The Wheeler-Watson tests the hypothesis H0: the samples came from the same population.

1. Testing two waves

The following waves represent angles in radians. Both are centered about pi/6.

data1 data2
0.553951 0.572457
0.556496 0.516971
0.558007 0.619459
0.493574 0.580837
0.551672 0.585822
0.518077 0.534662
0.517558 0.563266
0.532961 0.49541
0.499501 0.489289
0.564656 0.628698
0.511045 0.555638
0.521595 0.46913
0.486378 0.523104
0.532568 0.492851
0.531593 0.425477
  0.57336
  0.489757
  0.509024
  0.544693

To test the hypothesis H0, execute:

StatsWheelerWatsonTest/T=1/Q data1,data2

The results are displayed in the Wheeler-Watson Test table:

totalPoints 34
numSamples 2
W 7.10517
Critical 5.99146

Since the test statistic W is greater than the critical value, H0 is rejected.

2. Testing more than two waves (Mardia's method)

The additional sample is in the wave data3:

data3
0.583937
0.492531
0.44756
0.528031
0.549251
0.609156
0.475164
0.502774
0.523131
0.635587
0.610486
0.489298
0.54757
0.506267
0.5838
0.419416
0.616708

Again, H0 corresponds to the samples being from the same distribution. To run the test execute:

StatsWheelerWatsonTest/T=1/Q data1,data2,data3

The results are displayed in the Wheeler-Watson Test table:

totalPoints 51
numSamples 3
W 9.16895
Critical 9.48773

This time the test statistic is smaller than the critical value and H0 can't be rejected. This result may be explained, in part, by the fact that the wave data3 was constructed intentionally to have circular dispersion between that of data1 and data2. This can be seen by comparing the results of StatsCircularMoments for the three waves:

number_of_points 15 19 17
number_of_NaNs 0 0 0
C 12.9487 16.3212 14.5841
S 7.56325 9.67855 8.67316
R 14.9957 18.9751 16.9682
cBar 0.863245 0.859011 0.857889
sBar 0.504217 0.509397 0.510186
rBar 0.999713 0.998692 0.99813
tBar 0.528642 0.53526 0.536513
V 0.000286899 0.00130836 0.00187004
v 0.0239558 0.0511707 0.0611848
median 0.531594 0.534664 0.528032
mean_deviation 0.0201722 0.042801 0.0517856
Circular_Dispersion 0.000573973 0.00261935 0.00374701
Skewness 0.404109 0.214704 0.22167
Kurtosis -2.24571 -1.05747 -1.95149
Confidence_d 0.0129445 0.0242404 0.0308417

Forum

Support

Gallery

Igor Pro 9

Learn More

Igor XOP Toolkit

Learn More

Igor NIDAQ Tools MX

Learn More