Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
NCTM or The Math Forum.


Luis A. Afonso
Posts:
4,758
From:
LIsbon (Portugal)
Registered:
2/16/05


ALM  JarqueBera test
Posted:
Jun 6, 2013 5:33 PM


An error is easily detectable at the paper arXiv:math/0509423v1 [math.ST] 19 Sep. 2005 Precise finitesample quantiles of the JarqueBera adjusted Lagrange multiplier test D. Wurtz, H. G. Kratzgraber
In what concerns the ALM test statistics it seems had been unnoticed, as long as I know, that this test statistics definition  with a wrong multiplicative N (paper´s expression (2))  is incompatible with (c1) and (c3) simply because these quantities (skewness and kurtosis variances) behave as 6/N and 24/N as the sample size grows to infinite, resulting that, without the leading N, to be similar, as it should be, with the LM formula (1), here N rightly expressed.
Luis A. Afonso



