In randomized trials, researchers often measure a continuous variable at baseline and follow-up. Baseline measurements are common in trials of chronic conditions. Statistical comparisons can be made in several ways. Comparing follow-up scores or change scores (baseline to follow-up) can yield different results. If baseline scores are similar, both methods may yield similar treatment effects. However, the significance of the treatment effect may depend on the correlation between baseline and follow-up scores. A low correlation may make change scores less significant, while a high correlation may make follow-up scores less significant. It is incorrect to choose the analysis that gives a more significant result. The method should be specified in the trial protocol. Change scores can account for baseline imbalances, but they do not control for them due to regression to the mean. A better approach is analysis of covariance (ANCOVA), which is a regression method. ANCOVA adjusts follow-up scores for baseline scores and is unaffected by baseline differences. It provides a more accurate estimate of the treatment effect, even with baseline imbalance. In a study on acupuncture for shoulder pain, ANCOVA showed a greater treatment effect than change scores. ANCOVA is preferred as it has greater statistical power. However, when the correlation between baseline and follow-up scores is high, the efficiency gains of ANCOVA are low. In stable conditions, change scores may be a reasonable alternative. ANCOVA depends on assumptions that need to be tested, such as data transformation. It can include additional prognostic variables. The article also includes a case of a non-verbal patient who gave informed consent through non-verbal cues, highlighting the importance of understanding non-verbal messages in informed consent.In randomized trials, researchers often measure a continuous variable at baseline and follow-up. Baseline measurements are common in trials of chronic conditions. Statistical comparisons can be made in several ways. Comparing follow-up scores or change scores (baseline to follow-up) can yield different results. If baseline scores are similar, both methods may yield similar treatment effects. However, the significance of the treatment effect may depend on the correlation between baseline and follow-up scores. A low correlation may make change scores less significant, while a high correlation may make follow-up scores less significant. It is incorrect to choose the analysis that gives a more significant result. The method should be specified in the trial protocol. Change scores can account for baseline imbalances, but they do not control for them due to regression to the mean. A better approach is analysis of covariance (ANCOVA), which is a regression method. ANCOVA adjusts follow-up scores for baseline scores and is unaffected by baseline differences. It provides a more accurate estimate of the treatment effect, even with baseline imbalance. In a study on acupuncture for shoulder pain, ANCOVA showed a greater treatment effect than change scores. ANCOVA is preferred as it has greater statistical power. However, when the correlation between baseline and follow-up scores is high, the efficiency gains of ANCOVA are low. In stable conditions, change scores may be a reasonable alternative. ANCOVA depends on assumptions that need to be tested, such as data transformation. It can include additional prognostic variables. The article also includes a case of a non-verbal patient who gave informed consent through non-verbal cues, highlighting the importance of understanding non-verbal messages in informed consent.