OBJECTIVE Atypical antipsychotic medications are widely used to treat delusions, aggression, and agitation in people with Alzheimer disease (AD) and other dementia. Several clinical trials have not shown efficacy, and there have been concerns about adverse events. The objective of this study was to assess the evidence for efficacy and adverse events of atypicals for people with dementia. METHODS MEDLINE, the Cochrane Register of Controlled Trials, meetings, presentations, and information obtained from sponsors were used in this study. Published and unpublished randomized, placebo-controlled, double-blind, parallel-group trials in patients with AD or dementia of atypical antipsychotics marketed in the United States were studied. Clinical and trials characteristics, outcomes, and adverse events were extracted. Data were checked by a second reviewer. Fifteen trials including 16 contrasts of atypical antipsychotics with placebo met selection criteria: aripiprazole (k = 3), olanzapine (k = 5), quetiapine (k = 3), and risperidone (k = 5). A total of 3,353 patients were randomized to drug and 1,757 to placebo. Standard meta-analysis methods were used to summarize outcomes. RESULTS Quality of the reporting of trials varied. Efficacy on rating scales was observed by meta-analysis for aripiprazole and risperidone, but not for olanzapine. Response rates were frequently not reported. There were smaller effects for less severe dementia, outpatients, and patients selected for psychosis. Approximately one-third dropped out without overall differences between drug and placebo. Adverse events were mainly somnolence and urinary tract infection or incontinence across drugs, and extrapyramidal symptoms or abnormal gait with risperidone or olanzapine. Cognitive test scores worsened with drugs. There was no evidence for increased injury, falls, or syncope. There was a significant risk for cerebrovascular events, especially with risperidone; increased risk for death overall was reported elsewhere. CONCLUSIONS Small statistical effect sizes on symptom rating scales support the evidence for the efficacy of aripiprazole and risperidone. Incomplete reporting restricts estimates of response rates and clinical significance. Dropouts and adverse events further limit effectiveness. Atypicals should be considered within the context of medical need and the efficacy and safety of alternatives. Individual patient meta-analyses are needed to better assess clinical significance and effectiveness.