Nonlinear time series models incorporating exogenous regressors provide the foundation for numerous significant models across econometrics, queuing theory, machine learning, and various other disciplines. Despite their importance, the framework for the statistical analysis of such models is still incomplete. In contrast, multiple versions of the law of large numbers and the (functional) central limit theorem have been established for weakly dependent variables. We prove the transition of mixing properties of the exogenous regressor to the response through a coupling argument, leveraging these established results. Furthermore, we study Markov chains in random environments under a suitable form of drift and minorization condition when the environment process is non-stationary, merely having favorable mixing properties. Following a novel statistical estimation theory approach and using the Cram\'er-Rao lower bound, we also establish the functional central limit theorem. Additionally, we apply our framework to single-server queuing models. Overall, these results open the door to the statistical analysis of a large class of random iterative models.