SSDS Training Overview
The SSDS offers various workshops for faculty and graduate students on a recurring basis during the academic year. Faculty interested in having the SSDS help with methodological course work should contact John Daniels, SSDS Statistical Programming Consultant, for more information.
SSDS Workshops are held in the Social Sciences Data Science Lab in SSH 102.
SSDS Workshops
This workshop is for intermediate/advanced Stata users who wish take greater advantage of the extremely versatile scripting language of Stata. While most researchers master writing simple batch scripts to accomplish data manipulations and perform data analyses, quite often the code they produce fails to take full advantage of the many features of Stata scripting language. As a result their programs are often long and inefficient. The purpose of this workshop is to show experienced Stata users how to take advantage of the often untapped script procedures that can render a long repetitive task into a simple elegant solution.
Topics to be covered include: creating "real" do- and ado-files, macros, branching and looping, dealing with matricies, temporary variables, debugging Stata programs, and using Stata programs to deal with repetitive data and analytical problems. The workshop will involve a hands-on tutorial using Stata to write and execute a series of program examples. Those wishing to attend must already be comfortable using Stata and have at least one year of experience using Stata.
Trials and Tribulations of Data Manipulation
The purpose of this workshop is to help researchers cope with data when conducting quantitative analyses. It is not uncommon for researchers to be well versed in statistical methods and yet have very little grasp of how to actually work with data—especially data acquired from external sources such as general archives, governmental organizations, or other researchers. This workshop will introduce researchers to the most likely obstacles they will face when delving into a new dataset and offer solutions on how best to overcome these difficulties.
Topics to be covered include common data problems researchers face, how to diagnose data problems, some quick and easy tools for getting data into shape, and using DBMS/COPY (a powerful data translation software tool) to import data into your favorite statistical program (Stata, SAS, SPSS, etc.). The workshop will include a hands-on tutorial working with DBMS/COPY.
Stata is a widely used statistical software package and while it is not the easiest application to learn, Stata's robust programming environment and statistical procedures make it one of the best statistical applications available for the social science researcher. This workshop is designed to introduce new users to Stata. No previous experience with Stata or statistical programs in general is necessary.
Topics to be covered include how to input data into Stata, data management, statistical analysis, graphing, and writing batch files. The workshop will include hands-on training using Stata. By the end this class, you should have a firm grasp of the fundaments of using Stata.
This workshop is designed to teach the social science researcher all that is necessary to make best use of the SSDS UNIX research systems. Attendees do not need any previous experience with UNIX.
UNIX is the operating system of choice for large central research systems and is particularly well suited for dealing with very large data problems and computationally intensive statistical analysis. An added advantage to using a UNIX research system is users can connect remotely with a thin client over essentially any speed of internet connection and still have access to their data and analytical software.