Mis Scholars Survey Research

Survey research is believed to be well understood and applied by MIS scholars. It has been applied for several years, it is well defined, and it has precise procedures which, when followed closely,yield valid and easily interpretable data. Our assessment of the use of survey research in the MIS field between 1980 and 1990 indicates that this perception is at odds with reality. Our analysis indicates that survey methodology is often misapplied and is plagued by five important weaknesses: (1) single method designs where multiple methods are needed, (2) unsystematic and often inadequate sampling procedures,(3) low response rates, (4) weak linkages between units of analysis and respondents, and (5) over reliance on cross-sectional surveys where longitudinal surveys are really needed. Our assessment also shows thatthe quality of survey research varies considerably among studies of different purposes: explanatory studies are of good quality overall, exploratory and descriptive studies are of moderate to poor quality.This article presents a general framework for classifying and examining survey research and uses this framework to assess, review and critique the usage of survey research conducted in the past decade in the MIS field. In an effort to improve the quality of survey research, this article makes specific recommendations that directly address the major problems highlighted in the review.

Science may be said to progress on its methods. The production of knowledge depends very much on the techniques for collecting, analyzing, and interpreting data and on the way they are applied. The same may be said of management information systems (MIS). The academic study of MISrelies very much on the methods used to answer research questions and test research hypotheses, and on the careful application of these methods. Moreover, since the methods are borrowed for the most part from established disciplines, the issue of appropriate and skilful application becomes key. And this is especially the case in survey research where the basic methods have been known since the fifties, but where the application in many fields continues to fall short of the theoretical ideal. This review of 122 survey-based studies in MIS indicates that survey research in MIS suffers from the same problems that plague survey research generally: (1) single method designs where multiple methods are needed, (2) unsystematic and often inadequate sampling procedures, (3) low response rates, (4) weak linkages between units of analysis and respondents, and (5) over reliance on cross-sectional surveys where longitudinal surveys are really needed. On the one hand, this is reassuring in that one would expect a new field to have difficulties at first in adopting and applying methods developed in other fields for its own problems. On the other hand, it is disappointing, especially when one considers the extent to which survey research is used0 and the proportion of survey-based studies in