Misclassification arises from errors in measuring study data.
Nondifferential misclassification results from random errors that occur roughly equally within a study population.
Nondifferential misclassification usually yields measures of association that are closer to the null value of 1.0.
Differential misclassification results from systematic errors that occur preferentially within a subset of a study population.
Differential misclassification may obscure true associations, falsely amplify associations, or create false associations
Uniform data collection procedures help to minimize the possibility for differential misclassification.