Previous osteoporotic fracture

Never 165

Ever 82

709 165

CI, confidence interval.

Melhus et al., 1998.

n inactivity, and use of hormone replacement therapy were verified, providing a general indication that the selection of subjects was successful and thereby increasing confidence that the patterns of association for uncertain risk factors is more likely to be valid as well.

Conventional wisdom can be incorrect, of course, with supposedly known associations subject to error in previous studies. Furthermore, the prevalence of important cofactors may vary across populations, so that an exposure that operates as a risk factor in one population may truly not operate in that manner in another. As discussed above, the potential for selection bias will vary across risk factors, with a given study able to generate valid measures of association for one exposure yet incapable of doing so for others. Even if valid for confirming known associations, the study may not be valid for addressing the association of primary interest. Finally, there is the ever-present random error to consider, a par ticular concern in attempting to corroborate well-accepted associations that are modest in magnitude. Failure to confirm an association between a history of heavy cigarette smoking and lung cancer would raise serious doubts about the validity of other measures of association with lung cancer identified in a case-control study, whereas many of the established risk factors for diseases such as breast cancer are so modest in magnitude that random error alone could well yield a spurious absence of measurable association. For example, although a positive association between alcohol intake and breast cancer is generally accepted (Longnecker, 1994), the magnitude is modest. Thus, studies that fail to find it, a non-trivial proportion of all studies (Singletary & Gapstur, 2001), are not by any means rendered invalid as a result. Like the other strategies, the examination of known and strongly suspected associations helps to direct the effort to scrutinize potential selection bias without providing conclusions in isolation from other considerations.

10 Ways To Fight Off Cancer

10 Ways To Fight Off Cancer

Learning About 10 Ways Fight Off Cancer Can Have Amazing Benefits For Your Life The Best Tips On How To Keep This Killer At Bay Discovering that you or a loved one has cancer can be utterly terrifying. All the same, once you comprehend the causes of cancer and learn how to reverse those causes, you or your loved one may have more than a fighting chance of beating out cancer.

Get My Free Ebook


Post a comment