Question

In a large hospital-based case-control study of smoking and lung cancer, controls consisted of patients with noncancerous chronic pulmonary diseases, such as chronic bronchitis and emphysema. The investigators were surprised to find that the association between smoking and lung cancer was relatively weak. What was the odds ratio (OR) for the association between smoking and lung cancer? Was it statistically significant?

1) OR=1.4, p<0.05
2) OR=1.4, p>0.05
3) OR=1.4, p=0.05
4) OR=1.4, p<0.01

Answer 1

The odds ratio of 1.4 with a p-value <0.05 indicates a weak but statistically significant association between smoking and lung cancer. The choice of controls in the study may have influenced the strength of the observed association.

Step-by-step explanation:

The odds ratio (OR) for the association between smoking and lung cancer in the hospital-based case-control study described would be OR=1.4. However, to say whether this association was statistically significant, you would need to look at the p-value. If the p-value is <0.05, it suggests that the association observed is unlikely to have occurred by chance alone, and thus is statistically significant. In this scenario, if we have an OR of 1.4 with a p-value <0.05 (option 1), it indicates a relatively weak, but still statistically significant association between smoking and lung cancer.

However, the selection of patients with noncancerous chronic pulmonary diseases as controls may have influenced this result, as such patients might also have been smokers, thus diminishing the apparent strength of the association observed in the study. Such methodological issues may lead to underestimation of the true relation.