Documentation

This is machine translation

Translated by Microsoft
Mouse over text to see original. Click the button below to return to the English verison of the page.

Compute Measures of Shape

The measures of shape indicate the symmetry and flatness of the distribution of a data sample. MuPAD® provides the following functions for calculating the measures of shape:

  • The stats::moment function that calculates the k-th moment

    of the data sample x1, x2, ..., xn centered around X.

  • The stats::obliquity function that calculates the obliquity (skewness)

    ,

    where is the arithmetic average (mean) of the data sample x1, x2, ..., xn.

  • The stats::kurtosis function that calculates the kurtosis (excess)

    ,

    where is the arithmetic average (mean) of the data sample x1, x2, ..., xn.

The stats::moment function enables you to compute the kth moment of a data sample centered around an arbitrary value X. One of the popular measures in descriptive statistics is a central moment. The kth central moment of a data sample is the kth moment centered around the arithmetic average (mean) of that data sample. The following statements are valid for any data sample:

  • The zero central moment is always 1.

  • The first central moment is always 0.

  • The second central moment is equal to the variance computed by using a divisor n, rather than n - 1 (available via the Population option of stats::variance).

For example, create the lists L and S as follows:

L := [1, 1, 1, 1, 1, 1, 1, 1, 100.0]:
S := [100, 100, 100, 100, 100, 100, 100, 100, 1.0]:

Calculate the arithmetic average of each list by using the stats::mean function:

meanL := stats::mean(L);
meanS := stats::mean(S)

Calculate the first four central moments of the list L:

stats::moment(0, meanL, L),
stats::moment(1, meanL, L),
stats::moment(2, meanL, L),
stats::moment(3, meanL, L)

The zero and first central moments are the same for any data sample. The second central moment is the variance computed with the divisor n:

stats::variance(L, Population)

Now, calculate the first four central moments of the list S:

stats::moment(0, meanS, S),
stats::moment(1, meanS, S),
stats::moment(2, meanS, S),
stats::moment(3, meanS, S)

Again, the zero central moment is 1, the first central moment is 0, and the second central moment is the variance computed with the divisor n:

stats::variance(S, Population)

The obliquity (skewness) is a measure of the symmetry of a distribution. If the distribution is close to symmetrical around its mean, the value of obliquity is close to zero. Positive values of obliquity indicate that the distribution function has a longer tail to the right of the mean. Negative values indicate that the distribution function has a longer tail to the left of the mean. For example, calculate the obliquity of the lists L and S:

stats::obliquity(L);
stats::obliquity(S)

The kurtosis measures the flatness of a distribution. For normally distributed data, the kurtosis is zero. Negative kurtosis indicates that the distribution function has a flatter top than the normal distribution. Positive kurtosis indicates that the peak of the distribution function is sharper than it is for the normal distribution:

stats::kurtosis(-2, -1, -0.5, 0, 0.5, 1, 2),
stats::kurtosis(-1, 0.5, 0, 0, 0, 0, 0.5, 1)

Was this topic helpful?