Paul, You are demonstrating exactly why I remind everyone that we are after the truth. You say nothing has been found that supports the validity of CR. This is absolute nonesense. People have several times used invalid tests and jumped to conclusions, but those who bother to do the simulations properly end up admitting that CR works. Gus is an example of this. He SEES that when we start with uniform samples, we do get the results that CR produces.Gottfried sees it as well, as have most others who bothered to do the simulations. Gus's recent arguments have been based on an attempt to create uniform distributions but his understanding failed to appreciate why uniform distributions were needed and why trimming was logical. Gus used the word 'loaded" and that word is what prompted me to bring up the issue of honesty. The word loaded usually means there is some hidden meaning involved. There is nothing hidden in what I say. CR works, regardless of the criminal lengths to which statisticians are willing to go to suppress this fact.
Paul, you and others have every chance you need to disprove me. You have not and neither have any of the others people in statistics who market themselves as experts. In 1986 I discovered something important. Statisticians have fought that insight every since. In doing so, they commit fraud. And it is personal. The childish attacks on me are an indication of the lowly nature of the profession of statistics. I endured years of class work in statistics from people who really thought themselves of superior intellect. I paid a lot of money to attend all those classes. Well, I just do not see it that I got my money's worth. I see arrogance, I see pompous ignonorance and I see stupidity. I do not see any real love of the logic of statistics or any responsibility for the improvement of the profession. I see a bunch of criminals. The people on this newslist have recently attempted to disprove CR by violating assumptions, ignoring the probable existence of confounding variables and by highly evasive subsampling strategies. Some continue to work for the truth, Gus and Steve among them. I applaud them both. All I asked was how Gus did his sampling. And when he finally told me, it was obvious to me that he was simply reproducing the normal distribution. His was not a sin. I do not think he was being deceptive. He was just mistaken. People who seek truth make mistakes. Paul, you are not making mistakes. You are looking for an irrational fight, something to gossip about. Typical. The SEM treatment of CR is for all to see. Just go to the SEM archives. If you wish to see the acceptance letter and rejection letter I got from the journal SEM, just ask. I have nothing to hide. But youi will not seek the truth about these things. You lack the integrity. Some of you guys are trying your best to find some reason to reject CR. Ok, if you play fair. But you are ignoring all the logic, simulations and real data that support CR. This kind of closed mindedness protects you from having to think new thoughts but it is also an indication of intellectual cowardice. You think that you have an easy target by siding with tradition and the power folks in statistics. I would put logic above the whole bunch of you in any fight or search for truth. The use of normal distributed causes in correlation research is as stupid as it would be to use normally distributed cell sizes across the levels of an anova. Such a practice degrades sampling in the extremes, reduces power and forces us to over look conjunctive causes in favor of the conceptual garbage pile of disjunctive causes. Its is not just the people on this newlist who make this mistake. But apparently I am the only one with the intellectual integrity to point out that the emperor has no clothes. Now talk like a scholar. Do you SEE that the correlations between uniform causes polarize across the ranges of their mutual effect. If not, tell me where you get lost or disagree. I will try again to make it clear. Bill "Paul Bernhardt" <[EMAIL PROTECTED]> wrote in message [EMAIL PROTECTED]">news:[EMAIL PROTECTED]... > [EMAIL PROTECTED] said on 9/29/02 2:22 PM: > > >You seem to be playing the game "heads Gus wins, tails Bill loses." > > You seem to think that it is a game where there is a winner or a loser. > This error in perception causes great problems in the discussion. Gus > (and others here) are after the truth. You claim to be also, but belie > yourself with statements such as above, and your claims of bias and > unethical behavior by others. > > Gus and others here have treated your method with great seriousness, > more than I've seen anyone on the mainline stats discussion lists in the > past (I am not a subscriber to the SEM list to which you refer, maybe it > was similarly well treated there). They have attempted to understand it > and put it to test against both real and created data sets. The most > charitable way to put it is: they have found little to no support for > your method. > > Paul > . > . > ================================================================= > Instructions for joining and leaving this list, remarks about the > problem of INAPPROPRIATE MESSAGES, and archives are available at: > . http://jse.stat.ncsu.edu/ . > ================================================================= . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
