10, 2, 19, 24, 6, 23, 47, 24, 54, 77
These features are not present in the standard package of R, although they are easily available in some packets.
However, it is easy to calculate these values simply by remembering the mathematical formulas, and applying them in R.
$$H = \frac{n}{\frac{1}{x_1} + \frac{1}{x_2} + \cdots + \frac{1}{x_n}} = \frac{n}{\sum_{i=1}^n \frac{1}{x_i}}, \qquad x_i > 0 \text{ for all } i.$$
In R language:
a = c(10, 2, 19, 24, 6, 23, 47, 24, 54, 77)
1/mean(1/a) #compute the harmonic mean
[1] 10.01109
$$\overline{a}_{geom}=\bigg(\prod_{i=1}^n a_i \bigg)^{1/n} = \sqrt[n]{a_1 \cdot a_2 \cdots a_n}$$
In R language
a = c(10, 2, 19, 24, 6, 23, 47, 24, 54, 77)
n = length(a) #now n is equal to the number of elements in a
prod(a)^(1/n) #compute the geometric mean
[1] 18.92809
There are two packages that can help with this:
ReplyDeletePackage 'psych' ships geometric.mean() and harmonic.mean(). Both seem to be implemented as described above.
Package 'PerformanceAnalytics' ships mean.geometric() which allows to handle financial returns, including negative returns. It does so by using the following formula: exp(mean(log(1 + x))) - 1.
if we have a frequency then how we find it through this formula or something changes is needed on there.
ReplyDelete