Members of the Harvard Business School community can now access the Wharton Research Data Services (WRDS) platform via Stata. Stata connects to WRDS through ODBC, a standard application programming interface for accessing database management systems. For this reason, it is important to follow these comprehensive step-...
RCS recently partnered with Research Staff Services and Baker Knowledge and Library Services to provide incoming Research Associates with a new training on the Research Data Management (RDM) lifecycle. The training covered best practices for research projects from planning for data acquisition to data archiving. Materials from the training, including slides and handouts, are ... Read more about Research Data Management Training Materials Available
Members of the RCS team recently participated in Harvard’s Analytics Staff Consortium (ASC) event “Better Data Communication,” presented by Jon Schwabish, a leader in the area of policy-relevant data visualizations.
Dr. Schwabish outlined actionable and practical tips for visualizations and presentations that focus on
If you're interested in learning MATLAB, MathWorks is providing a free two hour self-paced tutorial for beginners on their website. The tutorial covers topics from basic commands, importing data, plotting data, and more. For more information, please see the... Read more about Free MATLAB Basics Self-Paced Tutorial
For researchers who are working with observational data and are interested in causal effects, Stata has a set of treatment effect commands that can help. Among these commands, there is a particular interest in matching. How do these commands work? This blog shows you some examples of some of these commands, and how to replicate them step by step: https://...
The EXPLAIN statement is a very useful tool in SQL databases to help users better understand what's going on in queries and where to apply tweaks. For example, the output of EXPLAIN can help you decide where to add indexes and can quickly remedy slow queries by telling you the join type, the possible indexes to choose vs. the index actually chosen, the estimate of rows to be examined, etc.