Friday, September 1, 2017
Dr. J. Scott Long, "Reproducible Results and the Workflow of Data Analysis"
2-3:30pm, Social Science Research Commons Grand Hall (Woodburn Hall 200)
Many disciplines are paying increasing attention to reproducible results. The fundamental idea is that other scientists should have access to your data and be able to obtain the same results—this is reproducibility. More generally, your results should be robust so that other scientists can confirm your findings using other data. Increasingly journals require authors to provide their data and analysis file before a paper is accepted to verify that that results. Producing reproducible results is highly dependent on your workflow for data analysis. This workflow encompasses the entire process of scientific research: Planning, documenting, and organizing your work; creating, labeling, naming, and verifying variables; performing and presenting statistical analyses; preserving your work; and ending with reproducible results. Most of the work in statistics classes focuses on estimating and interpreting models. In “real world” research projects, these activities may involve less than 10% of the total work. Professor Long’s talk is about the other 90% of the work. An efficient workflow saves time, introduces greater reliability into the steps of the analysis, and generates reproducible results.
Dr. Long is Distinguished Professor and Chancellor’s Professor of Sociology and Statistics at Indiana University.
Friday, September 15, 2017
Dr. Emily Meanwell, "Qualitative Research Methods: An Introduction"
Social Science Research Commons Grand Hall (Woodburn Hall 200), 2pm
What is qualitative research? When and how might qualitative research methods help you answer your research questions? This workshop will provide an overview of qualitative research methods, including interviews, focus groups, ethnography, and qualitative content analysis. For each, we will discuss the basics of data collection and analysis, best practices, and illustrative examples. Lastly, we will consider how these methods contrast with, and/or may be combined with, other empirical research methods, including quantitative and survey research methods.
Emily Meanwell is the Director of the Social Science Research Commons and the Study Director for the Sociological Research Practicum. She received her PhD in sociology in 2014 and has used a range of qualitative methods, including interviews, ethnography, and content analysis, in her research.
Friday, September 22, 2017
Dr. James Ziliak and Dr. Charles Hokayem, "Kentucky Research Data Center Infosession"
Social Science Research Commons (Woodburn Hall 200), 2pm
The Kentucky Research Data Center (KRDC) is a collaboration between the University of Kentucky and the U.S. Census Bureau established by a grant from the National Science Foundation in 2016. KRDC is part of the nationwide system of Federal Statistical Research Data Centers whose mission is to expand the data infrastructure available to qualified scholars and students with approved projects by providing access to restricted individual- and firm-level data from participating federal statistical agencies. KRDC is maintained by a regional consortium of leading research institutions, including Indiana University. This infosession is designed for IU researchers interested in developing research projects using the KRDC.
James Ziliak is the KRDC Executive Director, Carol Martin Gatton Endowed Chair in Microeconomics, and the Founding Director of the Center for Poverty Research at the University of Kentucky. Charles Hokayem is the KRDC Administrator with the United States Bureau of the Census.
Friday, September 29, 2017
Dr. Robert Calin-Jageman, "The New Statistics and Open Science: How to Get Started"
Social Science Research Commons (Woodburn Hall 200), 1-3pm
Recently the Association for Psychological Science revised its publication guidelines to reward Open Science practices and to encourage the use of the “New Statistics” as a better alternative to null hypothesis significance testing (NHST). Other journals and professional societies seem to be moving in the same direction, often in collaboration with funding agencies.
This workshop will provide a practical introduction to the New Statistics and some emerging Open Science practices. We will worth through examples from several common research designs. We will also explore resources that can help you adopt these approaches in your own research.
Robert Calin-Jageman is a professor of psychology and the neuroscience program director at Dominican University. He has taught statistics and mentored students in psychological science for 10 years, publishing with 16 undergraduate co-authors (so far). His research focuses on how memories are formed and forgotten. He has also been active in exploring the replicability of psychological science and promoting Open Science. He received his PhD in Biological Psychology from Wayne State University.
Friday, October 13, 2017
Jefferson Davis, "The Grammar of Graphics: An Introduction to ggplot2"
Social Science Research Commons (Woodburn Hall 200), 2-3:30pm
In The Grammar of Graphics, Leland Wilkinson created a systematic way to think about statistical graphics and the presentation of quantitative data. The package ggplot2 by Hadley Wickham implements of Wilkinson's system for the language R.
The talk will discuss the following:
- What are statistical graphs and what are some ways to talk about them?
- Examples of common plot types done in ggplot2.
- Using ggplot2 to display common statistical transformations.
- Grouping and faceting data in ggplot2.
- Using themes to add polish to graphs.
The talk requires no familiarity with ggplot2 or other libraries. Some familiarity with base R, however, will be useful.
Jefferson Davis is a software analyst with Research Analytics. He has worked on several projects that have used R and R libraries. Current projects include work in data visualization, machine learning methods, and large data sets.
Friday, December 1, 2017
Justin Wild, "Structural Equation Modeling in Open-Source Software"
Social Science Research Commons (Woodburn Hall 200), 2-4pm
Structural Equation Modeling (SEM) offers flexible statistical models for the social science researcher. A variety of software packages are available for implementing SEM with researchers’ datasets and are becoming increasingly sophisticated. This talk will briefly outline SEM in comparison with more familiar statistical models (such as linear regression) and review several R packages tailored for the SEM community. In addition, these packages are compared to perhaps the most well-known commercial package available, MPlus.
Justin Wild is a doctoral candidate at Indiana University studying Education Policy Studies, with a concentration in International and Comparative Education, and Inquiry Methodology. He has a Master’s of Arts in African Studies and a Master’s of Public Affairs from Indiana University. His research addresses K-12 language of instruction, language ecology, foreign language learning, evaluation in education, large-scale assessments, multi-method research, and cross-cultural issues. His geographic focus is Tanzania, East Africa.