ACAT Statistics vs. Mathematical statistics

Posting to Autocat

On 12/1/2014 6:39 PM, Brent Eckert wrote:

It is not clear to me what the difference is supposed to be between the two LCSH headings Statistics and Mathematical statistics. The authority record for Statistics has this scope note:
Here are entered works on statistics as a branch of learning, as well as works consisting of general statistical data not limited to a specific place or topic, and works on the discipline of statistics. For the latter the heading may be subdivided by place. Works of statistical data on a specific place or topic are entered under the place or topic with the subdivision $a Statistics.
The authority record for Mathematical statistics has no scope note. It seems to me that according to this scope note Statistics should be used for works about the discipline of statistics and works that are primarily statistical data. Thus, a statistics textbook should get the heading Mathematical statistics, right? But in searching the LC catalog it seems that the two headings have been used indiscriminately and interchangeably for statistics textbooks.
(Also, what is supposed to be the difference between “statistics as a branch of learning” and “the discipline of statistics” in the scope note above?)

In my experience, the field of statistics includes more than just mathematics. For instance, there is logic involved when selecting a representative sample, which is very difficult and where people make mistakes all the time. Those who rely only on mathematics when they select a representative sample can (and do) make serious errors. Once you have your representative sample, then the mathematics really come into play but logic is still needed.

Still, I am not sure about this, and a professional statistician could easily prove me completely wrong. Wikipedia, which for better-or-worse is becoming more and more an authority, states:

“Mathematical statistics is the application of mathematics to statistics, which was originally conceived as the science of the state — the collection and analysis of facts about a country: its economy, land, military, population, and so forth. Mathematical techniques which are used for this include mathematical analysis, linear algebra, stochastic analysis, differential equations, and measure-theoretic probability theory.”

Is this correct? More important for us: Is this what the LCSH headings mean? That “statistics” means “the science of the state” while “mathematical statistics” means “the difficult, tedious, boring stuff?” I don’t think so.

As you mentioned, the headings seem to be handled inconsistently in the catalog, which is not surprising. I have seen similar notes elsewhere, distinguishing one as a “branch of learning” vs. the other as a “discipline”. I guess this would mean the difference between theoretical vs. practical statistics, but again I do not know.

Whenever I come across this kind of situation, I think: if we don’t really understand, what does this mean for the public? Especially today’s public who undoubtedly know Wikipedia better than our catalogs? What are they to think? How is this supposed to work in a linked-data universe?

There need to be fuller explanations on many of these headings, if for no one else, but for the overworked cataloger, who often has no time to “contemplate the higher realms of thought.”