The goal of this meta-analysis is to provide evidence based information about proper dosing for buprenorphine maintenance treatment to improve treatment outcome. To be selected for the review and inclusion in the meta-analysis, articles had to be randomized, controlled, or double-blind clinical trials, with buprenorphine as the study drug; the length of buprenorphine maintenance treatment had to be 3 weeks or longer; doses of buprenorphine had to be clearly stated; outcome measures had to include retention rates in buprenorphine treatment; outcome measures had to include illicit opioid use based on analytical determination of drugs of abuse in urine samples as outcome variables; and outcome measures had to include illicit cocaine use based on analytical determination of drugs of abuse in urine samples as outcome variables. Twenty-nine articles were excluded because they did not meet the inclusion criteria. The authors present the results of 21 articles that met inclusion criteria. The higher buprenorphine dose (16-32 mg per day) predicted better retention in treatment compared with the lower dose (less than 16 mg per day) (P = .009, R(2) adjusted = 0.40), and the positive urine drug screens for opiates predicted dropping out of treatment (P = .019, R(2) Adjusted = 0.40). Retention in treatment predicted less illicit opioid use (P = .033, R(2) Adjusted = 0.36), and the positive urine drug screens for cocaine predicted more illicit opioid use (P = .021, R(2) Adjusted = 0.36). Strong evidence exists based on 21 randomized clinical trials that the higher buprenorphine dose may improve retention in buprenorphine maintenance treatment.