In this paper, we present a novel approach that enables network researchers to quickly select the most accurate modeling and analysis method for a given wired or wireless network path and network characteristic of interest (e.g., delay, loss, or error process). Amongst the network models that our approach includes in its analysis are two data preconditioning models that we have developed as a part of the Tapas project, an investigation into new approaches for accurately modeling and analyzing the behavior of various time-varying network path characteristics. Traditional modeling approaches, such as Discrete Time Markov Chains (DTMC) are limited in their ability to model time-varying characteristics. This problem is exacerbated in the wireless domain, where fading events create extreme burstiness of delays, losses, and errors on wireless links. We introduce a new approach to the modeling of network characteristics, the data preconditioning methodology, and present the latest application of this methodology, the Modified hidden Markov Model (M3). Our domain analysis methodology defines and classifies binary network traces (i.e., traces which describes the occurrence or the lack of occurrence of a network event over time), and using these classifications, it determines the most accurate model or models from a set of models.