Most departures from normality display combinations of both skewness and kurtosis
different from a normal distribution.
Calculating Skewness and Kurtosis
There are many methods for calculating skewness and kurtosis indices. Not all
computer programs calculate Skewness and Kurtosis the same way. If you use a
computer program to obtain skewness and kurtosis indices be sure you know how it
calculates them!
There are measures of skewness such as Pearson's second coefficient of skewness,
which is simply three times the mean minus the median divided by the standard
deviation. There are also skewness indices which look at the quartiles, and many
others. The most important group of measures of skewness and kurtosis use the third
and fourth moments about the mean.
The moments about the mean are simply the sum of [each observed value minus the
mean] raised to some power and divided by the sample size. In algebraic form, the rth
moment about the mean is:
The expected value of this statistic will be zero for symmetrical distributions.
And similarly, the Moment Coefficient of Kurtosis, denoted by statisticians as g4, is
defined in dimensionless form as:
This expected value of this statistic will be zero for Normal distributions.
These are the Skewness and Kurtosis formulas that are used by MVPstats, and
programs such as SPSS, and Excel.
Critical Values
The critical value tables for Skewness and Kurtosis may be found on this Website. (See
Skewness Critical Values, and Kurtosis Critical Values.) These tables have been
generated to match the formulas above. Note that other tables exist which do not match
these formulas, and using them would be misleading.
Using the Critical Value Tables and p-values
The tests for skewness and kurtosis are two-sided tests. The null hypothesis to be
tested is that the skewness and kurtosis values are zero. The alternative hypothesis
generally are that skewness and kurtosis are not equal to zero.
The critical value tables, found on this Website, provide the critical values for different
selections of alpha, for various sample sizes.
For skewness, if the absolute value is equal or exceeds the critical value for your level
of confidence, reject the assumption of normality.
For kurtosis, if the kurtosis value is greater than or equal to the high critical value, or is
less than or equal to the low critical value, reject the assumption of normality.
MVPstats displays p-values for skewness based on a t-distribution where (D'Agostino
and Tietjen, 1971):
The 't' approximation has an error in p-value no more than 1/2 percent below samples
sizes of 20, compared to the published values. It is actually better (1/10 percent error)
for small alpha (0.01-0.02) in this range. In the range 20-35 it has an error not greater
than 1/10 percent. Above samples of size 40, the p-value is essentially exact.
The kurtosis random sampling distribution is difficult to model, so p-values cannot be
calculated. The program simply looks up in the table and displays the range of the
significance. Sample sizes greater than 5,000 use the Normal approximation of the
Kurtosis random sampling distribution to generate p-values.
fundamental task in
many statistical
analyses is to
characterize the
location and
variability of a data
set. A further
characterization of
the data includes
skewness and
kurtosis.
Skewness is a
measure of
symmetry, or more
precisely, the lack
of symmetry. A
distribution, or data
set, is symmetric if
it looks the same to
the left and right of
the center point.
Kurtosis is a
measure of whether
the data are peaked
or flat relative to a
normal distribution.
That is, data sets
with high kurtosis
tend to have a
distinct peak near
the mean, decline
rather rapidly, and
have heavy tails.
Data sets with low
kurtosis tend to
have a flat top near
the mean rather than
a sharp peak. A
uniform distribution
would be the
extreme case.
The histogram is an
effective graphical
technique for
showing both the
skewness and
kurtosis of data set.
Definition of For univariate data Y1, Y2, ..., YN, the formula for skewness is:
Skewness