ONSITE | May 11, 2022 | 8:00 am - 11:30 am CST
Instructors: Chuck Shuttles and Jordon Peugh
Most public opinion professionals begin their careers working on projects whose budgets were created by others in their organization and they must live within the constraints of those budgets. This course is designed for those interested in better understanding budget creation and are ready to improve their own budget skills specific to public opinion research projects. Students will learn how to break down a project into manageable segments, multiple methods for estimating costs, how to build the budget as a model where assumptions change, and how to manage the budget over the life of the project.
This is not a lecture course. The entire course will be a hands-on / interactive exercise where you will be guided through the budget planning / building process (i.e., laptop computer with Excel or Google Sheets required). The instructors will discuss real-world demands made on anyone creating or managing a budget, e.g., “the client needs this to cost less than $X,” “we need X% profit margin,” “we must deliver results in X days / weeks / months,” or all of the above). In the end, students will experience the steps to building a project budget and prepare for the efficient management of project costs.
ONSITE | May 11, 2022 | 8:00 am - 11:30 am CST
Instructors: Marieke Haan and Yfke Ongena
Measuring someone's health by means of questionnaires is a challenging task. The concept of health is very broad - it encompasses a person's physical, social and mental state – which makes conceptualization difficult. In addition, there is a high risk of socially desirable answers, since people like to indicate that they are doing well. Finally, health research is often conducted among people who are not fit or the elderly for whom surveys are a cognitively demanding task.
This course will focus on both quantitative and qualitative data collection techniques to measure health. First, participants will learn more about implementation of surveys in hospital waiting rooms, taking the Total Survey Error Framework into account. Special attention will be paid to the risks of socially desirable answers. Second, participants will learn about collecting qualitative data on health through semi-structured interviews and researcher driven photo-elicitation interviews. Ensuring the scientific quality of these forms of data collection will be discussed on the basis of Guba and Lincoln's trustworthiness criteria. Finally, we pay attention to analyzing qualitative data by means of a thematic analysis.
ONSITE | May 11, 2022 | 8:00 am - 11:30 am CST
Instructor: Mamadou S. Diallo
Survey samples are often selected using predefined probabilistic methods from finite populations. Complex sampling designs are used to facilitate fieldwork and keep costs under control (e.g., stratification, clustering, stage sampling, etc.), resulting in samples with unequal selection probabilities. Techniques such as sample selection, weight adjustment, and sample analysis need to account for the complexity of the sampling design. I developed a Python package named samplics, which implements sample size calculation, sample selection, population parameter estimation, and small area prediction to allow Python users to work with survey data more efficiently.
This talk will show how a survey statistician can use Python and, more specifically, samplics to conduct a comprehensive survey. More specifically, I will show how to calculate sample size, use SRS and PPS techniques to select samples, calculate and adjust sample weights, estimate linear and non-linear population parameters using Taylor-based and replication-based techniques, including calibration techniques such as GREG, post-stratification, raking. In addition, I will illustrate regression techniques under the complex sampling design using samplics. Finally, if time allows, I will introduce conducting basic small area estimation (SAE) methods using samplics.
ONSITE | May 11, 2022 | 8:00 am - 11:30 am CST
Instructor: Michael Bailey
Survey researchers typically deal with non-response via weighting, quota sampling and multilevel regression and post-stratification (MRP). These tools are powerful, but do not address non-ignorable non-response, the kind of response that occurs when non-response is directly related to the content being surveyed. Ironically, non-ignorable non-response is often ignored, a pattern this course seeks to counteract by exploring survey research through the lens of non-ignorable non-response. This entails understanding first how ignorable and non-ignorable non-response have been important in the history of polling, including in the highly fluid contemporary era. Second, this involves thinking deeply about why non-ignorable non-response poses such dangers for polling, especially modern polling that is typically based either on opt-in internet samples or random samples with very low response rates.
The course ends on a constructive note. We need not be passive or fatalistic in the face of potential non-ignorable non-response. There is a broad and growing toolkit for dealing with non-ignorable non-response. Using this toolkit makes new demands on the data, but not unreasonable ones.
The goal is that participants emerge with a stronger understanding of this important potential source of survey error and a grasp of the tools to help tame it.