Professional Documents
Culture Documents
Normality Tests: NCSS Statistical Software
Normality Tests: NCSS Statistical Software
com
Chapter 194
Normality Tests
Introduction
This procedure provides seven tests of data normality. If the variable is normally distributed, you can use
parametric statistics that are based on this assumption.
If a variable fails a normality test, it is critical to look at the histogram and the normal probability plot to see if an
outlier or a small subset of outliers has caused the non-normality. If there are no outliers, you might try a
transformation (such as, the log or square root) to make the data normal. If a transformation is not a viable
alternative, nonparametric methods that do not require normality may be used.
Always remember that a reasonably large sample size is required to detect departures from normality. Only
extreme types of non-normality can be detected with samples less than fifty observations.
There is a common misconception that a histogram is always a valid graphical tool for assessing normality. Since
there are many subjective choices that must be made in constructing a histogram, and since histograms generally
need large sample sizes to display an accurate picture of normality, preference should be given to other graphical
displays such as the box plot, the density trace, and the normal probability plot.
Normality tests generally have small statistical power (probability of detecting non-normal data) unless the
sample sizes are at least over 100.
Technical Details
This section provides details of the seven normality tests that are available.
Shapiro-Wilk W Test
This test for normality has been found to be the most powerful test in most situations. It is the ratio of two
estimates of the variance of a normal distribution based on a random sample of n observations. The numerator is
proportional to the square of the best linear estimator of the standard deviation. The denominator is the sum of
squares of the observations about the sample mean. The test statistic W may be written as the square of the
Pearson correlation coefficient between the ordered observations and a set of weights which are used to calculate
the numerator. Since these weights are asymptotically proportional to the corresponding expected normal order
statistics, W is roughly a measure of the straightness of the normal quantile-quantile plot. Hence, the closer W is to
one, the more normal the sample is.
The probability values for W are valid for sample sizes greater than 3. The test was developed by Shapiro and
Wilk (1965) for sample sizes up to 20. NCSS uses the approximations suggested by Royston (1992) and Royston
(1995) which allow unlimited sample sizes. Note that Royston only checked the results for sample sizes up to
5000, but indicated that he saw no reason larger sample sizes should not work. W may not be as powerful as other
tests when ties occur in your data. The test is not calculated when a frequency variable is specified.
Anderson-Darling Test
This test, developed by Anderson and Darling (1954), is a popular among those tests that are based on EDF
statistics. In some situations, it has been found to be as powerful as the Shapiro-Wilk test.
Note that this test is not calculated when a frequency variable is specified.
194-1
© NCSS, LLC. All Rights Reserved.
NCSS Statistical Software NCSS.com
Normality Tests
Martinez-Iglewicz Test
This test for normality, developed by Martinez and Iglewicz (1981), is based on the median and a robust estimator
of dispersion. The authors have shown that this test is very powerful for heavy-tailed symmetric distributions as
well as a variety of other situations. A value of the test statistic that is close to one indicates that the distribution is
normal. This test is recommended for exploratory data analysis by Hoaglin (1983). The formula for this test is:
n
∑( x i −x )
2
i =1
I =
( n − 1)s bi2
where sbi2 is a biweight estimator of scale.
Kolmogorov-Smirnov Test
This test for normality is based on the maximum difference between the observed distribution and expected
cumulative-normal distribution. Since it uses the sample mean and standard deviation to calculate the expected
normal distribution, the Lilliefors’ adjustment is used. The smaller the maximum difference the more likely that
the distribution is normal.
This test has been shown to be less powerful than the other tests in most situations. It is included because of its
historical popularity.
( n + 1)( n + 3)
T = b1
6( n − 2)
W 2 = −1 + 2( C − 1)
2
a=
W 2
−1
1
d =
ln(W )
194-2
© NCSS, LLC. All Rights Reserved.
