A case control study of women with carcinoma in situ (CINIII) was undertaken comparing Papanicolaou smears for which false negative reports had been issued with slides for which true positive reports had been made. The number of abnormal cells was the strongest differentiating factor. Where there were less than 50 abnormal cells on the slide, the odds of a false negative report being issued was 23.7 times greater (95% confidence interval 3.7-150) than when there were 200 or more abnormal cells. In false negative slides, the abnormal cells were likely to be not represented throughout the slide, present only as single cells rather than as groups, small in size and with finely granular normochromatic nuclei. We conclude that there are intrinsic differences between true positive and false negative slides. Given these characteristics, rapid rescreening of slides that are considered negative may not be an effective method of reducing the false negative rate.