Note:
|
Variables |
Descriptions |
|
Exposed |
Exposed group |
|
Non-exposed |
Non-exposed group |
|
Disease |
Number of people having disease |
|
No disease |
Number of people not having disease |
Help Aids Top
Description:
Relative Risk is the ratio of incidence of disease in Exposed group to that in Non-exposed group from a cohort/prospective study.
If Relative Risk is larger than 1, it is a positive association; exposure may be a positive risk factor.
If Relative Risk is smaller than 1, it is a negative association; exposure may be a protective factor.
If Relative Risk is equal to 1, there are no association; the exposure appears to have no effect on risk. Attributable Risk is the amount of disease incidence which can be attributed to an exposure in a prospective study. Population Attributable Risk is the reduction in incidence if the whole population were unexposed, comparing with actual exposure pattern. Application: Relative Risk compares the risk of having a disease for not receiving a medical treatment against people receiving a treatment. It can also compare the risk of having side effect in drug treatment against the people not receiving the treatment. Attributable Risk and Population Attributable Risk tell the amount of risk prevented if we
do not have certain exposure. Interpretation: P-value<0.05. We reject the null hypothesis and conclude that the observed relative risk is statistically significantly different from 1.0 . P-value>0.05. We FAILED TO reject the null hypothesis and conclude that the observed relative risk is NOT statistically significantly different from 1.0. 95% C.I. excludes 1.0. We are 95% certain that the true RR is not 1.0 and we concluded that the observed RR is statistically significantly different from 1.0 at the 0.05 level. 95% C.I. includes 1.0 (null). We are not certain that the true RR is different from 1.0 and we concluded that the observed RR is NOT statistically significantly different from 1.0 at the 0.05 level. Procedure: a)
Value of Disease and No Disease
in the Exposed and Non-exposed group b) Value of 1-£\, the two-sided confidence level a)
The Relative Risk and the corresponding 100(1-£\)% confidence interval b) The Attributable Risk and the corresponding 100(1-£\)% confidence interval Formula: Variables: Disease No disease Totals Exposed a b n1=a+b Non-exposed c d n2=c+d Totals m1=a+c m2=b+d N=n1+n2 For Relative Risk, Define: The 100(1-£\)% confidence interval is defined
as: For Attributable Risk,
Define:
The
100(1-£\)% confidence interval is defined as: For Attributable Risk Percent, The 100(1-£\)% confidence interval is defined as: For Population Attributable Risk, For Population Attributable Risk Percent, Notation: 100(1-£\)% confidence interval: We are 100(1-£\)% sure the true value of the parameter is included in the confidence interval Suppose the disease is breast cancer (BC) and a woman is considered to be exposed if she gave birth at or after the age of 25. Breast Cancer No Breast Cancer Totals Exposed a=19 b=139 n1=158 Non-exposed c=53 d=789 n2=842 Totals n1=72 m2=928 N=1000 Then Relative Risk is 1.91044 and the 95% C.I. ((1-£\) =0.95) is (1.16365, 3.13649). The Attributable Risk is 0.05731 and the 95% C.I. is (0.01338, 0.10123). The Attributable Risk Percent is 47.65596% and the 95% C.I. is (11.12938%, 84.18254%). The Population Attributable Risk is 0.00905, the Population Exposure is 15.8% and Population Attributable Risk Percent is 12.57588%.
: The z-value for standard normal distribution with left-tail probability