Jack Tomsky changed matter

WORMTOMSKY SAID:

Herman Rubn wrote quoting me
*** The Lillieforss Test has critical values that are 2/3 (approximately) shorter than he K-S ones. In consequence using the latter ones the confidence intervals are INCORRECTLY LARGER than they should be, fail to reject H0 (when we REALY should do so) is MUCH MORE PROBABLE than what the chosen K-S ALPHA VALUE seems to indicate.***

My reply


READING THIS START any rational being expected that Herman´s response will report the comparison of conclusions concerning the use of each tests: one sample K-S and Lilliefors. However I was found nothing at all relative to this crucial point: H. Rubin change the point (once more Academic American escape, acronym AAE) and introduce a note about confidence limits of parameters in a *** gof (Goodness of Fit) *** TEST ?!.
AMAZING, ABSOLUTELY AMAZING!
It seems he IGNORES that prior to perform a Lilliefors´s (had him really made even one, I dare?) the parameters, m and s, (estimated from the sample X) have to be used in order to reduce data to a N(0,1) data, more exactly Z = (X-m)/s. Is Herman a son of CANNED SOFTWARE (trash in, trash out).? I think so.

The remainder is an incoherent (in very bad English) mixing of other test including the sentence worthing to be highlighted because it?s a source of brilliant new discoveries in Statistics, I ask him to reproduce here:: *** A test generally should not be used to test what it is not intended to test

*************************
I HAD NOT TO ADD TO MY COMMENTS, INCLUDING my reaction to THIS LAST PRENOSTIC Rubin´s statement,
However it should be noted that
_____Ronald A. Fisher
_____Herman Rubi
_____Luis Amaral Afonso
ARE CLEAR IN THAT THE CORRECT STATEMENT WHEN THE TEST FALLS IN THE SO-CALLED ACCEPTANCE REGION IS:
___there is not sufficient evidence to reject the Null Hypotheses_____________________

Wormtomsky had other interpretation, it is a ONE MAN ONE so no trouble at all unless for those that believes that really a Null Hypotheses can be proved true, hence accepted.
**********************
Luis AmaralAfonso
.