Date:
Location:
Nanocourse: https://nanosandothercourses.hms.harvard.edu/node/410
Course Instructors: Xiaoxue Li, Ph.D., Jin Lee, Ph.D.
Curriculum Fellow: Bradley Coleman, Ph.D.: bradley_coleman@hms.harvard.edu
Course Director: Eric Rubin, MD, Ph.D.
Description:
Missing data occur when data are expected but no value is stored. This is a very common situation, which may have a significant impact on the conclusions. This Nano course will use real and sample datasets to illustrate the possible impacts of missing data on the analyses, interpretation and conclusions of studies in the social or behavioral sciences using R. In session 1, individual examples will be used to explore the possible reasons for missing data. We will talk about types of missing data and potential missing data methods. In session 2, hands-on examples for implementing missing data analyses and visualization in R will be offered.
Course Objectives
This course is designed for students with little or no biostatistics experience and will not contain significant discussions of statistical theory, though students are expected to have basic knowledge of R programming. R and Rstudio should already be installed on your laptop prior to the second session. The examples and approaches discussed will be specific to studies in the social and behavioral sciences and are not directly applicable to molecular or laboratory data.
After this course, participants should:
· be aware that missing data problems need to be considered prior to the design of a study.
· have a basic understanding of the potential implications of missing data and potential solutions.
Schedule
First Session: Wednesday June 29, 09:00-12:00 pm. Location: TMEC 250
Second Session: Wednesday July 6, 09:00-12:00 pm. Location: TMEC 250
DROP DEADLINE: Wednesday June 22, 2016
If you are interested in this course (both auditors and enrolled students), please RSVP at: hsph.me/missingdata
Those taking the nanocourse for academic credit must enroll through the course registration process.