I don't think that the p-value concept is as well defined for multivariate
distributions. Do you want the area under the curve corresponding to (x <
t.x & y < t.y) or (x < t.x | y < t.y) or ( t.x + t.y < C ) or
all the area where the height of the density is less than at t.x,t.y? or
possibly others
Do you have the definition of the density? Or is the data frame a representation
of the heights of the distribution at given x and y coordinates? If the second,
do they x and y coordinates form a grid? Or some random pattern? Etc.?
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at imail.org
801.408.8111
> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Leon Yee
> Sent: Tuesday, November 10, 2009 11:23 PM
> To: R help
> Subject: [R] p-value calculation on a joint distribution
>
> Dear R users,
>
> For a uni-variable distribution represented in a numerical vector,
> we can obtain a distribution function using 'ecdf', and then
calculate
> corresponding p-values. But if I have a 2-column dataframe representing
> a bi-variable joint distribution, given a pair of values, how can I get
> the p-value? And how can I plot out the density of the joint
> distribution?
>
> Best wishes,
>
> Leon
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.