# Correct formatting (capitalization, italicization, hyphenation) of “p-value”?

I realize this is pedantic and trite, but as a researcher in a field outside of statistics, with limited formal education in statistics, I always wonder if I'm writing "p-value" correctly. Specifically:

1. Is the "p" supposed to be capitalized?
2. Is the "p" supposed to be italicized? (Or in mathematical font, in TeX?)
3. Is there supposed to be a hyphen between "p" and "value"?
4. Alternatively, is there no "proper" way of writing "p-value" at all, and any dolt will understand what I mean if I just place "p" next to "value" in some permutation of these options?
-
See the meta thread: meta.stats.stackexchange.com/questions/213/… where this question is proposed to be closed. – user28 Jul 30 '10 at 2:00

There do not appear to be "standards". For example:

• The Nature style guide refers to "P value"
• This APA style guide refers to "p value"
• The Blood style guide says:
• Capitalize and italicize the P that introduces a P value
• Italicize the p that represents the Spearman rank correlation test
• Wikipedia uses "p-value", but italicizes the p if used by itself

My brief, unscientific survey suggests that the most common combination is lower-case, italicized p without a hyphen.

-
Wow! I didn't expect this to vary. BTW, has the Nature style guide changed since you posted this answer? It's now pointing to "Life sciences reporting guidelines". – Andrew Grimm Oct 30 '13 at 1:35

This seems to be a style issue with different journals and publishers adopting different conventions (or allowing a mixed muddle of styles depending on authors' preferences). My own preference, for what it's worth, is p-value, hyphenated with no italics and no capitalization.

-

The ASA House Style seems to recommend italicizing the p with hyphen: p-value. A google scholar search shows varied spellings.

-

P value from theoretical point of view is some realization of random variable. There is some standard (in probability) to use upper case letters for random variables and lower case for realizations. In table headers we should use P (maybe italicize), in text together with its value p=0.0012 and in text describing for example methodology p-value .

-
So in a table header, something like "Student's $T$" would be used for the statistic and "$P$" for the significance? I'm a bit worried that nobody will get this subtlety and people will just assume a stupid typo ... – Christian Feb 27 '13 at 11:57