1.3.5.14. Anderson-Darling Test http://www.itl.nist.gov/div898/handbook/eda/section3/eda35e.

htm

1. Exploratory Data Analysis

1.3. EDA Techniques
1.3.5. Quantitative Techniques

1.3.5.14. Anderson-Darling Test

Purpose: The Anderson-Darling test (Stephens, 1974) is used to test if a

Test for sample of data came from a population with a specific distribution. It
Distributional is a modification of the Kolmogorov-Smirnov (K-S) test and gives
Adequacy more weight to the tails than does the K-S test. The K-S test is
distribution free in the sense that the critical values do not depend on
the specific distribution being tested. The Anderson-Darling test
makes use of the specific distribution in calculating critical values.
This has the advantage of allowing a more sensitive test and the
disadvantage that critical values must be calculated for each
distribution. Currently, tables of critical values are available for the
normal, lognormal, exponential, Weibull, extreme value type I, and
logistic distributions. We do not provide the tables of critical values
in this Handbook (see Stephens 1974, 1976, 1977, and 1979) since
this test is usually applied with a statistical software program that
will print the relevant critical values.

The Anderson-Darling test is an alternative to the chi-square and

Kolmogorov-Smirnov goodness-of-fit tests.

Definition The Anderson-Darling test is defined as:

H0: The data follow a specified distribution.
Ha: The data do not follow the specified distribution
Test The Anderson-Darling test statistic is defined as
Statistic:

where

F is the cumulative distribution function of the

specified distribution. Note that the Yi are the ordered
data.
Significance
Level:

1 of 5 7/20/2010 9:56 PM
1.3.5.14. Anderson-Darling Test http://www.itl.nist.gov/div898/handbook/eda/section3/eda35e.htm

Critical The critical values for the Anderson-Darling test are

Region: dependent on the specific distribution that is being
tested. Tabulated values and formulas have been
published (Stephens, 1974, 1976, 1977, 1979) for a
few specific distributions (normal, lognormal,
exponential, Weibull, logistic, extreme value type 1).
The test is a one-sided test and the hypothesis that the
distribution is of a specific form is rejected if the test
statistic, A, is greater than the critical value.

Note that for a given distribution, the Anderson-

Darling statistic may be multiplied by a constant
(which usually depends on the sample size, n). These
constants are given in the various papers by Stephens.
In the sample output below, this is the "adjusted
Anderson-Darling" statistic. This is what should be
compared against the critical values. Also, be aware
that different constants (and therefore critical values)
have been published. You just need to be aware of
what constant was used for a given set of critical
values (the needed constant is typically given with the
critical values).

Sample Dataplot generated the following output for the Anderson-Darling

Output test. 1,000 random numbers were generated for a normal, double
exponential, Cauchy, and lognormal distribution. In all four cases,
the Anderson-Darling test was applied to test for a normal
distribution. When the data were generated using a normal
distribution, the test statistic was small and the hypothesis was
accepted. When the data were generated using the double
exponential, Cauchy, and lognormal distributions, the statistics were
significant, and the hypothesis of an underlying normal distribution
was rejected at significance levels of 0.10, 0.05, and 0.01.

The normal random numbers were stored in the variable Y1, the
double exponential random numbers were stored in the variable Y2,
the Cauchy random numbers were stored in the variable Y3, and the
lognormal random numbers were stored in the variable Y4.
***************************************
** anderson darling normal test y1 **
***************************************

ANDERSON-DARLING 1-SAMPLE TEST

THAT THE DATA CAME FROM A NORMAL DISTRIBUTION

1. STATISTICS:
NUMBER OF OBSERVATIONS = 1000
MEAN = 0.4359940E-02
STANDARD DEVIATION = 1.001816

ANDERSON-DARLING TEST STATISTIC VALUE = 0.2565918

ADJUSTED TEST STATISTIC VALUE = 0.2576117

2. CRITICAL VALUES:

2 of 5 7/20/2010 9:56 PM
1.3.5.14. Anderson-Darling Test http://www.itl.nist.gov/div898/handbook/eda/section3/eda35e.htm

90 % POINT = 0.6560000
95 % POINT = 0.7870000
97.5 % POINT = 0.9180000
99 % POINT = 1.092000

3. CONCLUSION (AT THE 5% LEVEL):

THE DATA DO COME FROM A NORMAL DISTRIBUTION.

