High doses of antipsychotic medications are sometimes prescribed in clinical practice, although the efficacy and safety of such treatment have not been established. The purpose of this study was to determine whether high-dose, long-term antipsychotic treatment prescribed on the basis of clinical judgment can be justified. Patients who were receiving high doses of haloperidol were screened, and those patients whose plasma levels were at least 15 ng/mL were randomly assigned to an experimental group (N = 11) or to a control group (N = 12). The experimental group underwent a dose reduction to achieve the target plasma level of 10 ng/mL. The reduction was gradual over a period of 12 weeks. The control group treatment was maintained at the original level. Both groups were then followed up for another 16 weeks, during which the plasma levels of haloperidol were kept constant. The study used double-blind procedures. Both groups showed an average slight symptom reduction. There was no significant difference in the severity of symptoms between the two groups at any time point. The dose reduction had no apparent adverse effects. Thus, the results of this study did not provide justification for high-dose, long-term antipsychotic treatment. However, these results must be interpreted with caution because the sample studied here was small and biased.