Naming Conventions

When adding a proof or definition to "The Book of Statistical Proofs", please try to adhere to the following rules for title and shortcut of your submission.

Naming Proofs

1. The title of a proof typically combines the name of the theorem with the topic it belongs to.

   • Example: "Linear transformation theorem for the multivariate normal distribution", a page on the linear transformation theorem (theorem) applied to the multivatiate normal distribution (topic).

   There are exceptions to this.

   • Example: "Bayes’ theorem" and "Bayes’ rule", pages on Bayes’ theorem and rule (theorems), currently filed under Bayesian inference (topic).

2. The shortcut of a proof typically connects abbreviations of the topic and of the theorem.

   • Example: mvn (for "multivariate normal distribution") + ltt (for "linear transformation theorem) = mvn-ltt (for "Linear transformation theorem for the multivariate normal distribution").

   There are exceptions to this.

   • Example: bayes-th (for "Bayes’ theorem") and bayes-rule (for "Bayes’ rule").

Naming Definitions

1. The title of a definition is typically the name of the mathematical object it describes.

   • Example: "Multivariate normal distribution", a page on the multivatiate normal distribution (definition).

   When the title of a definition is identical to the name of the topic it belongs to, the value of the metadata field "definition" may be set to "Definition".

   • Example: definition: "Definition", in "Multivariate normal distribution".

2. The shortcut of a definition is typically the most straightforward abbreviation of the defined object, generally without hyphens.

   • Example: mvn (for "Multivariate normal distribution").

   There are exceptions to this, especially when there are there is a concept which allows for the definition of sub-concepts.

   • Example: ent-cond (for "Conditional entropy").

Table of Contents

For filling in metadata fields containing hierarchy information, locating a proof or definition in the currently accepted page hierarchy, please consult the Table of Contents.

• Example: "Maximum likelihood estimation for the general linear model" (Proof)

title: "Maximum likelihood estimation for the general linear model"
chapter: "Statistical Models"
section: "Multivariate normal data"
topic: "General linear model"
theorem: "Maximum likelihood estimation"

• Example: "Joint cumulative distribution function" (Definition)

title: "Joint cumulative distribution function"
chapter: "General Theorems"
section: "Probability theory"
topic: "Cumulative distribution function"
definition: "Joint cumulative distribution function"