Characterization-based Q-Q plots for testing multinormality
Three quantile-quantile (Q-Q) plots are derived from a characterization for the multivariate normal distribution. The Q-Q plots can be easily used for detecting a possible departure from multinormality in high-dimensional data analysis. An example is illustrated to employ the plots in practice.
Year of publication: |
2004
|
---|---|
Authors: | Liang, Jiajuan ; Pan, William S.Y. ; Yang, Zhen-Hai |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 70.2004, 3, p. 183-190
|
Publisher: |
Elsevier |
Keywords: | Characterization Multinormality Quantile-quantile plot Spherical distribution |
Saved in:
Saved in favorites
Similar items by person
-
Testing the mean for dependent business data
Liang, Jiajuan, (2008)
-
How shareholder resources impact on the allocation of control power : example of China Vanke
Gao, Li, (2022)
-
Gao, Li, (2022)
- More ...