2.13.1.21 swtest

Brief Information

Shapiro-Wilk Normality test

Command Line Usage

1. swtest irng:=col(a)

2. swtest irng:=Col(A) stat:=w df:=d prob:=p

Variables

Display
Name
Variable
Name
I/O
and
Type
Default
Value
Description
Input irng

Input

Range

<active>

This variable specifies the input data range for test normality. The sample size of data range needs to be between 3 and 5000 for the Shapiro-Wilk test to apply.

Statistics stat

Output

double

<unassigned>

Value of Shapiro-Wilk W statistic. This variable specifies the name of output statistic value.

Degrees of Freedom df

Output

double

<unassigned>

Degrees of freedom of the test. This variable specifies the name of output degrees of freedom value.

P-value prob

Output

double

<unassigned>

Probability that the null hypothesis, i.e. that the data are from normal distribution, will be rejected. This variable specifies the name of output probability value.

Description

The Shapiro-Wilk Normality Test is used to determine whether or not a random sample of values follows a normal distribution. The normality test is useful because other statistical tests (such as the t-test, 1- and 2-way ANOVA) require that data be sampled from a normally distributed population in order to produce statistically significant results. A W statistic and a p value are computed, which can be compared with a chosen level of significance, and used to make a statistical decision.

Examples

1. To list all input and output results of Shapiro-Wilk test on the 1st column of the active worksheet, using default setting, type:

swtest irng:=col(a);
swtest.=

2. To return the Shapiro-Wilk test statistic for the 2nd column of active worksheet, and test to see if these sample data arise from a normal distribution, type:

swtest irng:=col(b) stat:=s;

Algorithm

This routine calculates Shapiro Wilk's W statistic with a given significance level for any sample size between 3 and 5000. Origin calculates the W statistic based on the Applied Statistics Algorithm R94. The full description of the theory behind this algorithm is given in Royston (1995).

Given a set of observations Swtest help English files image002.gif sorted into either ascending or descending order, the Shapiro Wilk W statistic is defined as:

Swtest help English files image004.gif

where Swtest help English files image006.gif is the sample mean and Swtest help English files image008.gif, for Swtest help English files image010.gif are a set of mathematical weights, the values of which depend only on the sample size n.

References

Royston JP. AS R94. 1995. Shapiro-Wilk normality test and P-value. Applied Statistics; 44(4).

Related X-Functions

stats, kstest, lillietest


Keywords:normal distribution