pvalue calculate

Hi Mary,

I think the good old t-test is what you want:

x <- sample(1:50)
  
t.test(x, mu = 300)

gives:
         One Sample t-test

data:  x
t = -133.2, df = 49, p-value < 0.00000000000000022
alternative hypothesis: true mean is not equal to 300
95 percent confidence interval:
  21.36 29.64
sample estimates:
mean of x
      25.5

Best,
Henrik


Am 22.07.2012 21:37, schrieb Mary Kindall:

I have a value
a=300

observation (x) = sample(1:50)

How to find a p-value from this. I need to show that "a" is different fom
mean(x).
Thanks

Dipl. Psych. Henrik Singmann
PhD Student
Albert-Ludwigs-Universit?t Freiburg
http://www.psychologie.uni-freiburg.de/Members/singmann

HI,
Probably ?pnorm
x1<-mean(x)
x1
[1] 25.5

pnorm(25.5,mean=300)

[1] 0


A.K.







----- Original Message -----
From: Mary Kindall <mary.kindall at gmail.com>
To: r-help at r-project.org
Cc: 
Sent: Sunday, July 22, 2012 3:37 PM
Subject: [R] pvalue calculate

I have a value
a=300

observation (x) = sample(1:50)

How to find a p-value from this. I need to show that "a" is different fom
mean(x).
Thanks

-------------
Mary Kindall
Yorktown Heights, NY
USA

??? [[alternative HTML version deleted]]

______________________________________________
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.

I have a value
a=300

observation (x) = sample(1:50)

How to find a p-value from this. I need to show that "a" is different fom
mean(x).
Thanks

This question doesn't really make sense.  sample(1:50) gives you the 
same sample as 1:50 does, just in a different order.  So the mean is 
guaranteed to be 25.5, which is obviously different from 300.

If you really did have a random sample from some unknown distribution 
and you wanted to test whether the mean of that distribution is 
different from 300, then Henrik's suggestion is reasonable for most 
distributions.

Duncan Murdoch

Hi Mary,

I think the good old t-test is what you want:

Maybe, but calculating p-values with absolutely no consideration
of assumptions is pure folly. It may well be that Mary has some
assumptions in mind, but the way the question was posed does not
instil confidence in that assumption.

Peter Ehlers

x <- sample(1:50)

t.test(x, mu = 300)

gives:
          One Sample t-test

data:  x
t = -133.2, df = 49, p-value < 0.00000000000000022
alternative hypothesis: true mean is not equal to 300
95 percent confidence interval:
   21.36 29.64
sample estimates:
mean of x
       25.5

Best,
Henrik


Am 22.07.2012 21:37, schrieb Mary Kindall:

I have a value
a=300

observation (x) = sample(1:50)

How to find a p-value from this. I need to show that "a" is different fom
mean(x).
Thanks