MORNING SESSIONS- 9-noon each day
Introduction to Survey Design
This workshop will cover the fundamental stages of survey design, and will emphasize how to design questionnaires appropriate for mass surveys. The first part of the workshop will emphasize measurement: how to design questions that will result in variables appropriate for the concepts and models motivating a study. We will cover solutions to common problems in formulating questions, response options, and ordering of items and responses. The second part of the workshop will focus on sampling and implementation: we will cover the advantages and disadvantages of different approaches to drawing a probability sample, as well as procedures for conducting interviews, training staff, and maintaining quality control. Lectures will be accompanied by hands-on exercises and discussion related to questionnaire and sample design.
Jane Zavisca is Associate Professor of Sociology and Associate Dean for Research in the College of Social & Behavioral Sciences at the University of Arizona. Professor Zavisca holds an MA in Statistics from Columbia University, a PhD in sociology from UC Berkeley, and postdoctoral training from the Statistical and Applied Mathematical Sciences Institute of the National Institute for Statistical Sciences. She has designed and fielded several large surveys in the post-Soviet region, including in Russia, Ukraine, Azerbaijan, and Kyrgyzstan, with support from NSF, SSRC, and DoD. Professor Zavisca has taught advanced graduate courses on research design for the past decade, and also has extensive training and experience in historical and qualitative methods as well.
Qualitative Data Analysis in ATLAS.ti [PC Version]
Professor Corey Abramson
This workshop will provide both a conceptual background and practical experience in computer assisted qualitative data analysis (CAQDA) using ATLAS.ti. The workshop begins by examining the core elements common to all CAQDA, regardless of methodological orientation, discipline/profession, or platform. After instruction in the fundamental aspects of CAQDA, the course turns to the logic of the ATLAS.ti program, and how it functions as a tool for CAQDA. The workshop consists of both instruction and hands-on exercises in ATLAS.ti. By the end of the course, participants will have all the conceptual and practical tools necessary to employ ATLAS.ti in their current or future projects involving qualitative data.
Topics covered include: 1. How to perform the fundamentals of computer aided qualitative data analysis in ATLAS.ti, 2. The specific strategies necessary for dealing with different types of data including ethnographic field notes, in-depth interviews, texts, audio, video, and documents, 3. How to organize your data set, 4. How to construct and deploy a coding scheme for your project, 5. Making the best use of memos, 6. Inductive and deductive strategies for investigating substantive relationships in your data, 7. The query tool and reverse polish notation, 8. Using ATLAS.ti for team projects, and 9. Advanced functions in ATLAS.ti (e.g. networks, geocoding, quantitative output, supercodes and snapshots, co-occurrence functions, tools for inter-coder reliability, etc.).
We highly recommend Mac users install the Windows version of the software using parallels or VMware or use one of our computers, as the MAC version of ATLAS.ti lacks key functions. We will use the PC version for all demonstrations.
Corey M. Abramson is an Assistant Professor of Sociology at the University of Arizona. He received his Ph.D. in sociology from UC Berkeley in 2012. Professor Abramson has over a decade-and-a-half of experience using, teaching, and developing methods of Computer Assisted Qualitative Data Analysis (CAQDA). In addition to using CAQDA in his own ethnographic and interview based projects (including his book with Harvard University Press and a recent article on expanding frontiers of CAQDA in Sociological Methodology), Professor Abramson has had the opportunity to serve as a methodological adviser and consultant for individual and team based projects encompassing a wide range of data types, analytical approaches, and disciplines. He has worked to develop novel training programs for conducting qualitative research in social science and policy disciplines at the undergraduate, graduate, and post-graduate levels. In recent years, his workshops have been commissioned by a range of organizations including: universities, medical centers, think tanks, professional associations, and the ATLAS.ti training center.
AFTERNOON SESSIONS - 2-5 pm each day
Conducting Survey, Lab, and Field Experiments in the Social Sciences
S. Michael Gaddis
During the past decade, experiments in the social sciences have gained in popularity as the internet has made implementing experiments easier, cheaper, and faster. However, although social scientists may have a conceptual knowledge of how experiments work, the actual experience of implementing an experiment for the first time is often frustrating and time consuming. Researchers without prior experience often struggle with a number of issues such as navigating IRB, obtaining true random sampling and assignment, understanding blocking, and interpreting different types of treatment effects. The initial learning curve may be steep but the rewards are plentiful as experiments produce original data often highly valued in top journals, lend themselves to causal analysis in ways that traditional survey data cannot, and become easier to implement as a researcher’s experience level increases.
This course is designed for a variety of social scientists who are interested in social science experiments (survey, lab, and/or field). Those with only textbook knowledge of experiments will leave with the confidence to conduct their own experiments. Others with some experience designing and implementing experiments will leave with a deeper understanding of methods that can help save them time and effort with future experiments. In this course, we will begin with identifying what types of questions to ask with experiments and work our way through advanced analysis techniques. Hands-on activities will give students the opportunity to design and implement a survey experiment and explore the basics of a field experiment during the workshop.
S. Michael Gaddis is an Assistant Professor of Sociology and Demography at the Pennsylvania State University. His work explores the causes and consequences of racial and educational inequality, often through experiments. He has led the data collection efforts on nearly a dozen field and survey experiments. He is the editor of and a contributor to the forthcoming bookAudit Studies: Behind the Scenes with Theory, Method, and Nuance due out from Springer in 2017. His research has been published in the American Journal of Sociology, Social Forces, Social Science Research, and Educational Evaluation and Policy Analysis, among other outlets.
Introduction to Machine Learning for Social Scientists
As social scientists explore data of increasing size and complexity, they have turned to techniques from machine learning to find structure in and make predictions from these rich traces of social life. This workshop will introduce some of the basic ideas and techniques of machine learning. We will cover supervised and unsupervised methods, including Naïve Bayes, decision trees (classification and regression), k-means, and neural networks. We will discuss both the mathematical foundations of these methods and the practicalities of implementation. Some basic familiarity with probability and Python will ensure that participants get the most out of the workshop. Participants will leave the workshop with a map of the terrain, a sense of which methods are appropriate for which tasks, the skills to implement simple methods on their own data, and enough command of the jargon to collaborate effectively with experts in machine learning.
Jacob G. Foster is an Assistant Professor of Sociology at the University of California, Los Angeles. He is a computational sociologist interested in the evolution and population dynamics of ideas. His work blends computational methods with qualitative insights from science studies to probe the strategies, preferences, and social processes that shape the production and persistence of scientific ideas. He also develops formal models of the structure and evolutionary dynamics of ideas and institutions. He is the co-founder of the Metaknowledge Research Network, funded by the John Templeton Foundation. His work has appeared in American Sociological Review, Science, Proceedings of the National Academy of Sciences, Sociological Science, and Social Networks.