Prerequisites: 

"Paradata" are empirical measurements about the process of survey data themselves. They consist of visual observations of interviewers, administrative records about the data collection process, computer-generated measures about the process of the data col

Description: 

"Paradata" are empirical measurements about the process of survey data themselves. They consist of visual observations of interviewers, administrative records about the data collection process, computer-generated measures about the process of the data collection, external supplementary data about sample cases, and observations of respondents themselves about the data collection. Increasingly, survey methodologists are using paradata to provide insights into survey participation decisions (and attendant nonresponse errors) and the response formation process (and attendant measurement errors). This course will explore a variety of paradata to discover (jointly as a set of students and faculty) what properties of paradata are important and what analytic techniques are well-suited to exploiting them.

The course will have four parts:

a. Review of the (brief) literature on survey paradata

b. Review of analytic approaches to paradata

c. Student proposals on analysis of paradata

d. Analysis projects on paradata

Student Activities: Students will be responsible for reading careful the literature assigned, discussing it in class. Particular attention will be paid to identifying gaps in the past uses of paradata to answer questions about costs and errors of survey estimates. Each student will propose an analysis of paradata to be performed on data supplied by the instructors. The proposal will be written and presented in the class. Each student will conduct the proposed analyses and write a technical paper describing the analysis.