Example 1 The association between number of children (x) and the number of sick days during a year (y) is examined. The number of children ranges between 0 and 10, whereas the number of sick days in a year ranges between 0 and 365. The IRR we get is 1.07, suggesting that the higher the number of children, the higher the rate of sick days.
Example 2 In this example, we use a sample of soccer player to analyse the association between body mass index (x) and the number of goals scored during a soccer season (y). Body mass index ranges between 15 and 35, whereas the number of goals ranges from 0 to 60. We find that the IRR is 0.90. In other words, the higher the body mass index, the lower the rate of goals scored in a season.
Practical example
Dataset
StataData1.dta
Variable name
children
Variable label
Number of children (Age 40, Year 2010)
Value labels
N/A
Variable name
siblings
Variable label
Number of siblings (Age 15, Year 1985)
Value labels
N/A
sum children siblings if pop_poisson==1
poisson children siblings if pop_poisson==1, irr
When we look at the results for siblings, we see that the incidence rate ratio (IRR) is 1.01. Thus, for each additional sibling, the rate of children is 1.01 times higher. That is not much.
The association between siblings and children is not statistically significant, as reflected in the p-value (0.070) and the 95% confidence intervals (1.00-1.02).
Summary There is a positive association between number of siblings and number of children at age 40 (IRR=1.01). The association is however not statistically significant (95% CI=1.00-1.02).
