Although many cross-sectional social surveys have included questions about female genital cutting status and correlated personal characteristics, no longitudinal studies have been launched that permit investigation of response biases associated with such surveys. This study draws upon the findings of a longitudinal study of women aged 15 to 49 in rural northern Ghana. The self-reported circumcision status of women interviewed in 1995 was compared with the status they reported when they were interviewed again in 2000 after the government began enforcing a law banning the practice and public information campaigns against it were launched. In all, 13 percent of respondents who reported in 1995 that they had been circumcised stated that they had not been circumcised in the 2000 reinterview; this inconsistency reached 50 percent for the youngest age group. Analysis shows that women who said they had not been circumcised are significantly younger, more likely to be educated, and less likely to practice traditional religion than are women who reported that they were circumcised. Factors that may explain these correlates of denial are discussed, and implications for research are reviewed.