An area of statistics focusing on identifying causal effects, especially in contexts where identification and estimation is not possible with traditional methods, such as in an observational studies. It specializes in adjusting for confounders, selection bias, and measurement error which complicate causal interpretations in studies of non-randomized interventions and exposures. In our current work, we use this approach to account for the nonrandomized treatment assignment in the presence of interference with complex dependencies and develop more precise estimates of effects.