The aim of this retrospective study was to assess systematically the case distribution among three types of mini-implants and to evaluate the clinical factors that influence the failure rates of mini-implants used as an orthodontic anchorage. Data for 359 mini-implants (miniplates, miniscrews, and microscrews) in 129 patients were collected. The factors related to mini-implant failure were evaluated using univariate analysis and multivariate stepwise logistic regression analysis. Among these three different types of skeletal anchorage, there was a significant difference between the failure rates of these mini-implants, with the miniscrews and microscrews showing much higher failure rates. There were no significant differences in failure rates among the mini-implants for the following variables: gender, type of malocclusion, local or full-arch treatment, whether on the buccal or lingual side, length of the screw, loading pattern, or the duration of the healing phase. Greater risks for failure were found in younger patients, when an implant was placed for retraction/protraction, when it was placed on the mandibular arch, when it was placed anterior to the second premolars, or when using the miniscrew/microscrew systems. After adjusting for potential confounding effects, only three factors (type of mini-implant, placement on the mandibular arch, and age) were found to be statistically significant in predicting mini-implant failures (P<0.05) with an R2 value of 85.2%. Mini-implants placed in younger patients or placed on the mandibular arch are at a greater risk of failing. The miniplate system has greater stability compared with miniscrews or microscrews. However, it requires flap surgery for insertion and removal, which usually causes swelling and discomfort. Therefore, selection of the proper type of skeletal anchorage should be based on the specific treatment needs of each individual patient.