A basic methodological approach in developmental studies is the collection of longitudinal data. Behavioral data cen take at least two forms, qualitative (or discrete) and quantitative. Both types are fallible. Measurement errors can occur in quantitative data and measures of these are based on error variance. Qualitative or discrete data can contain misclassification errors, and these are expressed as probabilities of misclassification. Statistical models for psychological data must take these differences into account. A simple sequence is presented as an example of a qualitative model, while disengagement is the model given as an example for quantitative data. These examples, which are special cases of more general problems, lead to an outline of the general nature of the qualitative and quantitative models. The primary concern here is to develop statistical models which permit the investigation of structure in fallible longitudinal data. Statistical descriptions of the simple sequence and disengagement models are included in the appendix. (CK)