Friday, November 11
Data Quality and Measurement Error
Fri, Nov 11, 4:00 PM - 5:25 PM
Hibiscus B
Understanding the Role of Questionnaire Design in Measurement Error

Adult Education Survey in the Mixed-Mode Design (303377)

*Eva Belak, Statistical Office of the Republic of Slovenia 
Marta Arnez, Statistical Office of the Republic of Slovenia 
Vasja Vehovar, University of Ljubljana 

Keywords: mixed-mode design, web surveys, re-interviewing, paradata, measurement error, fieldwork strategy

The Statistical Office of the Republic of Slovenia will implement the Adult Education Survey in autumn 2016. The survey was last conducted in 2011 in sequential mixed mode design, where telephone interviewing (CATI) was followed by face-to-face interviewing (CAPI), but due to coverage and financial reasons, the plan is to have web survey mode with invitations sent out by mail followed by CATI and CAPI.

For the 2016 survey the feasibility of web survey mode has already been tested. In April 2016 the pilot web survey was conducted (n=2,075). The main goal of the pilot was to assess the quality of the reported informal and formal activities for precise coding; other goals were to analyze in detail the obtained paradata (interviewing time depending on how may activities were reported, drop-off rate, etc.) and to test the overall response rate and the response rate by different age groups and other socio-demographic characteristics of the selected persons.

Having conducted the pilot web survey, the re-interview survey was conducted in CATI mode with 500 units. With the re-interview survey the quality of the web questionnaire was assessed: what the number of formal or informal activities reported by the same respondent by different modes is, and also what the matching rate of the activities reported and coded by different modes is. In the web survey respondents were asked to describe in detail which activities they attended, while in the CATI re-interview the interviewer directly coded the activities. The purpose of the re-interview was also to evaluate why selected persons did not cooperate in the web surveys.

Results of both the pilot and the re-interview survey will be presented. The main added value of this paper is to illustrate the problems related to the introduction of a web survey data collection into a mainstream survey data collection: in what circumstances and when could (or should) this be done? What justifications and preliminary studies are required for this? What are the risks involved?