Manuals/calci/KURT

KURT(n1,n2,…)

• $n1$,$n2$ are values to calculate kurtosis.

Description

• This function gives the value of kurtosis of a given set.
• Kurtosis is the peakedness or flatness of the graph of a frequency distribution especially with respect to the concentration of values near the mean as compared with the normal distribution.
• A normal distribution has a kurtosis of 3.
• Distributions having higher kurtosis have flatter tails or more extreme values that phenomenon called 'leptokurtosis'also it is the positive excess kurtosis , and those with lower kurtosis have fatter middles or fewer extreme value that phenomenon called 'platykurtosis' also it is the negative excess kurtosis.
• Example for positive kurtosis(leptokurtosis) is Exponential distribution,possion distribution, Laplace distribution.
• Example for negative kurtosis(platykurtosis) is Bernoulli distribution, Uniform distribution.
• Kurtosis has no units.
• Kurtosis is defined by:
• kurtosis={n(n+1)/(n-1)(n-2)(n-3)*summation[(xi-x(bar)/s]^4}-3(n-1)^2/(n-2)(n-3), wher s is the sample standard deviation.x(bar) is the arithmetic mean.
• In this function argumentsmay be any type like numbers,names,arrays or references that contain numbers.
• We can give logical values and text references also directly.
• Suppose the referred argument contains any null cells, logical values like that values are not considered.
• This function will return the result as error when

1. Any one of the argument is nonnumeric.
2. suppose the number of data points are less than four or the standard deviation of the sampleis zero
3. The referred arguments could not convert

in to numbers.

Examples

1.DATA 14 11 23 54 38 KURT(C1:C5)=-0.8704870492 2. DATA={6,7,8,9,10} KURT(A1:A5)=-1.199999999 3.DATA={1898,1987,1786,1947} KURT(B1:B4)=0.870901113729 4.DATA={26,16,12} KURT(D1:D3)=NAN

See Also

• SKEW
• STDEV
• STDEVP

References

Correlation