The function calculates the original and modified Whipple index to evaluate age heaping.
numeric vector holding the age of persons
“standard” or “modified” Whipple index.
numeric vector holding the weights of each person
The original Whipple's index is obtained by summing the number of persons in the age range between 23 and 62, and calculating the ratio of reported ages ending in 0 or 5 to one-fifth of the total sample. A linear decrease in the number of persons of each age within the age range is assumed. Therefore, low ages (0-22 years) and high ages (63 years and above) are excluded from analysis since this assumption is not plausible.
When the digits 0 and 5 are not reported in the data, the original Whipple index varies between 0 and 100, 100 if no preference for 0 or 5 is within the data. When only the digits 0 and 5 are reported in the data it reaches a to a maximum of 500.
For the modified Whipple index, age heaping is calculated for all ten digits (0-9). For each digit, the degree of preference or avoidance can be determined for certain ranges of ages, and the modified Whipple index then is given by the absolute sum of these (indices - 1). The index is scaled between 0 and 1, therefore it is 1 if all age values end with the same digit and 0 it is distributed perfectly equally.
The original or modified Whipple index.
Matthias Templ, Alexander Kowarik
Henry S. Shryock and Jacob S. Siegel, Methods and Materials of Demography (New York: Academic Press, 1976)
1 2 3 4 5 6 7 8 9 10 11 12 13 14
#Equally distributed age <- sample(1:100, 5000, replace=TRUE) whipple(age) whipple(age,method="modified") # Only 5 and 10 age5 <- sample(seq(0,100,by=5), 5000, replace=TRUE) whipple(age5) whipple(age5,method="modified") #Only 10 age10 <- sample(seq(0,100,by=10), 5000, replace=TRUE) whipple(age10) whipple(age10,method="modified")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.