Objective To investigate the association between obesity and miscarriage. Design Meta-analysis. Setting The Academic Unit of Reproductive and Developmental Medicine, The University of Sheffield, United Kingdom. Patient(s) Obese and overweight patients who had miscarriage after spontaneous or assisted conception, compared with patients with a normal body mass index. Intervention(s) A systematic review was conducted for all relevant articles in MEDLINE from 1964 to September 2006 and in EMBASE from 1974 to September 2006, using a combination of the following search terms: obesity/obes ∗/obes$/BMI, miscarriage/abortion/pregnancy, IVF, clomifene/clomiphene, gonadotrophins/gonadotrop ∗/gonadotrop$. Main Outcome Measure(s) Pregnancy loss at <20 weeks of gestation. Result(s) Sixteen studies were included in the meta-analysis. Patients with a body mass index of ≥25 kg/m 2 had significantly higher odds of miscarriage, regardless of the method of conception (odds ratio, 1.67; 95% confidence interval, 1.25–2.25). Subgroup analysis from a limited number of studies suggested that this group of women may also have significantly higher odds of miscarriage after oocyte donation (odds ratio, 1.52; 95% confidence interval, 1.10–2.09) and ovulation induction (odds ratio, 5.11; 95% confidence interval, 1.76–14.83). There was no evidence for increased odds of miscarriage after IVF–intracytoplasmic sperm injection. Conclusion(s) There is evidence that obesity may increase the general risk of miscarriage. However, there is insufficient evidence to describe the effect of obesity on miscarriage in specific groups such as those conceiving after assisted conception.