StatsWatsonWilliamsTest
StatsWatsonWilliamsTest [/ALPH=val /Q/Z/T=k /WSTR=waveListString ] [srcWave1, srcWave2, srcWave3,...]
The StatsWatsonWilliamsTest operation performs the Watson-Williams test for two or more sample means. Output is to the W_WatsonWilliams wave in the current data folder or optionally to a table.
Flags
| /ALPH=val | Sets the significance level (default val =0.05). | ||||||
| /Q | No results printed in the history area. | ||||||
| /T=k | Displays results in a table. k specifies the table behavior when it is closed. | ||||||
| |||||||
| The table is associated with the test, not the data. If you repeat the test, it will update any existing table with the new results. | |||||||
| /WSTR=waveListString | |||||||
| Specifies a string containing a semicolon-separated list of waves that contain sample data. Use waveListString instead of listing each wave after the flags. | |||||||
| /Z | Ignores errors. V_flag will be set to -1 for any error and to zero otherwise. | ||||||
Details
The StatsWatsonWilliamsTest must have at least two input waves, which contain angles in radians, can be single or double precision, and can be of any dimensionality; the waves must not contain any NaNs or INFs.
The Watson-Williams H0 postulates the equality of the means from all samples against the simple inequality alternative. The test computes the sums of the sines and cosines from which it obtains a weighted r value (rw). According to Mardia, you should use different statistics depending on the size of rw: for rw>0.95 use the simple F statistic, but for 0.95>rw>0.7 you should use the F-statistic with the K correction factor. Otherwise you should use the t-statistic. StatsWatsonWilliamsTest computes both the (corrected) F-statistic and the t-statistic as well as their corresponding critical values.
V_flag will be set to -1 for any error and to zero otherwise.
References
See, in particular, Section 6.3 of:
Mardia, K.V., Statistics of Directional Data, Academic Press, New York, New York, 1972.
See, in particular, Chapter 27 of:
Zar, J.H., Biostatistical Analysis, 4th ed., 929 pp., Prentice Hall, Englewood Cliffs, New Jersey, 1999.
See Also
Statistical Analysis, StatsWatsonUSquaredTest, StatsWheelerWatsonTest