NCSS Statistical Software NCSS.com
Normality Tests
3n − 3
b2 −
n +1
G=
24n( n − 2)( n − 3)
( n + 1) 2 ( n + 3)( n + 5)
6( n 2 − 5n + 2) 6( n + 3)( n + 5)
E=
( n + 7)( n + 9) n( n − 2)( n − 3)
82 4
A= 6+ + 1+ 2
EE E
D’Agostino Omnibus
D’Agostino (1990) describes a normality test that combines the tests for skewness and kurtosis. The statistic, K2,
is approximately distributed as a chi-square with two degrees of freedom. After calculated zs and zk, calculate K2
as follows:
K 2 = z s2 + z k2
Data Structure
The data are contained in a single variable.
194-3
© NCSS, LLC. All Rights Reserved.
NCSS Statistical Software NCSS.com
Normality Tests
Setup
To run this example, complete the following steps:
Option Value
Variables Tab
Data Variable(s) ...................................... SepalLength
Report Options (in the Toolbar)
Variable Labels ....................................... Column Names
Summary Section
Summary Section of SepalLength ─────────────────────────────────────────────────
Standard Standard
Count Mean Deviation Error Minimum Maximum Range
150 58.43333 8.280662 0.6761132 43 79 36
Count
This is the number of non-missing values. If no frequency variable was specified, this is the number of non-
missing rows.
Mean
This is the average of the data values.
Standard Deviation
This is the standard deviation of the data values
Standard Error
This is the standard error of the mean.
194-4
© NCSS, LLC. All Rights Reserved.
NCSS Statistical Software NCSS.com
Normality Tests
Minimum
The smallest value in this variable.
Maximum
The largest value in this variable.
Range
The difference between the largest and smallest values for a variable.
Count Section
Counts Section of SepalLength ──────────────────────────────────────────────────
Rows
This is the total number of rows available in this variable.
Sum of Frequencies
This is the number of non-missing values. If no frequency variable was specified, this is the number of non-
missing rows.
Missing Values
The number of missing (empty) rows.
Distinct Values
This is the number of unique values in this variable. This value is useful for finding data entry errors and for
determining if a variable is continuous or discrete.
Shapiro-Wilk W Test
This test for normality, developed by Shapiro and Wilk (1965), has been found to be the most powerful test in
most situations. The test is not calculated when a frequency variable is specified.
194-5
© NCSS, LLC. All Rights Reserved.
NCSS Statistical Software NCSS.com
Normality Tests
Anderson-Darling Test
This test, developed by Anderson and Darling (1954), is the most popular normality test that is based on EDF
statistics. In some situations, it has been found to be as powerful as the Shapiro-Wilk test. The test is not
calculated when a frequency variable is specified.
Martinez-Iglewicz Test
This test for normality, developed by Martinez and Iglewicz (1981), is based on the median and a robust estimator
of dispersion.
Kolmogorov-Smirnov
This test for normality is based on the maximum difference between the observed distribution and expected
cumulative-normal distribution. This test has been shown to be less powerful than the other tests in most
situations. It is included because of its historical popularity.
D’Agostino Skewness
D’Agostino (1990) describes a normality test based on the skewness coefficient.
D’Agostino Kurtosis
D’Agostino (1990) describes a normality test based on the kurtosis coefficient.
D’Agostino Omnibus
D’Agostino (1990) describes a normality test that combines the tests for skewness and kurtosis.
194-6
© NCSS, LLC. All Rights Reserved.
NCSS Statistical Software NCSS.com
Normality Tests
Histogram Plot
The following plot shows a histogram of the data.
Histogram
The histogram is a traditional way of displaying the shape of a group of data. It is constructed from a frequency
distribution, where choices on the number of bins and bin width have been made. These choices can drastically
affect the shape of the histogram. The ideal shape to look for in the case of normality is a bell-shaped distribution.
194-7
© NCSS, LLC. All Rights Reserved.
NCSS Statistical Software NCSS.com
Normality Tests
This is a plot of the inverse of the standard normal cumulative versus the ordered observations. If the underlying
distribution of the data is normal, the points will fall along a straight line. Deviations from this line correspond to
various types of non-normality. Stragglers at either end of the normal probability plot indicate outliers. Curvature
at both ends of the plot indicates long or short distribution tails. Convex, or concave, curvature indicates a lack of
symmetry. Gaps, plateaus, or segmentation in the plot indicate certain phenomenon that need closer scrutiny.
194-8
© NCSS, LLC. All Rights Reserved.