Workshop in Methods
Permanent link for this collectionhttps://hdl.handle.net/2022/18413
The Workshop in Methods (WIM) was created in 2009. The initial idea for WIM began with Scott Long, who discussed his vision with Dr. William Alex Pridemore. Pridemore created WIM and directed the series until 2013. The mission of the Workshop in Methods is to provide introductory education and training in sophisticated research methods to graduate students and faculty in the social sciences at Indiana University. Our goal is to supplement statistics and methods courses across the Bloomington campus with topical workshops led by leading methodological scholars from IU and across the United States. In Fall 2013, the SSRC, working under the direction of the WIM advisory committee, began hosting the WIM series.
Browse
Recent Submissions
Now showing 1 - 20 of 127
Item Power Analyses Power Hour: Understanding and Conducting Statistical Power For Your Research(Indiana University Workshop in Methods, 2025-02-07) Ray, Elizabeth; Klein, NeelaFrom research design, to grant proposals, preregistrations, post hoc results interpretation, journal submissions, and beyond, power analysis is an important part of the scientific process. A priori power analysis determines the sufficient sample size needed to reach desired power and effect size without wasting resources through overpowering a study and without underpowering a study or analysis. The goal of this workshop is to provide IU faculty, staff, and graduate students an accessible, conceptual, and practical understanding of statistical power, effect size, writing power analysis results, and using G*Power software. The workshop will cover power analysis related definitions, theoretical concepts such as the importance of power analysis, point and click examples in G*Power, resources, and more. Though not required, to make the most of your attendance, arrive with the free and open source software, G*Power, already downloaded.Item Introduction to Regression Models for Panel Data Analysis(Indiana University Workshop in Methods, 2025-01-24) McManus, PatriciaThis workshop provides an introduction to the analysis of panel data (sometimes called cross-section time-series data) using Stata statistical software. The focus is on the linear error components model. We cover what differentiates panel data from other longitudinal data, why use panel analysis techniques and how to use Stata’s “xt” suite of commands to facilitate data exploration and analysis. The workshop introduces linear fixed effects models (in three flavors), random effects models, and Allison’s (2009) hybrid model. Participants may have the opportunity to follow along using a small example dataset.Item Extensions to Embedding Regression: Models for Context-Specific Description and Inference(Indiana University Workshop in Methods, 2024-02-02) Spirling, ArthurSocial scientists commonly seek to make statements about how word use varies over circumstances—including time, partisan identity, or some other document-level covariate. For example, researchers might wish to know how Republicans and Democrats diverge in their understanding of the term “immigration.” Building on the success of pretrained language models, we introduce the a la carte on text (conText) embedding regression model for this purpose. This fast and simple method produces valid vector representations of how words are used—and thus what words “mean”—in different contexts. We show that it outperforms slower, more complicated alternatives and works well even with very few documents. The model also allows for hypothesis testing and statements about statistical significance. We also provide extensions of the model to non-English languages and demonstrate applications for the same.Item Navigating the Shift from Face-to-Face to Push-to-Web Data Collection in Cross-National Survey Research(Indiana University Workshop in Methods, 2024-01-26) Ságvári, BenceThis presentation looks at the changing landscape of cross-national survey research and provides a first-hand account of the European Social Survey’s (ESS) transition from traditional face-to-face methods to the increasingly prevalent push-to-web data collection methods. The ESS is one of the largest academically led cross-national survey that has been conducted across much of Europe since its establishment in 2001. Its aim is to measure attitudes, beliefs, values and behavioral patterns and thus provide comparative data across countries and over time. However, like any other survey research, ESS faces major challenges, such as declining response rates, rising costs for traditional data collection and deteriorating data quality due to the interviewer effect. To resolve this situation and create a uniformly applicable new data collection standard, the ESS has conducted numerous experimental push-to-web mixed mode (web and postal) studies in several countries in recent years. In addition, the pandemic has made face-to-face surveys impossible in many European countries between 2020 and 2022, which has meant a rapid and forced shift to self-completion questionnaires. In this workshop, participants will learn about the characteristics of the data collection process itself, and some of the lessons learned from comparing the two types of fieldwork used in parallel in Hungary. Possible solutions for achieving representative samples, especially for hard-to-reach social groups in push-to-web surveys, strategies to improve participation, including the use of conditional and unconditional incentives, will be discussed in the first part of the workshop. The second part of the workshop will be dedicated to critically assessing the ‘mode effect’ associated