***************************************
** anderson darling normal test y2 **
***************************************

ANDERSON-DARLING 1-SAMPLE TEST

THAT THE DATA CAME FROM A NORMAL DISTRIBUTION

1. STATISTICS:
NUMBER OF OBSERVATIONS = 1000
MEAN = 0.2034888E-01
STANDARD DEVIATION = 1.321627

ANDERSON-DARLING TEST STATISTIC VALUE = 5.826050

ADJUSTED TEST STATISTIC VALUE = 5.849208

2. CRITICAL VALUES:
90 % POINT = 0.6560000
95 % POINT = 0.7870000
97.5 % POINT = 0.9180000
99 % POINT = 1.092000

3. CONCLUSION (AT THE 5% LEVEL):

THE DATA DO NOT COME FROM A NORMAL DISTRIBUTION.

***************************************
** anderson darling normal test y3 **
***************************************

ANDERSON-DARLING 1-SAMPLE TEST

THAT THE DATA CAME FROM A NORMAL DISTRIBUTION

1. STATISTICS:
NUMBER OF OBSERVATIONS = 1000
MEAN = 1.503854
STANDARD DEVIATION = 35.13059

ANDERSON-DARLING TEST STATISTIC VALUE = 287.6429

ADJUSTED TEST STATISTIC VALUE = 288.7863

2. CRITICAL VALUES:
90 % POINT = 0.6560000
95 % POINT = 0.7870000
97.5 % POINT = 0.9180000
99 % POINT = 1.092000

3. CONCLUSION (AT THE 5% LEVEL):

THE DATA DO NOT COME FROM A NORMAL DISTRIBUTION.

***************************************
** anderson darling normal test y4 **
***************************************

ANDERSON-DARLING 1-SAMPLE TEST

THAT THE DATA CAME FROM A NORMAL DISTRIBUTION

1. STATISTICS:
NUMBER OF OBSERVATIONS = 1000
MEAN = 1.518372
STANDARD DEVIATION = 1.719969

ANDERSON-DARLING TEST STATISTIC VALUE = 83.06335

ADJUSTED TEST STATISTIC VALUE = 83.39352

2. CRITICAL VALUES:
90 % POINT = 0.6560000
95 % POINT = 0.7870000
97.5 % POINT = 0.9180000

3 of 5 7/20/2010 9:56 PM
1.3.5.14. Anderson-Darling Test http://www.itl.nist.gov/div898/handbook/eda/section3/eda35e.htm

99 % POINT = 1.092000

3. CONCLUSION (AT THE 5% LEVEL):

THE DATA DO NOT COME FROM A NORMAL DISTRIBUTION.

Interpretation The output is divided into three sections.

of the Sample
Output 1. The first section prints the number of observations and
estimates for the location and scale parameters.

2. The second section prints the upper critical value for the
Anderson-Darling test statistic distribution corresponding to
various significance levels. The value in the first column, the
confidence level of the test, is equivalent to 100(1- ). We
reject the null hypothesis at that significance level if the value
of the Anderson-Darling test statistic printed in section one is
greater than the critical value printed in the last column.

3. The third section prints the conclusion for a 95% test. For a
different significance level, the appropriate conclusion can be
drawn from the table printed in section two. For example, for
= 0.10, we look at the row for 90% confidence and compare
the critical value 1.062 to the Anderson-Darling test statistic
(for the normal data) 0.256. Since the test statistic is less than
the critical value, we do not reject the null hypothesis at the
= 0.10 level.

As we would hope, the Anderson-Darling test accepts the hypothesis

of normality for the normal random numbers and rejects it for the 3
non-normal cases.

The output from other statistical software programs may differ

somewhat from the output above.

Questions The Anderson-Darling test can be used to answer the following

questions:

Are the data from a normal distribution?

Are the data from a log-normal distribution?
Are the data from a Weibull distribution?
Are the data from an exponential distribution?
Are the data from a logistic distribution?

Importance Many statistical tests and procedures are based on specific

distributional assumptions. The assumption of normality is
particularly common in classical statistical tests. Much reliability
modeling is based on the assumption that the data follow a Weibull
distribution.

4 of 5 7/20/2010 9:56 PM
1.3.5.14. Anderson-Darling Test http://www.itl.nist.gov/div898/handbook/eda/section3/eda35e.htm

There are many non-parametric and robust techniques that do not

make strong distributional assumptions. However, techniques based
on specific distributional assumptions are in general more powerful
than non-parametric and robust techniques. Therefore, if the
distributional assumptions can be validated, they are generally
preferred.

Related Chi-Square goodness-of-fit Test

Techniques Kolmogorov-Smirnov Test
Shapiro-Wilk Normality Test
Probability Plot
Probability Plot Correlation Coefficient Plot

Case Study Airplane glass failure time data.

Software The Anderson-Darling goodness-of-fit test is available in some

general purpose statistical software programs, including Dataplot.

5 of 5 7/20/2010 9:56 PM