Dear Walter,

From the inside perspective of someone who perfectly knows the difference and does the error himself often enough the reason is simple: For most parts of the theory the difference is not relevant, as the same concepts hold for both (e.g. both are conditionally negative definite, both carry sufficient information to do the kriging, ...) and if you have one you also have the other (dividing by 2). Further the students get annoyed by writing semivariogram over and over again. So effectively one runs into a habit thinking of them as more or less the same thing and this is called variogram for convenience. And than suddenly the brain slips and you use the term also in the rare situation in which its clearly the semivariogram. You still write gamma and not 2 gamma and assume that everybody knows what you are talking about.

However the difference gets obscure to those listeners not perfectly aware of the few situations where the difference is relevant (computing the kriging error). And than the sloppiness has become a well learned wrong terminology.

Therefore I would consider this degradation  a psychological mechnanism happening again and again and not as something that happened in literature once and has become tradition.

Best regards,

Gerald

You can find the answer in this article:

Mathematical Geosciences

August 2011, Volume 43, Issue 6, pp 735-740

Date: 01 Jul 2011

Variogram or Semivariogram? Variance or Semivariance? Allan Variance or Introducing a New Term?

Dear Walter,

From the inside perspective of someone who perfectly knows the difference and does the error himself often enough the reason is simple: For most parts of the theory the difference is not relevant, as the same concepts hold for both (e.g. both are conditionally negative definite, both carry sufficient information to do the kriging, ...) and if you have one you also have the other (dividing by 2). Further the students get annoyed by writing semivariogram over and over again. So effectively one runs into a habit thinking of them as more or less the same thing and this is called variogram for convenience. And than suddenly the brain slips and you use the term also in the rare situation in which its clearly the semivariogram. You still write gamma and not 2 gamma and assume that everybody knows what you are talking about.

However the difference gets obscure to those listeners not perfectly aware of the few situations where the difference is relevant (computing the kriging error). And than the sloppiness has become a well learned wrong terminology.

Therefore I would consider this degradation  a psychological mechnanism happening again and again and not as something that happened in literature once and has become tradition.

Best regards,

Gerald

I agree with K. Gerald. And I've made the same mistake several times without giving any thought to it.

Nevertheless at least for published articles and "Introduction to geostatistics" courses there should be more care (in fact for every media that presents itself for newcomers). I'm guessing that the expression variogram is pretty obvious, on most occasions,  for both author and reviewer but that does not mean it is for all readers.

Unfortunately it's the kind of "mistake" that can bring misinterpretation for anyone outside the area, thus leaving an article with a more difficult reading. It's the ever lasting "tradition" of professionals writing for themselves. It's not anyone fault but it is a problem.