Social Science Research Commons

Permanent link for this communityhttps://hdl.handle.net/2022/18403

Browse

Now showing 1 - 20 of 154

Your Statistical Toolbelt
(Indiana University Workshop in Methods, 2013-09-27) Dickinson, Stephanie
This workshop will give an overview of how to identify what types of data analysis tools to use for a project, along with basic “DIY” instructions. We will discuss the most common analysis tools for describing your data and performing significance tests (ANOVA, Regression, Correlation, Chi-square, etc), and how they should be selected based on the type of data and the type of research question you have. We will spend the first hour outlining “what analysis to use when” and the second hour going through examples in SPSS software.
Introduction to Questionnaire Design
(Indiana University Workshop in Methods, 2013-11-08) Giroux, Stacey; Yahng, Lilian; Bowers, Ashley
A well-designed and tested survey questionnaire is one of the most powerful tools that researchers in education, health, business and public policy, and the social sciences have to obtain accurate and reliable measurements of a wide range of attitudes, opinions, beliefs, and behaviors. With technological advances in how data are captured, exciting new horizons for survey measurement and assessment of the quality of those measurements are emerging. In this workshop, we review best practices in the development and testing of survey questionnaires that may be administered using web, mail, telephone and/or face-to-face data collection methods. We will provide numerous practical examples of how to design and evaluate survey questions and how to implement commonly used testing procedures, including in-depth cognitive interviews and field pretests.
Your Statistical Toolbelt (in SPSS)
(Indiana University Workshop in Methods, 2014-01-31) Dickinson, Stephanie
This workshop will give an overview of how to identify what types of data analysis tools to use for a project, along with basic "DIY" instructions. We will discuss the most common analysis tools for describing your data and performing significance tests (ANOVA, Regression, Correlation, Chi-square, etc.), and how they should be selected based on the type of data and the type of research question you have. We will spend the first hour outlining "what analysis to use when" and the second hour going through an example dataset in SPSS software ("Comparing motivations for shopping at Farmer’s markets, CSA’s, or neither.")
Introduction to MatLab
(Indiana University Workshop in Methods, 2014-02-14) Davis, Jefferson
Matlab is a numerical programming environment with a large library of functions for numerical analysis and computation. This workshop will be an introduction to Matlab syntax and computation. We will cover: - Basic Matlab data structures and syntax - Importing and exporting data - Plotting curves and surfaces - Running simple statistical tests - Comments on Matlab’s use in image processing and GIS. The workshop assumes no prior familiarity with Matlab.
Introduction to GIS and Spatial Data Analysis
(Indiana University Workshop in Methods, 2014-04-04) Evans, Tom
This course teaches what a GIS is and what you can do with it. Participants will be introduced to spatial data structures and issues of spatial data representation. Brief exercises will be used to emphasize particular dimensions of spatial data analysis. Applications will address census data analysis (and import), fundamentals of map design, and data integration. The workshop will use ArcGIS, although the principles discussed will be broadly applicable to any GIS toolkit. The workshop will conclude with a presentation of next steps to gain additional training in GIS and spatial data analysis.
Your Statistical Tool Belt
(Indiana University Workshop in Methods, 2014-09-05) Dickinson, Stephanie
This workshop will give an overview of how to identify what types of data analysis tools to use for a project, along with basic “DIY” instructions. We will discuss the most common analysis tools for describing your data and performing significance tests (ANOVA, Regression, Correlation, Chi-square, etc), and how they should be selected based on the type of data and the type of research question you have. We will spend the first hour outlining ‘what analysis to use when’ and the second hour going through an example dataset in SPSS software “Comparing motivations for shopping at Farmer’s markets, CSA’s, or neither.” Bring your own data set to work along also.
Getting Serious About Test Score Reporting
(Indiana University Workshop in Methods, 2014-11-07) Hambleton, Ronald
Ronald K. Hambleton holds the titles of Distinguished University Professor and Executive Director of the Center for Educational Assessment at the University of Massachusetts Amherst. He earned an M.A. in 1967 and Ph.D. in 1969 from the University of Toronto with specialties in psychometric methods and statistics. Professor Hambleton has taught graduate-level courses in item response theory and applications, classical test theory, and principles of assessment at UMass since 1969. He is the author or co-editor of nine books on educational assessment and has published papers on applications of item response theory, and such topics as criterion-referenced assessment, test adaptation methodology, test score reporting, standard-setting, and computer-based testing, over his 45 years in the assessment field.