with f2f surveys compared to self-completion surveys when it comes to sensitive topics such as attitudes in politics, LGBTQ and migration. The workshop will end with a brief demo of a smartphone app-based solution to collect digital behavior and trace data. This workshop is intended for faculty and students working with secondary survey data or conducting or planning their own data collection.Item Introduction to Python for Social Scientists(Indiana University Workshop in Methods, 2023-10-20) Kavalerchik, Anne; Kim, EehyunPython has become the lead instrument for data scientists to collect, clean, and analyze data. As a general-purpose programming language, Python is flexible and well-suited to handle large datasets. This workshop is designed for social scientists, who are interested in using Python but have no idea where to start. Our goal is to “demystify” Python and to teach social scientists how to manipulate and examine data that deviate from the clean, rectangular survey format. This workshop is intended for social scientists who are new to programming. No experience required.Item Introduction to IPUMS: US Complete Count and Linked Census Data(Indiana University Workshop in Methods, 2023-09-22) Nelson, MattIPUMS provides free census and survey data from around the world. We receive funding from the NIH and NSF to make data more accessible to researchers by making them comparable across time and space. By reducing the barriers to accessing rich data sources, IPUMS allows researchers to leverage publicly available datasets to answer a broad array of demographic and economic questions. This talk will provide an introduction to IPUMS, review the current historical full count and linked census data available, and showcase some of the current research applications of the historical data.Item Human Subjects Research Submission Process at IU(Indiana University Workshop in Methods, 2023-09-15) Mumaw, CaseyThis session will cover information that will make the submission, as well as review and approval process, of human subjects research protocols at Indiana University. The presentation will cover various regulatory topics to provide clarification, as well as providing information about the review and approval process at IU, including specific directions and guidance for using the Kuali Protocols system.Item Studying Socioeconomic Inequality from Digital Footprint Networks(Indiana University Workshop in Methods, 2023-03-24) Tsvetkova, MilenaSocial connectivity structures and reinforces inequality in society but also provides a footprint of it. I will present two projects in which we analyze network structures to extract information about socioeconomic inequality. In the first project, we use correspondence analysis to infer Twitter users’ socioeconomic status from the accounts of commercial and entertainment brands in the US they follow. In the second project, we analyze SafeGraph data on physical store visits and co-visits in the US to investigate nuances of socioeconomic inequality in daily consumption. The projects demonstrate how we can both exploit and examine traces of economic and cultural consumption practices to understand an important manifestation of inequality in everyday life.Item Using Natural Language Processing to Facilitate Social Science Research(Indiana University Workshop in Methods, 2023-03-03) Katz, AndrewRecent advances in natural language processing in the form of large language models (e.g., ChatGPT, GPT-3, BERT) have created new opportunities for social science research. While some of these models are proprietary and not easily accessible to researchers, others are publicly available through open source repositories such as HuggingFace. Key to these new language models is their ability to capture semantic meaning in texts, which means social scientists can leverage them to identify themes in large corpora of text that were previously unwieldy to analyze. In this workshop, we will review methods to harness these models to glean information from a range of sources including interviews, open-ended surveys, and web-scraped data.Item Using Machine Learning to Infer Real-world Political Attitudes and Behaviors from Social Media Data(Indiana University Workshop in Methods, 2023-02-24) Bestvater, SamuelSocial media has become a primary means of communication and personal expression for many, and digital trace data from social media platforms can contain rich and extensive archives of individuals’ attitudes, beliefs, and actions. But even though these data are increasingly plentiful and available to social science researchers, the process of extracting meaningful measures of individual-level attributes from large collections of social media data is nontrivial. In this talk, Computational Social Scientist, Sam Bestvater, will draw from his research on political engagement in online spaces and its impacts on real-world behaviors to discuss how machine learning algorithms can be used to analyze large amounts of social media data and extract insights into political attitudes and activities. Along the way, the talk will introduce several recent innovations in natural language processing and computer vision, and will discuss some potential challenges and limitations of using these tools and data sources for political research, as well as ethical considerations that should be taken into account.Item Workflow of Data Preparation(Indiana University Workshop in Methods, 2023-02-03) Manago, BiancaBefore conducting analyses, we all know that we need to “clean the data”, but what exactly does that mean? What steps are involved and in what order? How do we decide what needs to be done? Data preparation involves all the