This paper serves as a practical guide to mediation design and analysis by evaluating mediation models' ability to detect a significant mediation effect using limited data. The cross-sectional mediation model, which has been shown to be biased when the mediation is happening over time (Maxwell & Cole, 2007; Maxwell, Cole, & Mitchell, 2011) is compared to longitudinal models: sequential, dynamic, and cross-lagged panel. These longitudinal mediation models take this time effect into account but bring many problems of their own, such as choosing measurement intervals and number of measurement occasions. Furthermore, researchers with limited resources often cannot collect enough data to fit an appropriate longitudinal mediation model. These issues were addressed using simulations comparing these four mediation models each using the same amount of data but with differing numbers of people and time points, against data with varying characteristics that may be incorrectly specified in the model. Models were evaluated using power and type I error rates in detecting a significant indirect path, from which cross-sectional and sequential mediation analysis were found to have the best performance. Finally, each of these models were demonstrated in an empirical analysis.