients of agreement are one of many small jungles in statistical science, with a substantial but tangled literature over more than 60 years now that is likely to prove confusing to many researchers. See also the wider synthesis of Berry, Johnston, and Mielke (2018). Klein’s concise but also wide-ranging account lucidly surveys the territory, identifying also what is possible so far with both official and community-contributed commands in Stata and going beyond them with his versatile new command
Data management tasks include manipulating variables, variable labels, and value labels. While Stata has versatile commands and functions to address the first task,managing variable and value labels is not always as convenient. Klein (2019a) introduces and exemplifies a new command,
As posts on Statalist often show, Klein is the leading expert in the Stata user community on labels. If there is a challenging label problem, it usually turns out that he has solved it already or can suggest a new solution from his extensive experience. Previous commands in this field from users have often been very specific and even utterly ad hoc. Although like Good (1965, 56) we believe that “real life is both complicated and short, and we make no mockery of honest adhockery,” we still prefer synthesized, systematic approaches such as
In sum, we salute Daniel Klein for outstanding contributions to the Stata community through his recent publications in the Stata Journal. His work draws upon extensive experience in his own research and as reported by the user community, detailed and thorough understanding of problems in both data management and statistical analysis, and excellent programming skills.
As editors, we are indebted to the awardee for biographical material and to necessarily anonymous nominators for most helpful appreciations.