Advanced Topics in R
(Indiana University Workshop in Methods, 2014-12-05) Davis, Jefferson; Zhang, Hui; Michael, Scott
In this follow up workshop to “Introduction to R” researchers will have the opportunity for a deeper dive into R. Available on all IU's supercomputers, R is a flexible open source statistical programming language that can work with large and complex data sets. This workshop will address several advanced topics in R as well as giving participants the opportunity to use R on IU’s supercomputers. The topics to be covered include: R scripting on IU supercomputers; debugging, profiling, and performance analysis of R code; parallel programming in R, including the Rmpi and snowfall packages; and advanced plotting in R. Participants will have access to the supercomputer Big Red II during the session and will be able to see hands-on examples of running R code and submitting batch jobs in R.
Your Statistical Tool Belt
(Indiana University Workshop in Methods, 2015-01-23) Dickinson, Stephanie
This workshop will give an overview of how to identify what types of data analysis tools to use for a project, along with basic "DIY" instructions. We will discuss the most common analysis tools for describing your data and performing significance tests (ANOVA, Regression, Correlation, Chi-square, etc.), and how they should be selected based on the type of data and the type of research question you have. We will spend the first hour outlining "what analysis to use when" and the second hour going through an example dataset in SPSS software "Comparing motivations for shopping at Farmer’s markets, CSA’s, or neither." Bring your own data set to work along also.
Systematic Reviewing and Meta-Analysis: How to be a Good Consumer of Scientific Literature Reviews
(Indiana University Workshop in Methods, 2015-02-06) Valentine, Jeffrey
Policymakers, researchers, and practitioners are increasingly likely to value systematic reviews. However, the quality of systematic reviews varies widely. This workshop will (a) describe the history and logic of systematic reviewing and meta-analysis, (b) demonstrate the ways in which systematic reviews provide a better method for assessing what a body of evidence reveals about the relationships under study, and (c) walk participants through a simple meta-analysis. The workshop will conclude with a core list of questions that can be asked of any systematic review to assess its quality.
Introduction to Regression Models for Panel Data Analysis
(Indiana University Workshop in Methods, 2015-02-13) McManus, Patricia
Panel methods are appropriate for large-N, small-T data where N represents individual units – for example persons, families, organizations, cities – observed at two or more points in time T. This workshop covers the basic theory underlying the analysis of panel data along with essential terminology, an overview of the kind of data that are appropriate for panel analysis, examples from various disciplines, and a list of common mistakes made when working with panel data models. We then work through an example of an application of the linear error components model from assumptions to estimation, specification tests and interpretation. The workshop concludes with a brief discussion of limitations, extensions, and related approaches.
A Brief Introduction to Multilevel Modeling: Concepts & Applications
(Indiana University Workshop in Methods, 2015-02-27) Rutkowski, Leslie
In this two-hour workshop, participants will be provided with a brief overview of multilevel modeling concepts and several applications, including random intercepts and random slopes models. Several examples will be provided along with SAS syntax and a data set will be made available. Participants will have an opportunity to fit several models in SAS and interpret the results.
Nonparametric statistics for social scientists
(Indiana University Workshop in Methods, 2015-04-10) Luen, Brad
Parametric statistical methods may perform poorly when their assumptions are violated. For example, the t-test may have low power when samples are not from normal distributions, while linear regression will predict poorly when the relationships between variables is not linear. "Nonparametric statistics” refers to a broad range of techniques that avoid restrictive parametric assumptions about populations or data. We will explore two very different nonparametric methods: Rank tests, where hypotheses are tested by comparing the ranks of samples, and smoothing splines, which fit smooth curves and surfaces to data that may not be linear. We will implement these techniques in R, and discuss when it may or may not be appropriate to use these techniques instead of their parametric counterparts.
