R help - Aug 2004 - (no subject)

Hi my name is Paolo Tommasini does anyone know how to compute a "mode"
( most frequent element ) for a distribution ?

thanks

On 08/24/04 13:50, Paolo Tommasini wrote:
>Hi my name is Paolo Tommasini does anyone know how to compute a
"mode"
>( most frequent element ) for a distribution ?
which.max

-- 
Jonathan Baron, Professor of Psychology, University of Pennsylvania
Home page: http://www.sas.upenn.edu/~baron
R search page: http://finzi.psych.upenn.edu/

No, this is not quite right: 

which.max

-- 
Jonathan Baron, Professor of Psychology, University of Pennsylvania
Home page: http://www.sas.upenn.edu/~baron
R search page: http://finzi.psych.upenn.edu/

You need to be more careful 

1. For a continuous distribution, the mode is ** not ** the most frequent
value (this has no meaning) -- it is the maximum of the density function. So
you must fit a density function and then estimate the mode, perhaps by using
which.max() on a discretization of the fitted density. Or, if you have the
fitted density in closed form (and it is unimodal) you can use calculus.

2. For a discrete distribution, which could be the sample empirical
distribution,use which.max(table()). 

-- Bert Gunter