What's wrong with geostatistics?
Geostatistical factoids
Statistical facts
The Bre-X fraud
Bait borehole
Sampling and Statistics Explained
Spreadsheet templates
Statistics for geoscientists
More statistical facts
Geostatistical textbooks
About my work
Contact me
Geostatscam Blog



























Dr Isobel Clark praised "Andre Journel and others at Fontainebleau who taught her all she knows about the theory of The theory of Regionalized variables". So she is a dependent thinker! She stripped the factor 2 off df=2(n-1) degrees of freedom for "mathematical convenience"! She didn't apply Fisher's F-test to verify whether or not her set of hypothetical uranium concentrations displays a significant degree of spatial dependence within her sample space? Dr Clark's set is randomly distributed within her sample space!

Dr Andre G Journel, Matheron's most gifted disciple, stripped the variance off the distance-weighted average and called what was left kriged estimate. He found zero kriging variances, assumed spatial dependence but does not count degrees of freedom. He teaches only those who have a PhD in geostatistics. His latest flavor is stringing Markov chains. Good grief!!!

Dr Roussos Dimitrakopoulos was born to be McGill's miracle man and JMG's Editor-in-Chief. He knows all about stochastic mine planning optimization with Markov chains. Dr RD does not know how to derive unbiased confidence limits for contets and grades.

In November 1989, Merks and Merks applied Fisher's F-test in Precision Estimates for Ore Reserves and confirmed spatial dependence between gold grades of ordered rounds in a decline. Testing for spatial dependence troubled Professor Dr M David, CIM Bulletin's most dedicated enforcer of Matheronian geostatistics. Scores of similarly gifted geostatistocrats postulated spatial dependence may be inferred unless proven otherwise. Stanford's Journelwas troubled when "classical Fischerian statistics" proved a significant degree of spatial dependence between gold grades of ordered rounds. Fisher's F-test proved the intrinsic variance of Bre-X's bogus gold in Busang's barren rock to be statistically identical to zero, as it ought to be. Sound statistics did so several months before Bre-X's boss salter vanished! Bre-X's original and duplicate bogus assays for a few early boreholes could have proved that a salting scam was in progress at the Busang project!

Professor Dr R Dimitrakopoulos, Editor-in-Chief, Journal for Mathematical Geosciences, stand on guard against genuine variances. His journal got a new name and Markov chain is a reborn game. Dr RD teaches McGill's students all he knows about stochastic modeling with Markov chains. When he chaired in June 1993 a forum on Geostatistics for the Next Century, he did not even know that each and every kriged estimate does have its own variance. JMG's Editor-in-Chief got into playing games with Markov chains. Surely, McGill's students should know how to derive the variance of the distance-weighted average AKA kriged estimate. Students should also know that stochastic modeling of ore reserves with Markov chains is a scientific fraud. Voodoo variances are doomed to generate junk statistics.

The world's mining industry is caught in a Catch-22. The problem is that grades and contents of mineral inventories in annual reports are due to shrink during mining. David dabbled at geostatistical grade control in his 1988 handbook. He was proud that his kriged block was larger than his so-called erratic block. But he did not show that his kriged block had a significantly lower grade. Less pay dirt in mined ores add up to more tailings! Invalid grade control in exploration and mining. Statistical grade and quality control with ISO standards in smelting and refining! Now that's a Catch-22! Sound statistics in smelting and refining but surreal geostatistics in exploration and mining!

The National Securities Regulator ought to rule it is a scientific fraud to assume ore between boreholes. The more so since Bre-X showed more red flags than a Bolshevist parade. The OSC watched the parade with Felderhof in front! Incompetence is rampant but not deemed a crime. I explained to the OSC in 1994 and to the SEC in 2003 why Matheronian geostatistics is a flawed variant of applied statistics. Infinite sets of kriged estimates, zero pseudo kriging variances and lack of degrees of freedom make goofy geostatistics! All of it seems to make sense to CRIRSCO's new Chair and her flock of Crirsconians!

Matheron's quixotic work is posted with the On-Line Library of the Centre de Géostatistique. Matheron was not a born genius at probability but a self-made wizard of odd statistics. One-to-one correspondence between functions and variances remained beyond his grasp until his passing in 2000. Matheron did fumble two variances whereas Agterberg fumbled the same variance twice. Scores of qualified persons accept geostatistics as much as do geostatistocrats and krigeologists!

Statistically challenged experts talk confidently about confidence without limits. Applied statistics does give unbiased confidence limits for metal contents of mined ores and mineral concentrates. I have done so for Barrick Gold. It can be done not only for metal contents and grades of ore reserves but also for proven ore within inferred resources. Borehole Statistics with Spreadsheet Software shows how to derive 95% confidence intervals and ranges for masses of metals in volumes of in-situ ores. It's high time to set up an ISO Technical Committee on reserve and resource estimation. But Barrick Gold, BHP Billiton, Rio Tinto and Vale prefer stochastic mine planning with voodoo variances.

Between January 1, 2007 and March 31, 2014 a total of 116,896 visitors called on this site 198,554 times, looked at 558,549 pages, and downloaded 37.4 GB of sound sampling practices and proven statistical methods. Most visitors to my website in March 2014 came from USA, China, Ukraine, Netherlands and Israel.

Functions without variances?
Learn More click on link below.





©Matrix Consultants Limited All rights reserved.