Flexible capacitive sensors are essential for applications in wearable electronics, soft robotics, and biomedical devices due to their adaptability and sensitivity. This study focuses on optimizing the performance of a parallel plate capacitive sensor through electrostatic analysis and design of experiments (DOE). The sensor, composed of a conductive layer and an Ecoflex 30 dielectric, is modeled using Ansys Maxwell to evaluate the influence of key design parameters such as dielectric distance, sensor thickness, and sensor radius on capacitance. A 3-level full factorial DOE approach is employed to systematically analyze the interactions between these parameters and their associated uncertainties, such as variations in permittivity (±5%) and applied voltage (±5%). Statistical analysis, including ANOVA, reveals that dielectric distance is the most significant factor affecting capacitance, with an F-value of 270.06 and p < 0.0001. The half-normal plot further confirms the significance of these factors, with dielectric distance and sensor radius deviating significantly from the reference line. The developed functional equation allows future designers to predict capacitance without extensive simulations, significantly reducing computational effort. The predicted vs. actual graph is plotted to illustrate the distribution of data points, demonstrating the model’s accuracy with an R2 value of 0.9312. This work high-lights the advantages of DOE in optimizing sensor design, enabling the selection of input parameters for targeted performance in flexible and printable sensor systems. The findings provide a framework for designing high-sensitivity capacitive sensors, advancing their application in flexible electronics and soft robotics.