We report an experiment investigating graph comprehension. Verbal protocol data were collected while participants attempted to understand six bar or line graphs representing relationships between three variables. Analysis of the verbal protocols revealed significant differences in the level of comprehension between the two graph types. Specifically, a significant proportion of line graph users was either unable to interpret the graphs, or misinterpreted information presented in them. These errors did not occur in the bar graph condition. The difference is explained in terms of the high salience of the lines in line graphs which hinders the correct or full interpretation of the relationships depicted. The results of the experiment provide a strong rationale for the use of bar graphs to display such three-variable data sets, particularly for a general audience.