<bold>Introduction: </bold>The purpose of this study was to assess the effect of dose escalation of stereotactic ablative radiotherapy (SABR) by investigating the long-term clinical outcomes of SABR for stage I non-small-cell lung cancer (NSCLC).<bold>Methods: </bold>A retrospective analysis was performed on a total of 169 patients with 178 lesions of stage I NSCLC treated with SABR at a single institution from June 2000 to May 2015. The standard dose scheme for SABR was 48 Gy in 4 fractions during the early period of the analysis, but it was escalated to 60 Gy in 4 fractions from June 2009. All failures were recorded over the follow-up period.<bold>Results: </bold>Median follow-up time was 32 months. The 5-year overall survival rate was 46.7%, and the actuarial local control rate was 79.3%. Tumor size was an independent prognostic factor for survival. No relapse occurred in tumors ≤ 2 cm irrespective of SABR dose. Escalated doses of approximately 60 Gy in 4 fractions (biologically effective dose [BED] = 150 Gy10) achieved higher local control compared with 48 Gy in 4 fractions (BED = 106 Gy10) (76.2% vs. 60.6%) at 5-year follow-up (P = .022) in tumors > 2 cm. There were no differences in treatment-related toxicities between the dose groups. Major failures consisted of distant metastasis to another lung parenchyma.<bold>Conclusion: </bold>SABR provides satisfactory long-term local control and high overall survival in medically inoperable stage I NSCLC. Tumors ≤ 2 cm had no local recurrence regardless of dose; whereas for tumors > 2 cm, an escalated BED of approximately 150 Gy10 provided significantly higher local tumor control.