This paper provides a comprehensive review of over a dozen sensitivity analysis techniques used in environmental modeling. Sensitivity analysis helps identify parameters that most influence model results, which is critical for model validation and guiding future research. The review is intended for those unfamiliar with statistics or sensitivity analysis techniques. The most basic method involves partial differentiation, while a simpler approach involves varying parameters one at a time. Correlation analysis determines relationships between variables, and regression analysis provides the most comprehensive sensitivity measure, often used to build response surfaces. Sensitivity analyses are typically conducted by defining the model, assigning probability distributions to inputs, generating input matrices, and assessing input-output relationships. Various methods exist, but they may not always yield identical results. The paper discusses several techniques, including differential analysis, one-at-a-time design, factorial design, sensitivity and importance indices, subjective analysis, scatter plots, relative deviation methods, correlation coefficients, rank transformation, regression techniques, and statistical tests. It also briefly mentions advanced methods like structural identifiability, adjoint equations, Fourier analysis, and Green's functions, which are used for complex models. The paper highlights the practicality of methods based on computational ease and result usefulness. It emphasizes the importance of evaluating the relative merits of techniques against their cost and resource requirements. A separate paper compares these methods in a numerical study on probabilistic dose assessment. The review aims to provide a clear understanding of various sensitivity analysis techniques for environmental modeling.This paper provides a comprehensive review of over a dozen sensitivity analysis techniques used in environmental modeling. Sensitivity analysis helps identify parameters that most influence model results, which is critical for model validation and guiding future research. The review is intended for those unfamiliar with statistics or sensitivity analysis techniques. The most basic method involves partial differentiation, while a simpler approach involves varying parameters one at a time. Correlation analysis determines relationships between variables, and regression analysis provides the most comprehensive sensitivity measure, often used to build response surfaces. Sensitivity analyses are typically conducted by defining the model, assigning probability distributions to inputs, generating input matrices, and assessing input-output relationships. Various methods exist, but they may not always yield identical results. The paper discusses several techniques, including differential analysis, one-at-a-time design, factorial design, sensitivity and importance indices, subjective analysis, scatter plots, relative deviation methods, correlation coefficients, rank transformation, regression techniques, and statistical tests. It also briefly mentions advanced methods like structural identifiability, adjoint equations, Fourier analysis, and Green's functions, which are used for complex models. The paper highlights the practicality of methods based on computational ease and result usefulness. It emphasizes the importance of evaluating the relative merits of techniques against their cost and resource requirements. A separate paper compares these methods in a numerical study on probabilistic dose assessment. The review aims to provide a clear understanding of various sensitivity analysis techniques for environmental modeling.