steps that occur between data collection and analysis (e.g., merging, appending, labeling, data analytics, cross-validation, constructing/re-constructing variables for analysis, identifying missing data). This seminar will provide a general framework for approaching these processes. The framework informs decisions about an ideal order in which data cleaning should be conducted to represent data both accurately and fully. This framework also delves into some of the trickier issues. For example, when you come across anomalous, vague, or missing data – what kinds of things should you consider? I will also provide guidance for ensuring that your findings are reproducible. Finally, I will discuss how to prepare data for analysis as efficiently as possible.Item Using Google Maps to Generate Organizational Sampling Frames(Indiana University Workshop in Methods, 2023-01-20) Fulton, Brad R.Organizational researchers use a variety of methods to obtain sampling frames. The utility of these methods, however, is constrained by access restrictions, limited coverage, prohibitive costs, and cumbersome formats. This workshop presents a new method for generating sampling frames for any type of organization that is cost-effective, uses publicly available data, and produces near-comprehensive sampling frames for any geographic area in the U.S. The Python-based program we developed systematically scans the Google Maps platform to identify organizations of interest and retrieve their contact information. We demonstrate the program’s viability and utility by generating a sampling frame of religious congregations in the U.S. To assess Google Maps’ coverage and representativeness of such congregations, we examined two nationally representative samples of congregations and a census of every congregation in Indianapolis. We found that Google Maps contains approximately 98% of those congregations––near-complete coverage that ensures a near-perfect degree of representativeness. Using Google Maps to generate sampling frames promises to substantially improve the process for obtaining representative samples for organizational studies by reducing costs, increasing efficiency, and providing greater coverage and representativeness.Item The NIH Final Policy on Data Management & Sharing: What you need to know(Indiana University Workshop in Methods, 2022-12-02) Fridmanski, Ethan; Tempel, ClaireWhile not all research data can be made publicly available, many funders would like to see the research data generated by their funding dollars made more accessible. Combined with the emergence of journal data availability requirements, there is a strong trend towards openness for access to research data. In October 2020, the Final NIH Policy for Data Management and Sharing was released. This policy requires submission of a Data Management and Sharing Plan at the time of proposal as well as release of the data, whether access is open or controlled, to be made “no later than the time of an associated publication, or the end of the award/support period, whichever comes first.” When this policy goes into effect in January 2023, awards will include the approved DMS Plan in the Terms and Conditions, at which point IU will become legally responsible for complying with the DMS Plan. In this talk the IU Data Management Plan Working Group will give a short presentation on these upcoming changes, some resources to assist faculty, and answering questions.Item Institutional Agency and Divergent Innovation: How Micro-institutional Change Happens in Meso-level Contexts(Indiana University Workshop in Methods, 2022-11-11) Bridwell-Mitchell, EbonyInstitutions are a stabilizing force in society. At the same time, institutional resilience and persistence can be counterproductive when existing institutions cannot meet the new demands of a changing world. One example is U.S. public schooling where institutionalized work practices, namely classroom instructions, too often undermines forms of learning needed for a modern economy and to provide equitable learning opportunities across diverse student groups. Existing research on changes in institutionalized work practices or micro-institutional changes focuses mainly on fraught and politicized processes between groups of reformers and resisters sometimes resulting in ‘turmoil’. In contrast to questions about how political processes unfold among competing groups, it is also important to ask questions about what makes it possible for groups of individuals to conceive of and gain a shared understanding of alternatives to institutionalized work practices in the first place. The current paper examines this question in two related multi-method studies: a multi-stage group experiment examining changes in institutionalized work practices and a study using qualitative comparative case methods to identify possible necessary conditions for generating the novel work conceptions involved in micro-institutional change. The findings confirm and extend prior research demonstrating the important role of socialization and innovation opportunities for micro-institutional change. The findings also indicate there is at least one necessary, if not sufficient, condition for generating novel alternatives to institutionalized practice: the mutual presence of (a) task certainty, (b) the perceived expertise and competence of group members, and (c) explicit encouragement to challenge accepted practice. Implications for existing understandings of micro-institutional change and for public school reforms are discussed.Item Weighting for Polls and Samples(Indiana University Workshop in Methods, 2022-11-04) Franklin, CharlesCharles Franklin is a nationally-recognized government