Message-ID: <19B6A447-C2DD-41C3-AE8D-0830BE2B46CC@comcast.net>
Date: 2011-01-20T20:29:29Z
From: David Winsemius
Subject: densities greater than 1 for values within an (0, 1) intervall
In-Reply-To: <1295551727577-3228268.post@n4.nabble.com>
The same way you interpret densities less than one?
On Jan 20, 2011, at 2:28 PM, Paul Ramer wrote:
>
> How does one then interpret kernel density distributions with values
> greater
> than one?
The same way you interpret densities less than one?
density != probability
>
> My output from the density function.
> ---
> density(delt.m[[1]][,6], na.rm=TRUE)
>
> Call:
> density.default(x = delt.m[[1]][, 6], na.rm = TRUE)
>
> Data: delt.m[[1]][, 6] (171 obs.); Bandwidth 'bw' = 0.004501
>
> x y
> Min. :-0.05211 Min. : 0.00586
> 1st Qu.:-0.02177 1st Qu.: 0.43632
> Median : 0.00856 Median : 3.08833
> Mean : 0.00856 Mean : 8.23366
> 3rd Qu.: 0.03889 3rd Qu.:14.97542
> Max. : 0.06923 Max. :30.04107
--
David Winsemius, MD
West Hartford, CT