A Systematic Method for the Selection of Independent Variables in the Investigation of Complex Systems

Abstract

This paper describes a systematic methodology for selecting independent variables to be considered in large-scale research problems. Five specific procedures including brainstorming, prototype interface representation, feasibility/relevance analyses, structured literature reviews, and user subjective ratings are evaluated and incorporated into an integrated strategy. This methodology is demonstrated in the context of designing the user interface for a telephone-based information inquiry system. The procedure was successful in reducing an initial set of 95 independent variables to a subset of 19 factors that warrant subsequent detailed analysis. These results are discussed in terms of a comprehensive sequential research methodology useful for investigating human factors problems.

Get full access to this article

View all access options for this article.

References

Box

G. E. P.

Hunter

W. G.

Hunter

J. S.

(1978). Statistics for experimenters. New York, NY: Wiley.

Geiselman

R. E.

Samet

M. G.

(1982). Notetaking and comprehension for computer displayed messages: Personalized versus fixed formats. In Proceedings of Human Factors in Computer Systems (pp. 45–50). Washington, DC: National bureau of Standards.

Meister

, (1985). Behavioral Analysis and Measurement Methods. New York, NY: Wiley.

Simon

C. W.

(1977). Design, analysis, and interpretation of screening studies for human factors engineering (Tech. Report CWS-03–77). Westlake Village, CA: Canyon Research Group.

Williges

R. C.

Mills

R. G.

(1982). Catalog of methodological considerations for systems experimentation (Tech Report) Wright-Paterson Air Force Base, OH: Aeronautical Systems Division.