When pundits get together, concerns about priority precede the need for scientific integrity as much as Journel's assumption of spatial dependence precedes Fisher's F-test. Other sources of concern are argument, debate and invective. Krige mused in 1977 that geostatistics encountered, "some stormy receptions from the English-speaking mining countries around the world." Armstrong was troubled in 1989 by the rise and fall of kriging covariances and variances. Journel recalled in 1992 that, "Mathematical Geology has had more than its share of invective."

I submitted in June 1993 an abstract for a paper in which I derived the variance of a single kriged estimate, and deduced that the kriging variance of a set of kriged estimates is invalid. My "very interesting" paper could not be accommodated but when I asked Dimitrakopoulos, Chairman of Geostatistics for the Next Century, a Forum in honor of David, author of first geostatistical textbook, if I could attend without presenting a paper, I received no response.

It has occurred to IAMG's President that I might wish to voice my concerns at the 2005 IAMG meeting in Toronto . Need Krige be told in person that the distance-weighted average lost its variance when it turned into a kriged estimate? How often do I have to tell Journel that assuming spatial dependence makes no sense? And how many times do I have to tell Armstrong that the kriging variance of a set of kriged estimates is as meaningless a measure for variability as its kriging covariance is for spatial dependence? How many more gurus need I tell face-to-face that each calculated datum has its own variance? And that a set of n measured data with equal weights give df r =n-1 degrees of freedom for the randomized set, and df o =2(n-1) for the first variance term of the ordered set?

Geostatistics is beyond salvation! If the pundits were to break their silence and admit that the distance-weighted average does indeed have its own variance, and that its metamorphosis into a kriged estimate does not make it any less functionally dependent, then the clock is turned back to mathematical statistics. It saddens me that so many textbooks were published after I reported in April 1992 that geostatistics is a fundamentally flawed variant of mathematical statistics. I shall post more reviews if and when necessary. Most of all, I shall post numerous applications of statistical methods on my website.