Purpose: This study was designed to evaluate the clinical utility of the Four square step test (FSST) for predicting falls in stroke patients, to compare the ability of the FSST test to discriminate between subgroups of fallers, and to determine if the test has any predictive value in identifying stroke patients who will fall. Methods: Stroke patients (N=37) who could walk at least 50 m with minimal assistance were recruited consecutively when attending a physical therapy session during their rehabilitation. Dynamic standing balance was measured using the FSST. The main outcome measures were FSST time and fall number. Numbers of falls were compared with FSST scores. Differences between the groups in FSST scores were examined using a t-test and 1-way analysis of variance. Post hoc analysis using the Tukey B procedure was used to identify specific group differences. Alpha was set at 0.05. Results: A total of 15 participants (40.5%) reported falls 6 had recurrent falls (2 falls) and 9 fell once. The mean FSST time differed significantly between groups with zero and multiple falls. A cutoff score of greater than 17 seconds on the FSST was associated with a sensitivity of 83% and a specificity of 84% for the identification of subjects with multiple risk factors for falls. Conclusion: The FSST is a feasible and valid clinical test of dynamic standing balance and can predict falls in post-stroke patients.