MENSTRUAL PHASE AND BREAST-CANCER SURGERY - INFLUENCE ON CLINICAL OUTCOME OR PITFALL OF STATISTICAL-ANALYSIS

The influence of menstrual status at the time of surgery on the progno sis of women suffering from breast cancer is still discussed controver sially. In our patient collective, including 149 patients, we obtained statistically significant results for six different time intervals, i ndicating that patients who underwent surgery between 11 and 22 days a fter the last menstrual period (LMP) have a poorer outcome. Focusing o n the effect of statistical data evaluation strategy we designed a sim ulation study to evaluate the amount of type I error (error of a false positive test result) in a multiple testing situation involving a cyc lical covariate. Accordingly, we corrected the minimum P-values for th e occurring type I error rates. After that correction all six previous ly significant P-values failed to achieve statistical significance. Th e impact of different statistical data evaluation strategies in a mult iple testing situation is discussed.