This chapter introduces the concepts of sensitivity analysis and uncertainty analysis in the context of model building. It begins by defining sensitivity analysis as the study of how uncertainty in model outputs can be attributed to different sources of uncertainty in model inputs. The chapter emphasizes the importance of distinguishing between numerical and non-numerical models, as well as between inputs and outputs. It discusses the role of uncertainty and sensitivity analyses in model building, highlighting the need for both to be conducted together. The chapter then delves into the nature of models, explaining that models can be diagnostic or prognostic, data-driven or law-driven. It also addresses the challenges of model indeterminacy and the limitations of physical laws in simplifying complex systems. The discussion on uncertainty highlights the inherent uncertainty in scientific inquiry and the need for rigorous methods to assess model robustness. The chapter outlines the steps for setting up uncertainty and sensitivity analyses, including the estimation of model parameters and the propagation of uncertainty through the model. It introduces the concept of parametric bootstrap and bootstrapping of the modeling process, emphasizing the importance of careful selection of inputs for analysis to avoid introducing biases. Finally, the chapter discusses the implications for model quality, noting that the choice of inputs for analysis can significantly impact the results. It emphasizes the need for a clear objective in defining a factor's importance and introduces the concept of "settings" in sensitivity analysis, such as factor prioritization, to ensure that the analysis is meaningful and reliable.This chapter introduces the concepts of sensitivity analysis and uncertainty analysis in the context of model building. It begins by defining sensitivity analysis as the study of how uncertainty in model outputs can be attributed to different sources of uncertainty in model inputs. The chapter emphasizes the importance of distinguishing between numerical and non-numerical models, as well as between inputs and outputs. It discusses the role of uncertainty and sensitivity analyses in model building, highlighting the need for both to be conducted together. The chapter then delves into the nature of models, explaining that models can be diagnostic or prognostic, data-driven or law-driven. It also addresses the challenges of model indeterminacy and the limitations of physical laws in simplifying complex systems. The discussion on uncertainty highlights the inherent uncertainty in scientific inquiry and the need for rigorous methods to assess model robustness. The chapter outlines the steps for setting up uncertainty and sensitivity analyses, including the estimation of model parameters and the propagation of uncertainty through the model. It introduces the concept of parametric bootstrap and bootstrapping of the modeling process, emphasizing the importance of careful selection of inputs for analysis to avoid introducing biases. Finally, the chapter discusses the implications for model quality, noting that the choice of inputs for analysis can significantly impact the results. It emphasizes the need for a clear objective in defining a factor's importance and introduces the concept of "settings" in sensitivity analysis, such as factor prioritization, to ensure that the analysis is meaningful and reliable.