Survey Research And Methodology Program
First Advisor
Jolene D. Smyth
Date of this Version
12-2016
Citation
Powell, R. J. (2016). An Experimental Examination of Visual Grouping Techniques in Skip Patterns on Respondent Navigation Errors (Doctoral Dissertation). Retrieved from University of Nebraska Digital Commons.
Abstract
Researchers are able to obtain better coverage and response rates with mail surveys compared to landline telephone surveys due to (1) easier access to the United States Postal Service (USPS) Computerized Delivery Sequence File (CDSF) (Iannacchione, 2011), and (2) the rise of households with no landline telephone (Blumberg and Luke, 2016). However, the use of the mail mode raises important challenges, such as the need to help respondents navigate the questionnaire without interviewer assistance.
As not all questions asked are relevant to all respondents, skip patterns are introduced to navigate respondents around questions that do not apply to them. With no computers or interviewers to assist, respondents may commit one of three errors: omission errors (failure to answer follow-up questions when they should have answered them), commission errors (answer follow-up questions when they should have skipped them), or item nonresponse (failure to answer initial filter question).
The first published empirical piece on this topic reported results of an experiment for the 2000 US decennial census where adding verbal and visual cues significantly decreased skip errors (Redline et al., 2003). Since this research was conducted, there has been enormous growth within survey methodology in understanding how respondents process visual information. Survey methodologists have drawn on concepts from the visual sciences and cognitive psychology to better understand how visual design can be used strategically in questionnaire design (Dillman et al., 2014; Tourangeau et al., 2004).
This dissertation research tests three visual design elements aimed at further decreasing skip errors in mail surveys—common region, indentation, and sub-numbering. Each design is intended to create stronger grouping and subgrouping among items within skip patterns, making navigation through them clearer and decreasing skip errors. The overall effectiveness of each element is assessed by examining rates of item nonresponse on the first question of the skip pattern, omission and commission errors. Error rates will also be examined for respondents of different age, education, literacy, and motivation levels.
Advisor: Jolene D. Smyth
Comments
A Dissertation Presented to the Faculty of The Graduate College at the University of Nebraska In Partial Fulfillment of Requirements For the Degree of Doctor of Philosophy, Major: Survey Research and Methodology, Under the Supervision of Professor Jolene D. Smyth, Lincoln, Nebraska: December, 2016
Copyright 2016 Rebecca J. Powell