The Grammar of Graphics: An Introduction to ggplot2
(Indiana University Workshop in Methods, 2015-04-24) Davis, Jefferson
In The Grammar of Graphics, Leland Wilkinson laid out 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 cover 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.
What Is The Impact of Smartphone Optimization on Long Surveys?
(2015-06-24) Sarraf, Shimon; Brooks, Jennifer; Cole, James; Wang, Xiaolin
Each year, an increasing number of college student survey respondents are accessing online surveys using smartphones, instead of desktop computers (Sarraf, Brooks, & Cole, 2014). In 2011, about 4% of respondents to the National Survey of Student Engagement (NSSE) used a smartphone, but by 2015 the proportion increased to about 27%. The widespread adoption of smartphones among college students has prompted discussions among some institutional and higher education researchers about data quality and appropriate survey formats. Some research suggests that there is little or no substantive difference for users accessing web surveys on tablets as compared to desktop machines, but the user experience on a smartphone is recognized to be significantly different than the other devices (Buskirk & Andrus, 2012). This has caused some researchers to optimize their online surveys for smartphones, however research is limited about how this may affect survey data quality. Using results from a ten institution experiment using the 2015 National Survey of Student Engagement (NSSE) the current study details the impact that smartphone optimization has on a survey with over one hundred questions. Study research questions center on how various data quality indicators are effected by optimizing a survey for smartphones, including item skipping, completion time, scale factor structure, and response option differentiation (straight-lining). Based on their recent experience, presenters will offer insights into developing a smartphone-optimized version of a relatively long survey.
Examining the Impact of Mobile First and Responsive Web Design on Desktop and Mobile Respondents
(2015-06-24) Tharp, Kevin
Mobile First and Responsive Web Design are two approaches that survey researchers can utilize to improve the experiences of smart phone users, who make up a growing proportion of web survey respondents. The Mobile First approach has a layout optimized for smart phones that also serves as the basis for the desktop design, while Responsive Web Design allows for more dynamic adjustments based on browser size. We conducted experiments with each design within the past year. Both experiments were attempts to better meet the needs and expectations of mobile respondents with designs that could also be employed for desktop respondents with minimal differences in layout. For each, a random sample of respondents was assigned to receive the experimental version of each survey, while other respondents were assigned to a more traditional, desktop-focused design. The Mobile First experiment was conducted first. Smart phone users who were assigned the Mobile First layout were less likely to break off, and had lower duration times than smart phone users assigned to the traditional design. They also gave the Mobile First design higher ratings in a short post-survey evaluation questionnaire. Desktop users, however, had longer duration times when completing the Mobile First design when compared to the traditional design. They also rated the Mobile First design lower on professional appearance, and commented on excessive need for scrolling. We found no significant differences in response distribution among the layout versions and devices. Our second experiment was designed to address these specific concerns of desktop while maintaining the positive benefits for smart phone users. When this additional experiment is completed, we will compare both designs, considering data quality, response rates, evaluation scores, cost, and development time.
A Comparison of Online Panels with GSS and ANES Data
(2015-06-24) Zack, Elizabeth; Kennedy, John
In the past five years, researchers have increasingly used low cost data collection methods to conduct surveys. Survey data collection software platforms such as Qualtrics and Survey Monkey allow researchers to easily and cheaply create questionnaires for distribution. Similarly, low cost methods are available to recruit survey participants. Some of these include online panels, Amazon’s Mechanical Turk (MTurk), and Google Consumer Surveys. With these tools, researchers are much less dependent on professional survey researchers to conduct surveys. More importantly however, survey researchers are now using non-probability online panels as a substitute for probability samples. In 2010 and 2013, AAPOR released task force reports that analyzed the challenges encountered when using online panels and nonprobability samples for high quality survey research. In 2014, a book on the use of online panels in survey research included chapters written by respected survey researchers (Callegaro et al, 2014). In the past five years, at least 20 peer-reviewed methods articles were published on the use of Mechanical Turk for social and behavioral science research. Despite the cautions raised about the appropriate use of online panels, they are being used more often, e.g., the YouGov panel and CBS News. In this presentation, we will discuss the results of a number of experiments we conducted that compared distributions in questions asked recently in the ANES and GSS to similar questions asked with MTurk samples and a Qualtrics online panel. In addition, we will show how simple multivariate models are similar and different using data from both the probability and non-probability samples. This presentation will contribute to the continuing research into the appropriate uses of online panels for survey research.
