Hi there,
I was wondering if you could help me to write the following procedure. I
need to plot x against y.
The x is read directly from a file. The y is delta from power.t.test:
y - as.vector(power.t.test(n=4, sd =z, power = 0.8)$delta), where z
values are also read from the file.
Thank you for
power.t.test() requires a standard deviation as input, but for a two sample
test, I do not understand what is required. Is it the standard deviation of
the means (standard error), or of the combined sample?
thanks,
Hank Stevens
Martin Henry H. Stevens, Assistant Professor
338 Pearson Hall
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Hank Stevens
Sent: Monday, March 31, 2003 2:43 PM
To: [EMAIL PROTECTED]
Subject: [R] power.t.test
power.t.test() requires a standard deviation as input, but for
a two sample
test, I do not understand
Hi - Is it possible to use the power.t.test function in a scenario where the
number of observations in each group is different?
Thanks
--
Andrew Swan
CSIRO Livestock Industries
Armidale 2350 Australia
ph. 02 6776 1377
fax. 02 6776 1408
email: [EMAIL PROTECTED]
[EMAIL PROTECTED] writes:
Hi - Is it possible to use the power.t.test function in a scenario where the
number of observations in each group is different?
No. It's not rocket science to modify the p.body expression, though.
The tricky bit is what to do instead of solve for n.
--
O__
[EMAIL PROTECTED] writes:
Hi - Is it possible to use the power.t.test function in a scenario where the
number of observations in each group is different?
No. It's not rocket science to modify the p.body expression, though.
The tricky bit is what to do instead of solve for n.
One
