Problem 4.c
#Problem 4
## Problem 4.c
x.10 <- (1:10)
unstableGeoMean = function(dataA){prod(dataA)^(1/length(dataA))}
unstableGeoMean(x.10)
## [1] 4.528729
stableGeoMean = function(dataB){exp(mean(log(dataB)))}
stableGeoMean(x.10)
## [1] 4.528729
Problem 4.d
#Problem 4
## Problem 4.d
x.1000 <- (1:1000)
unstableGeoMean = function(dataA){prod(dataA)^(1/length(dataA))}
unstableGeoMean(x.1000)
## [1] Inf
stableGeoMean = function(dataB){exp(mean(log(dataB)))}
stableGeoMean(x.1000)
## [1] 369.4917
When there are a small set of numbers (for example, from 1 to 10),
it is generally sufficient to compute the direct product and nth root
for the geometric mean. However, as the size of the numbers increases,
the direct multiplication could lead to numerical instability with the
problem of product becoming too large or too small. The result of
‘infinite’ in Problem 4.d could be the example.
The logarithmic approach changes the multiplication into addition,
which can mitigate the numerical stability issues associated with very
large or very small numbers. It tends to provide more accurate results,
especially with a larger set of numbers. Thus, in Problem 4.d, the
result could still be driven with this approach even though there are
1000 numbers.