Soybean yield response variability to foliar fungicide applications was evaluated in on-farm replicated strip trials (OFTs) and small-plot trials (SPTs) from 2008 through 2015 in Iowa. A total of 230 OFTs and 49 SPTs were compared for yield response to pyraclostrobin, pyraclostrobin + fluxapyroxad, or trifloxystrobin + prothioconazole fungicides. OFTs (18 to 55 m wide and 200 to 800 m long strips) were harvested with farmers' combines equipped with yield monitors and GPS, while SPTs (3.0 to 4.6 m wide and 10.7 to 15.3 m long plots) were harvested by small research plot combines. Variance component and power analyses were conducted with a subset of data consisting of 12 OFTs and SPTs, each with pyraclostrobin and evaluated in 2008 and 2009. While average yield responses were similar, the residual random yield variation was smaller in OFTs than SPTs. Power analysis showed that SPTs need more replications than OFTs to detect the same overall treatment differences. To detect a yield response of 134 kg/ha, it would require at least three treatment replications with 12 locations in OFTs and seven replications with 12 locations in SPTs. Researchers need to acknowledge the differences in statistical power of detecting yield responses to foliar fungicide on soybean in different types of field experiments, especially with smaller plot sizes in situations with less foliar disease.