Applied Regression with R for Social Science Researchers
An ISSR two-day workshop at UMass
9:00 am to 2:00 pm May 29-30, 2013
Location: ISSR Training Lab: Machmer W37E
Click here to register for this workshop
*Please note that this workshop has reached capacity. If you would like to be placed on the wait list please fill out the registration form. You will be contacted should space become available.
This course is geared to social science researchers who work with regression models to analyze data in their particular field. It offers opportunities to learn how to perform multiple regression, ANOVA, and hypothesis testing, and estimate fixed and random effects regression models in the R environment. R is a versatile programming language that can estimate numerous types of regression models, with many add-on packages available for your particular area. This two-day workshop will get you comfortable running regressions in R and reading output. The first day will focus on multiple regressions and the tools needed to run them: importing and plotting data, specifying a model, checking model assumptions, reading output, and testing hypotheses. This session is aimed at researchers who have some experience with R, but need some help with multiple regression basics. The second day will focus on multiple regression extensions: estimating fixed and random effects models with panel data, and interpreting output from these models. On the second day researchers are encouraged to bring their own data to practice coding.
Software Note: The instructor will be using RStudio for this course, but the commands in R are identical. R and RStudio are free for any user to download through the Internet. You can download R at http://cran.r-project.org and RStudio (must download R before installing) at http://www.rstudio.com/ide/download.
Cost: $100 faculty, $40 graduate students (includes lunch)
Workshop Leader: Chris Burns
Chris Burns is a doctoral student in the Department of Resource Economics at UMass-Amherst. He uses R to manage data, code, estimate models, and run simulations when conducting research. His main research area looks at the effects of measurement error in panel data models. He has significant experience with R, has taught workshops on its use, trained people one-on-one, and consulted with researchers on using R for their projects.