[R] How to use multiple test for trend in proportions?

[David Winsemius]

On Dec 9, 2013, at 9:46 AM, celebrex wrote:

> dataorder.csv <http://r.789695.n4.nabble.com/file/n4681879/dataorder.csv>

>  I have a set of data as attached.Like (181,246,378).....(180,228,378). And I
> want to use test for trend in proportions using (400,500,600) as denominator
> and get 119 p-values. So I use the code as
> below:

Reformatted:
> 
> data=read.table("dataorder.csv", sep=",",  stringsAsFactors=F)
> 
> i<-1:nrow(data)
> n <- c(400,500,600)
> e <- data[i,c(1,2,3)]

What is your intent with that command?


> prop.trend.test(e, n)
> 
> allpvalue = apply(data, 1, function(x) { prop.trend.test(e, n)$p.value})

In the function body there is no reference to "x". Did you intend this:

   allpvalue = apply(data, 1, function(x) { prop.trend.test(x, n)$p.value})


> However, there is something wrong but I can't figure out, can anybody
> help? Thanks

Posting from Nabble often screws up formatting,  as it did big-time in your case. It is possible to post in plain text from Nabble, so you should now take the time to learn how to do that.

> View this message in context: http://r.789695.n4.nabble.com/How-to-use-multiple-test-for-trend-in-proportions-tp4681879.html
> Sent from the R help mailing list archive at Nabble.com.

Nabble is NOT the Rhelp Mailing List!

> 	[[alternative HTML version deleted]]

And Nabble also deletes this very important message which you should now read and heed:
> 

> 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.
-- 
David Winsemius
Alameda, CA, USA