scholar and pollster. He has been director of the Marquette Law School Poll since its inception in 2012 and became a full-time member of the faculty in 2013. He previously co-founded Pollster.com, and now writes at https://pollsandvotes.com/.Item Software History: Exploring the Materiality of Virtual Things(Indiana University Workshop in Methods, 2022-10-21) Ensmenger, NathanSoftware-based systems are an increasingly pervasive and fundamental technology of modern social, economic, and political life. And yet most of these systems are effectively black boxes, either necessarily or deliberately opaque. Software is often invisible, ethereal, and immaterial. Opening up the black box of software to scholarly analysis requires creativity and cross-disciplinary perspectives. This talk will discuss several methods for situating software within its larger social context. These include labor and gender history, case studies in the materiality of computer chess and software maintenance, and emerging perspectives on the environmental history of computing.Item Heuristics for Feeling Your Way in the Dark(Indiana University Workshop in Methods, 2022-09-30) Walker, MichaelEthnography is a practical method, and vague descriptions of talking to or observing people are not helpful for others who want to use the findings or replicate how the researcher conducted the study. In this presentation, I mean to discuss the how of ethnography–not the definitive “how.” Such a thing does not exist, but I want to offer some practical heuristics for ethnography in known and unknown environments. My general focus includes (a) genuine interest, (b) networks of interactions, (c) mood, (d) generic theory toolbelt, (e) recording shorthand, (f) analogy, and (g) writing as presentation.Item Characters and Grammar: How Linguists Can Become More Fluent in R(Indiana University Workshop in Methods, 2022-09-23) Myers, JamesR is not just statistics software, but a full-fledged computer language, and with its thousands of extra packages linguists can program it to do things far beyond basic statistical analysis and graph-making (though of course R is great at those things too). In this talk I hope to give a painless introduction to the grammar of R for those who have not yet dared to try it, while still offering some new ideas to more experienced users. The empirical focus is on my own explorations of the “grammar” of Chinese characters, which will allow me to survey a variety of methods of particular use to Chinese linguists, including how to work with non-Roman writing systems, how to analyze text corpora, how to compile data from lab experiments, and of course how to run statistical analyses and make graphs, from the simple to the fancy, including new types of analyses that you can invent yourself with some basic concepts in probability and a bit of programming. If time permits, I will also demonstrate how diverse and powerful R’s extra packages really are by highlighting tools for sound and image processing (the latter useful for the study of writing systems and sign language). Above all, I will emphasize that there is no reason to feel intimidated: anybody can become ever more fluent in R through workshops like these, textbooks, internet searches, and most importantly, patient trial and error.Item Cycles of Conflict, a Century of Continuity: Computational Methods and the Longue Durée(Indiana University Workshop in Methods, 2022-09-09) Nelson, Laura K.The women’s liberation movement hotly debated both the cause of women’s oppression and the best approach to changing it. When treated as a moment within 1960s political polarization, these debates can seem esoteric and arbitrary. When examined across the longue durée, I show that these debates reflect complex and stable differences in interpretation that were tied to place more than to the political moment. Using computational methods to examine women’s movements from the 1860s to the 1970s, I challenge long-standing theories of feminist waves and reflect on the potential for using computational methods, in particular when combined with qualitative methods and interpretation, to re-examine historical patterns in social movements over long time frames.Item Abortion Attitudes: The difficulties of simple questions about complex issues(Indiana University Workshop in Methods, 2022-08-26) Jozkowski, Kristen; Crawford, BrandonThe recent Supreme Court decision in the Dobbs v. Jackson resulted in the overturning of Roe v. Wade, ending the constitutional right of a pregnant person to choose to have an abortion until fetal viability (i.e., until about 24 weeks). Although this ruling marks a significant shift in abortion policy and climate in the U.S., the vast majority of polls measuring abortion attitudes show that there has been little change in attitudes since the 1970s. What does that mean about the relationship between policy and public opinion and how we measure abortion attitudes? In this workshop, we will provide an overview of abortion as a contentious social issue, historical trends of abortion attitudes, and the implications of the Dobbs v. Jackson decision. Next, we will share an overview of our project: Developing and Assessing Measures for Social Surveys (DAMSS). Then we will present some of our preliminary findings and discuss what makes a “good” question actually a “bad” question? We will conclude with what these preliminary findings mean for how we assess abortion attitudes and what the DAMSS project will be doing next. No previous experience with abortion attitudes is needed. Although the focus of this presentation will be abortion attitudes, the findings and methodology have relevance for other social issues.