Welcome to Data Management Methods in Health Research Studies. Through this course each student will acquire the basic skills needed to manage data for a health research study conducted in the U.S. or in a less developed country. The course is designed for study team members directly involved in data management, logisticians who develop study protocols, study coordinators responsible for day-to-day field activities, and doctoral students preparing to undertake field research. It is also designed for principal investigators who want to gain an understanding of and an appreciation for data management. The skills gained are applicable to epidemiological and health systems research.

Students will design a data entry and editing system for a small study, which will hone their skills. Every class member will edit questionnaires, design a double data entry system with range checks, enter and verify data, write computer code to identify out-of-range and illogical values, make and document edit decisions regarding the out-of-range and illogical values, and write computer code to clean the data in preparation for data analysis.

Each student will complete a tutorial that provides step-by-step instructions to design the data entry and editing system described above. Because each task is built on the previous tasks, homework has to be turned in on time. While the concepts are not difficult, data management, in real life and in this course, requires a considerable time commitment. Student evaluation is based on the tutorial.

Lectures provide the basic framework for data management principals and techniques. Each lecture (or group of lectures) is paired with a data management task. Students should review the lecture before beginning the corresponding tutorial.

The course uses Microsoft Access software to design the data management system and either SPSS or Stata statistical software. You do not need previous experience with Access or with Stata or SPSS. The knowledge you gain while working with these packages is applicable to other data entry and/or analysis software. Homework assignments will be emailed in WinZip files (winzip.com).

A weekly LiveTalk session will provide opportunities for students and faculty to discuss problems encountered completing the tutorial, as well as time to clarify points made during the lectures. During the rest of the week, students are encouraged to use email to ask faculty for assistance in completing assignments or debugging software.