Rigor in Quality Improvement Studies and the Role of Time-Series Methodologies

To the Editor In response to the Editorial by Grady and colleagues about quality improvement for quality improvement studies¹ that was published in a recent issue of JAMA Internal Medicine, we disagree that rigor always requires concurrent controls and randomization. Time series with multiple data points provide comparable evaluative rigor to controlled, nonrandomized trials. When an intervention needs refinement, as is often the case in quality improvement, they often represent a more efficient evaluative strategy. The SQUIRE guidelines,² which Grady and colleagues¹ recommend to encourage improved reporting, explicitly list analyses that include the effects of time as a variable as appropriate.