What Does arg Mean in Maximum Likelihood Estimation?

[Simfish]

http://en.wikipedia.org/wiki/Maximum_likelihood


What exactly does the "arg" here mean? It seems to be an unnecessary - the max L(\theta) seems to be sufficient enough. Or am I missing something?
\widehat{\theta} = \underset{\theta}{\operatorname{arg\ max}}\ \mathcal{L}(\theta).

 

[EnumaElish]

arg is needed because the left-hand side is the argument of L.

One can write L(\widehat{\theta}) = \underset{\theta}\max\ {L(\theta)}..

Or one can write \widehat{\theta} = \underset{\theta}{\operatorname{arg\ max}}\ {L}(\theta).