From 1970 to 1980 cemented metal-on-plastic total hip replacement was performed on 799 hips with primary osteoarthritis using one surgical technique. At the 10- to 20-year follow-up there had been 97 revisions for mechanical loosening. Univariate survivorship analysis showed that an increased risk of revision was associated with male gender, young age at primary THR, the Brunswik and Lubinus snap-fit prostheses with large femoral heads (as compared with the Charnley prosthesis), and varying experience of the surgeon. Multivariate statistical analysis showed a three-fold increased risk of revision for men (p < 0.0001), an increase in relative risk of 1.8 per 10 years younger at surgery (p < 0.0001), a fivefold increase in risk for the Brunswik prosthesis (p < 0.0001) and a twofold increase for the Lubinus prosthesis (p = 0.0067). Inexperience of the surgeon, however, was not validated as a risk factor. The study shows that the true risk factors for revision can be identified accurately by combining univariate survivorship and multivariate statistical analyses.