RT Journal
A1 Slattery ML
T1 EXposure to cigarette smoke and cervical cancer-reply
JF JAMA
JO JAMA
YR 1989
FD July 28
VO 262
IS 4
SP 499
OP 499
DO 10.1001/jama.1989.03430040069019
UL http://dx.doi.org/10.1001/jama.1989.03430040069019
AB In Reply. — 
    Control patients were matched to case patients by age in our study, while sexual history, education, and church attendance (to help control for sexual activity) were controlled in the smoking analyses so that they also could be examined as independent risk factors in other analyses.1 Because of the risk of cervical cancer associated with these variables,1 major differences in their distribution between case and control subjects were noted. These variables, although associated, did not present, in the analysis, a problem of multicolinearity. While logistic regression models have the capability to control for confounding, they can only control to the extent that the data are accurate. Thus, biased risk estimates could result if important confounding variables were reported inaccurately, although they were controlled in the analyses. While there is the possibility that sexual history is reported inaccurately, we do not believe that case patients reported differently