% pubman genre = book-item @incollection{item_3335814, title = {{Managing historical linguistic data for computational phylogenetics and computer-assisted language comparison}}, author = {Tresoldi, Tiago and Rzymski, Christoph and Forkel, Robert and Greenhill, Simon J. and List, Johann-Mattis and Gray, Russell D.}, language = {eng}, isbn = {9780262366076}, doi = {10.7551/mitpress/12200.001.0001}, publisher = {The MIT Press}, address = {Massachusetts}, year = {2022}, date = {2022}, abstract = {{The popularisation of computer-based methods in comparative linguistics has led to a greater awareness of issues resulting from limited data sustainability and proper data management. In this use-case and its accompanying tutorial, we present principles of data management as applied to computational phylogenetics and computer-assisted language comparison, showcasing the solutions we recommend. Instead of enumerating the many possibilities to code and use linguistic data to conduct a phylogenetic analysis, we illustrate our suggestions for phylogenetic data management in a workflow based on a concrete analysis, showing how data should be managed with the help of a published dataset, exploring the information, file formats, processes, and software involved, explaining and showing how to collect and store cross-linguistic information, how to guarantee that datasets are cross-linguistically comparable, how to store intermediate and final results of the analyses, and how to share data in a reusable form by relying in the tools and principles of the CLDF initiative.}}, booktitle = {{The open handbook of linguistic data management}}, note = {author: Collister, Lauren B.}, editor = {Berez-Kroeker, Andrea L. and McDonnel, Bradley and Koller, Eve}, pages = {345--354}, }