Problem of between-eye correlation for statistical hypothesis testing: rabbit corneal thickness

The two eyes of a subject often yield correlated data. Statistical analysis which treats correlated data as if it were independent is most likely to be biased toward statistical significance; that is, the probability of a type I error is likely to be inflated. To illustrate the importance of lack of independence to the inferential process, data from an experimental design commonly used in optometric research are used to demonstrate (1) the potential magnitude of between-eye correlation, (2) the statistical bias toward a significant outcome when the between-eye correlation is ignored via inappropriate analysis, and (3) simple ways by which the bias can be avoided. The researcher must be aware of the between-eye correlation which exists for the particular effect under study, and the statistical bias that ensues from the correlation when the data are not handled correctly.