Noumbissi's method improves on Whipple's method by extending its basic principle to all ten digits. It compares single terminal digit numerators to denominators consisting in 5-year age groups centered on the terminal digit of age in question. For example, 9, 19, 29, etc are all of digit 9.

check_heaping_noumbissi(
  Value,
  Age,
  ageMin = 20 + digit,
  ageMax = ageMin + 30,
  digit = 0
)

Arguments

Value

numeric. A vector of demographic counts by single age.

Age

numeric. A vector of ages corresponding to the lower integer bound of the counts.

ageMin

lower age used for estimation (inclusive). Default 20

ageMax

upper bound used for estimation (inclusive). Default 50

digit

integer. Any digit between 0 and 9. Default c(0,5). Otherwise it needs to be a single digit.

Value

The value of the index.

Details

ageMin and ageMax are applied to numerator ages, not denominators. Denominators are always 5-year age groups centered on the digit in question, and these therefore stretch into ages a bit higher or lower than the numerator ages. ageMax is an inclusive upper bound, treated as interval. If you want ages 20 to 64, then give ageMin = 20 and ageMax = 64, not 65.

References

Noumbissi A (1992). “L'indice de Whipple modifié: une application aux données du Cameroun, de la Suède et de la Belgique.” Population (french edition), 1038--1041. Spoorenberg T, Dutreuilh C (2007). “Quality of age reporting: extension and application of the modified Whipple's index.” Population, 62(4), 729--741.

Examples

Age <- 0:99 check_heaping_noumbissi(pop1m_pasex, Age, digit = 0) # 2.32
#> [1] 2.239127
check_heaping_noumbissi(pop1m_pasex, Age, digit = 1) # 0.55
#> [1] 0.5679979
check_heaping_noumbissi(pop1m_pasex, Age, digit = 2) # 0.73
#> [1] 0.7653283
check_heaping_noumbissi(pop1m_pasex, Age, digit = 3) # 0.76
#> [1] 0.7533247
check_heaping_noumbissi(pop1m_pasex, Age, digit = 4) # 0.49
#> [1] 0.5206658
check_heaping_noumbissi(pop1m_pasex, Age, digit = 5) # 2.08
#> [1] 2.040742
check_heaping_noumbissi(pop1m_pasex, Age, digit = 6) # 0.66
#> [1] 0.6597471
check_heaping_noumbissi(pop1m_pasex, Age, digit = 7) # 1.08 7 looks good!
#> [1] 1.077396
check_heaping_noumbissi(pop1m_pasex, Age, digit = 8) # 0.57
#> [1] 0.5700284
check_heaping_noumbissi(pop1m_pasex, Age, digit = 9) # 0.59
#> [1] 0.5895384