The purpose of this project is to develop sensitivity analysis methods for Structural Equation Modeling (SEM). A second purpose is to implement the methods developed in the SEMsens package for the R statistical software, allowing applied researchers to easily run and report SEM sensitivity analyses. Sensitivity analysis quantifies how strongly related an omitted confounder must be to observed variables for the conclusions of the analysis to change. In SEM, sensitivity analysis can be done by specifying a phantom variable that acts as a potential omitted confounder, but this method requires manual specification of complex path configurations between the phantom variable and several variables in the model. This difficulty can be overcome with metaheuristic optimization algorithms that have been used for specification searches in SEM, such as the (1) ant-colony optimization algorithm, (2) Tabu search, (3) genetic algorithm, and (4) simulated annealing. These algorithms can search for the smallest set of paths between an omitted confounder and the model’s variables that would lead to a change in the researcher’s conclusions about the statistical significance of coefficients. The methods developed in this project will increase educational researchers’ understanding of the strengths and limitations of their models, specifically about the extent to which their conclusions could change due to omitted confounders. We created the SEMsens R package for sensitivity analysis in SEM with functions to implement each metaheuristic algorithm. The SEMsens package connects to the lavaan R package to run models, which allows the sensitivity analysis to incorporate many advanced features available in this programs. Related materials: Posters from AERA 2021 Annual Meeting: https://aera21-aera.ipostersessions.com/default.aspx?s=18-03-9C-94-90-B5-BA-15-74-99-CA-E0-11-06-D4-CD https://aera21-aera.ipostersessions.com/default.aspx?s=D5-D2-0B-EE-A2-18-99-91-B0-C1-11-FE-E8-83-15-52 Paper published in the Structural Equation Modeling Journal: https://www.tandfonline.com/doi/full/10.1080/10705511.2021.1881786