Understanding Sample Surveys: Selective Learning about Social Science Research Methods (original) (raw)

Turning the tables: making surveys relevant in the classroom

International Journal of Information and Operations Management Education, 2012

Researchers want to survey students. Instructors have little incentive to allow their class to be surveyed and students have little incentive to be surveyed. This paper suggests a solution to this problem for researchers, students and instructors of statistics classes. Research suggests that active survey announcement and the offering of extra credit increases survey response rates over passive survey announcement and no extra credit. Therefore, a course instructor can have an influential role in the response rate of electronic surveys administered over time. Instructors can offer extra credit in good conscience if the survey offers a class benefit that can be used for discussion and class activity. Students receive extra credit towards their grade as well as experience working with new data sets. Instructors receive an additional teaching opportunity, and researchers receive a high survey response rate. The process of engaging the researcher, the instructor and the students is detailed.

Engaging Students in Survey Research Projects across Research Methods and Statistics Courses

Teaching Sociology, 2016

One innovative way to help students make sense of survey research has been to create a multifaceted, collaborative assignment that promotes critical thinking, comparative analysis, self-reflection, and statistical literacy. We use a short questionnaire adapted from the Higher Education Research Institute’s Cooperative Institutional Research Program’s Freshman Survey. In our Research Methods course, students begin by administering the brief questionnaire to a small, nonrandom sample of students at our university. They analyze the data descriptively and compare their “results” to the national trends as part of their required course homework. These data are then quantitatively analyzed throughout all homework exercises the next semester during their statistics course. This collaborative effort bridges methods, statistics, and capstone courses, helping students connect the courses and develop a deeper understanding, awareness and appreciation of the utility of preestablished instruments...

Introducing Undergraduates to Concepts of Survey Data Analysis

Journal of Statistics Education

Increasingly students, particularly those in the social sciences, work with survey data collected through a more complex sampling method than a simple random sample. Failing to understand how to properly approach survey data can lead to inaccurate results. In this article, we describe a series of online data visualization applications and corresponding student lab activities designed to help students and teachers of statistics better understand survey design and analysis. The introductory and advanced materials presented are designed to focus on a conceptual understanding of survey data and provide an awareness of the challenges and potential misuse of survey data. Suggestions and examples of how to incorporate these materials are also included. Supplementary materials for this article are available online.

Experiential Learning Revisited: Lessons from a Student-Led Public Opinion Polling Class

PS: Political Science & Politics

For decades, political and private polling operations have informed about the public’s perceptions regarding a range of topics. In particular, universities (e.g., Marist and Quinnipiac) provide noteworthy research to inform and predict the outcomes of US elections. Yet, what role do our classrooms play in advancing the public opinion polling skills of our students? This article uses experiential learning as a descriptive framework to illustrate how a yearlong, immersive, and student-led public opinion polling experience, the Big Sky Poll, advances students’ social-science and data-fluency skills. Our findings suggest important insights into the future of public opinion polling from the vantage point of a rural Western state, which can be replicated in other academic institutions.

Syllabus: iTV / Poli Sci U Course on Survey Experiments

p.m. In Person iTV / Poli Sci U: Survey Experiments Course Description Given decreased costs of collecting survey data and the desire to make causal inferences in political science research, survey experiments have become widespread in political science. Focusing primarily on vignette-based survey experiments, this course (1) reviews the methodological logic behind survey experiments; (2) exposes students to prominent examples in the literature; (3) explores questions of internal and external validity; and (4) examines recent advances in survey experiment design and analysis. Course Goals Through engagement with the readings, course lectures, and in-class discussion and through completion of the assignments in this course, students will improve their capacities for (1) critically reading research that uses (survey) experimental methodologies; (2) discussing (survey) experimental research in professional settings; and (3) developing experimental (and non-experimental) research. At the end of the course, students will have developed, in consultation with their peers and the instructor, their own research design using survey experimental methods for a substantive question of interest to them. Course Requirements Students are expected to come to class prepared having done the required readings for the week and to engage in class conversation.

Teaching Sample Survey Design—A Project Using a Virtual Population

Journal of Statistics Education

Sample survey design is a topic usually taught to students undertaking a minor or major in statistics in the latter part of their bachelor's degree. This article describes an assessment project that fosters active learning and helps to develop a set of essential skills for statistical practice. The project is completed in pairs and submitted in two parts. This allows feedback from the first part to be acted upon for the second part. Ideally, students would gain experience sampling from an actual population. However, the time involved in obtaining approval from the university's ethics committee may not be feasible for a short course. An alternative is to use an online virtual population such as the Islands, which provides students with an experience in setting up a sampling frame, requesting consent from potential participants, and collecting data. Proficiency in written communication and teamwork are highly valued by employers of statistics graduates. This project encourages collaborative learning in the design of the sample survey, statistical analysis of data collected, and the development of a final written report. It can easily be adapted for first year students and also be extended to suit Honors or Masters level students.

The Logic of the Survey Experiment Reexamined

Political Analysis, 2006

Scholars of political behavior increasingly embed experimental designs in opinion surveys by randomly assigning respondents alternative versions of questionnaire items. Such experiments have major advantages: they are simple to implement and they dodge some of the difficulties of making inferences from conventional survey data. But survey experiments are no panacea. We identify problems of inference associated with typical uses of survey experiments in political science and highlight a range of difficulties, some of which have straightforward solutions within the survey-experimental approach and some of which can be dealt with only by exercising greater caution in interpreting findings and bringing to bear alternative strategies of research.