An alternative to using large numbers of test participants is offered for HF professionals with limited budgets. This alternative justifies design decisions using effect size estimates which have been calculated from published data germane to the design of the particular system. The calculations for effect size estimation are given in simple algebra, using only the information available from published ANOVA summary tables.
Get full access to this article
View all access options for this article.
References
1.
CohenJ. (1977) Statistical Power Analysis for the Behavioral Sciences. (Rev. Ed). New York: Academic Press.
2.
DoddD.J.SchultzR.F.Jr. (1973) Computational procedures for estimating magnitude of effect for some analysis of variance designs. Psychological Bulletin.79, 391–395.
3.
GrahamN.E. (1956) The speed and accuracy of reading horizontal, vertical, and circular scales. The Journal of Applied Psychology.40, (4), 228—232.
4.
KeppelG. (1982) Design and Analysis: A Researcher's Handbook. (2nd Ed.) Englewood Cliffs, NJ: Prentice Hall.
5.
MarrasW.S.KroemerK.H.E. (1980) A method to evaluate human factors / ergonomics design variables of distress signals. Human Factors22(4).
6.
RosenthalR. (1984) Meta-Analytic Procedures for the Social Research.Beverly Hills, CA: Sage Publications.
