shapiro.test
Shapiro-Wilk Test for Normality
Description
Computes the Shapiro-Wilk W-statistic for testing for departures from normality.
Usage
shapiro.test(x)
Arguments
x |
a numeric vector. Missing values (NAs) and infinite values (Infs) are allowed, but are ignored in the calculation.
The length of x, after dropping infinite values, must be greater than 3 and less than 5000.
|
Details
The calculations for this test are based on the algorithm by Royston (1995).
Value
returns an object of class htest that represent the result of the Shapiro-Wilk normality test. This object contains the following components:
statistic |
value of the test statistic along with the names attribute W.
|
p.value |
p-value for the test.
|
data.name |
a character string that describes the actual name of the data used in the test.
|
method |
name of the test applied, for example Shapiro-Wilk Normality Test.
|
Background
Shapiro and Wilk's W-statistic is a well-known goodness of fit test
for the normal distribution. It is attractive because it has a simple,
graphical interpretation. You can think of it as an approximate
measure of the correlation in a normal quantile-quantile plot of the
data.
Differences Between TIBCO Enterprise Runtime for R And Open-Source R
When you run the shapiro.test on a dataset
with missing values (NA),
TIBCO Enterprise Runtime for R reports a warning about NAs that is not shown in R.
(The test output is the same.)
In R, shapiro.test fails if the data includes Infs.
TIBCO Enterprise Runtime for R removes the non-finite value(s), issues a warning about them,
and then runs the test on the remaining values.
References
Royston, P. (1995).
A remark on algorithm AS 181: the W-test for normality.
Applied Statistics 44: 547-551.
Shapiro, S.S. and Wilk, M.B. (1965).
An analysis of variance test for normality (complete samples).
Biometrika 52: 591-611.
Patrick Royston (1982)
An extension of Shapiro and Wilk's W test for normality to large
samples.
Applied Statistics, 31, 115--124.
Patrick Royston (1982)
Algorithm AS 181: The W test for Normality.
Applied Statistics, 31, 176--180.
See Also
Examples
# Should not be significant
shapiro.test(rnorm(30))
# Should be significant.
shapiro.test(runif(50))