A prospective cohort study was conducted to assess the role of daily alcohol consumption in the occurrence of breast carcinoma. The investigators reported a 5-year relative risk of 1.4 for people who consume alcohol daily compared to those who do not. The 95% confidence interval was 1.02-1.85. Which of the following p-values is most consistent with the results described above?
Relative risk (RR) is used in cohort studies to determine how strongly a risk factor (ie, exposure) is associated with an outcome. RR is the risk of an outcome (eg, breast cancer) in the exposed group (eg, individuals who consume alcohol daily) divided by the risk of that outcome in the unexposed group (eg, individuals who do not consume alcohol daily). If the RR = 1.0 (null value), then there is no association between the exposure and the disease. An RR >1.0 indicates that the exposure is associated with increased risk of disease. An RR <1.0 means that the exposure is associated with decreased risk of disease.
The RR by itself does not account for the possibility that chance alone is responsible for the results. The 95% confidence interval (CI) and p-value are 2 measures of statistical significance that can help strengthen the findings of a study using RR. For a result to be considered statistically significant, its corresponding CI must NOT contain the null value. When the 95% CI does not include the null value, this gives a corresponding p-value <0.05 and the association between exposure and outcome is considered statistically significant. A p-value <0.05 reflects that there is a very low probability that the result was due to chance alone; formally, the p-value is the probability of observing a given (or more extreme) result due to chance alone assuming that the null hypothesis is true.
In this example, the RR is 1.4 with a 95% CI of 1.02-1.85. It can be concluded that daily alcohol consumption is associated with an increased risk of breast carcinoma (RR >1) and that the findings are statistically significant (95% CI does not include the null value of 1.0). Therefore, the expected p-value would be <0.05.
(Choices B, C, D, and E) These options contain p-values >0.05, so the results would not be statistically significant. Note the relationship between CI and p-value: a statistically significant 95% CI corresponds to a p-value <0.05; a statistically significant 99% CI (would also not include the null value and likely be wider than a 95% CI) corresponds to a p-value <0.01.
Educational objective:
A result is considered statistically significant if the 95% confidence interval does not cross the null value, which corresponds to a p-value <0.05.