extracting p-values in scientific notation

Dear all
How does print.htest display the p-value in scientific notation?

(x<- cor.test(iris[[1]], iris[[3]]))

	Pearson's product-moment correlation

data:  iris[[1]] and iris[[3]]
t = 21.65, df = 148, p-value<  2.2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
  0.8270 0.9055
sample estimates:
    cor
0.8718

Above the p-value comes as '<  2.2e-16', while inspecting the object I
get a good old '0'.

x$p.value

[1] 0

I tried to inspect print.htest but couldn't find it. I also played
with format, round and the like to no avail. Any pointers?

Regards
Liviu

is(x)

# take a look at     stats:::print.htest
format.pval(x$p.value)

Dear all
How does print.htest display the p-value in scientific notation?

(x <- cor.test(iris[[1]], iris[[3]]))

? ? ? ?Pearson's product-moment correlation

data: ?iris[[1]] and iris[[3]]
t = 21.65, df = 148, p-value < 2.2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
?0.8270 0.9055
sample estimates:
? cor
0.8718

Above the p-value comes as '< 2.2e-16', while inspecting the object I
get a good old '0'.

x$p.value

[1] 0

I tried to inspect print.htest but couldn't find it. I also played
with format, round and the like to no avail. Any pointers?

Regards
Liviu


--
Do you know how to read?
http://www.alienetworks.com/srtest.cfm
http://goodies.xfce.org/projects/applications/xfce4-dict#speed-reader
Do you know how to write?
http://garbl.home.comcast.net/~garbl/stylemanual/e.htm#e-mail

is(x)

[1] "htest"

# take a look at     stats:::print.htest
format.pval(x$p.value)

[1] "< 2.22e-16"

Does that answer your question?

KK

On Mon, Oct 3, 2011 at 10:53 AM, Liviu Andronic
<landronimirc at gmail.com> wrote:

Dear all
How does print.htest display the p-value in scientific notation?

(x <- cor.test(iris[[1]], iris[[3]]))

_ _ _ _Pearson's product-moment correlation

data: _iris[[1]] and iris[[3]]
t = 21.65, df = 148, p-value < 2.2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
_0.8270 0.9055
sample estimates:
_ cor
0.8718

Above the p-value comes as '< 2.2e-16', while inspecting the object I
get a good old '0'.

x$p.value

[1] 0

I tried to inspect print.htest but couldn't find it. I also played
with format, round and the like to no avail. Any pointers?

Regards
Liviu


--
Do you know how to read?
http://www.alienetworks.com/srtest.cfm
http://goodies.xfce.org/projects/applications/xfce4-dict#speed-reader
Do you know how to write?
http://garbl.home.comcast.net/~garbl/stylemanual/e.htm#e-mail

base::format.pval(x$p.value)  ##Hmisc also has such a function

Isn't it true that 0 < 2.2e-16?

identical(x$p.value, 0)

Thanks all for your pointers. The following does trick:

base::format.pval(x$p.value)  ##Hmisc also has such a function

[1] "<2e-16"


On Mon, Oct 3, 2011 at 10:25 AM, Rolf Turner <rolf.turner at xtra.co.nz> wrote:

Isn't it true that 0 < 2.2e-16?

Yes, but it doesn't mean that the p-value actually hits absolute zero.
And cor.test, as Ted noticed, returns

identical(x$p.value, 0)

[1] TRUE

Not that this makes a great practical difference in my case, but I
would still prefer to print "<2e-16" in my Sweave document.

Regards
Liviu