Interpretations of graphs seem to be rooted in principles of cognitive natu
ralness and information processing rather than arbitrary correspondences. T
hese predict that people should more readily associate bars with discrete c
omparisons between data points because bars are discrete entities and facil
itate point estimates. They should more readily associate lines with trends
because lines connect discrete entities and directly represent slope. The
predictions were supported in three experiments-two examining comprehension
and one production. The correspondence does not seem to depend on explicit
knowledge of rules. Instead, it may reflect the influence of the communica
tive situation as well as the perceptual properties of graphs.