Description

Online survey applications typically offer the capability to individually randomize the order in which survey items are presented to subjects, a method that structurally eliminates several sources of method bias inherent to static surveys. IS researchers who use online surveys have a strong interest in knowing how prior surveys were administered in published research, however, we find this information is rarely available in current practice. This paper presents a call for increased transparency in reporting item-ordering methodology in future online IS survey research. This call is based on 1) a literature review of online survey research published in the AIS Senior Scholars’ Basket of Journals, 2) results of new research comparing reliability and construct validity characteristics produced by individually-randomized vs. static survey administration methods, and 3) results of hypothetical structural equation modeling (SEM) analyses contrasting structural models following purification of the individually-randomized and static datasets.

Share

COinS
 
Aug 10th, 12:00 AM

A Call for Item-ordering Transparency in Online IS Survey Administration

Online survey applications typically offer the capability to individually randomize the order in which survey items are presented to subjects, a method that structurally eliminates several sources of method bias inherent to static surveys. IS researchers who use online surveys have a strong interest in knowing how prior surveys were administered in published research, however, we find this information is rarely available in current practice. This paper presents a call for increased transparency in reporting item-ordering methodology in future online IS survey research. This call is based on 1) a literature review of online survey research published in the AIS Senior Scholars’ Basket of Journals, 2) results of new research comparing reliability and construct validity characteristics produced by individually-randomized vs. static survey administration methods, and 3) results of hypothetical structural equation modeling (SEM) analyses contrasting structural models following purification of the individually-randomized and static datasets.