Date of Award

9-1992

Document Type

Thesis

Degree Name

Master of Science

First Advisor

David S. Christensen, PhD

Second Advisor

Richard Antolini

Abstract

This thesis investigated whether a scale break on the dependent axis a affects a decision maker's interpretation of the data presented in the graph. A literature search revealed criteria for constructing high integrity graphs and formatting scale breaks. An experiment was conducted to determine the effect of a scale break on the dependent axis. Graphs following the criteria for high integrity graphs were presented to the control group, while graphs following the criteria for high integrity graphs, with the exception of the scale break, were presented to the experimental group. Using a parametric two-sample t test and a non-parametric Rank Sum test, it was shown that data presented in a graph with a scale break was interpreted differently from data presented in a graph without a scale break. Analysis of variance was conducted on the demographic factors for each subject. In the experimental group, sex and professional experience were factors that led to different interpretations of graphs with a scale break. The level of experience using graphs in decision making was also a factor that led to different interpretations of graphs in both groups.

AFIT Designator

AFIT-GSM-LSY-92S-5

DTIC Accession Number

ADA258989

Comments

The authors' Vita pages are omitted.

Presented to the Faculty of the School of Systems and Logistics

Download

Share

COinS