Developing and Testing a Framework for Understanding Public Support of "Fracking"
(2015-06-24) Alcorn, Jessica; Schenk, Olga; Graham, John; Rupp, John; Carley, Sanya; Lee, Michelle; Zhang, Yu; Clark, Ashley
As citizens within many U.S. states have interacted with increased natural gas production through unconventional gas development (UGD), the public’s attitudes towards the practice have not been straightforward. Previous research on acceptance of energy technologies, and UGD specifically, highlight a wide range of factors that may drive public attitudes, namely sociodemographic characteristics and political ideology. Decades of research have also sought to explore the dimensionality of environmental attitudes; however, the theoretical frameworks and methods from this literature have not been employed in analyzing attitudes towards specific kinds of energy development. In this study, we conducted a survey of adult U.S. residents in six U.S. states where UGD is underway or geologically promising: three states with high and/or growing production (Ohio, Pennsylvania, and Texas) and three that have little or no UGD (New York, Illinois, and California). We analyze both whether respondents typically identify different components of advantages and disadvantages of UGD in their attitudes and what factors influence attitudes. Our analysis comports with prior research indicating that those who identify as White or male perceive fewer disadvantages of UGD. As expected, older respondents and those who receive royalty payments perceive more advantages of UGD, and those who identify as members of the Democratic Party perceive more disadvantages of UGD. However, the role of education in influencing attitudes remains somewhat unclear. With respect to dimensionality, we find that respondents generally do not differentiate between the various aspects of potential advantages and disadvantages of UGD.
Using jsPsych to Conduct Behavioral Research Online
(Indiana University Workshop in Methods, 2015-09-04) de Leeuw, Josh
Behavioral scientists have been using the internet to conduct research for over two decades, but only recently has the scope of internet research begun to rival the traditional laboratory experiment. In this workshop, I will introduce you to the basics of online data collection and various tools for conducting online research, including jsPsych (http://www.jspsych.org), a programming library for conducting laboratory-like experiments online developed at Indiana University. I'll describe all the necessary components of running an online experiment, the features of jsPsych, and how to create a simple experiment using the jsPsych library.
Probabilistic Topic Models and User Behavior
(Indiana University Workshop in Methods, 2015-10-16) Blei, David
Probabilistic topic models provide a suite of tools for analyzing large document collections. Topic modeling algorithms discover the latent themes that underlie the documents and identify how each document exhibits those themes. Topic modeling can be used to help explore, summarize, and form predictions about documents. Topic modeling ideas have been adapted to many domains, including images, music, networks, genomics, and neuroscience. Traditional topic modeling algorithms analyze a document collection and estimate its latent thematic structure. However, many collections contain an additional type of data: how people use the documents. For example, readers click on articles in a newspaper website, scientists place articles in their personal libraries, and lawmakers vote on a collection of bills. Behavior data is essential both for making predictions about users (such as for a recommendation system) and for understanding how a collection and its users are organized. In this talk, I will review the basics of topic modeling and describe our recent research on collaborative topic models, models that simultaneously analyze a collection of texts and its corresponding user behavior. We studied collaborative topic models on 80,000 scientists' libraries from Mendeley and 100,000 users' click data from the arXiv. Collaborative topic models enable interpretable recommendation systems, capturing scientists' preferences and pointing them to articles of interest. Further, these models can organize the articles according to the discovered patterns of readership. For example, we can identify articles that are important within a field and articles that transcend disciplinary boundaries. More broadly, topic modeling is a case study in the large field of applied probabilistic modeling. Finally, I will survey some recent advances in this field. I will show how modern probabilistic modeling gives data scientists a rich language for expressing statistical assumptions and scalable algorithms for uncovering hidden patterns in massive data.

Browse

Browsing Social Science Research Commons by Issue Date