On Sat, May 16, 2009 at 10:15:50PM +0000, Ben Pfaff wrote:
Follow-up Comment #4, patch #6829 (project pspp):
Under Hypothesis Testing:
>+or does the mean of a dataset significantly differ from a particular
I would write "whether" in place of "does", "differs" in place of
"differ".
You're right. Then the tense would be consistent with that of the
previous clause.
I notice that @footnote is not used in quite the right way in a few
places.
In particular, there should be no space between the text and the @footnote
command; otherwise there is a space between the text and the footnote
marker
in the output, which is not the usual style.
OK. I'll fix that.
>+...@footnote{this example assumes that is it already proven that @var{B}
is
>+not greater than @var{A}.}
Is this correct? I would have guessed that it assumes that it assumes that
it is *not* already proven.
There are three possibilities: A < B, A == B, or A > B. Often,
however, the event A < B common sense tells us cannot be true, and
the researcher can dismiss this possibility. If we know that A < B
(or B < A) cannot be true, then a one tailed test can be used instead
of a two tailed test, thus doubling the power of the test.
For example, in an experiment involving animals exposed to some
radiation treatment, A might be the mean radiation from the cells of
the exposed animals, and B the mean of the cells from the control group.
Regardless of whether I'm right about that, "is it" => "it is".
I'll fix that.
As I continue to read through examples, I find myself wondering whether
there
is value in inserting the @prompt{PSPP>} prefixes. Since these appear on
(almost) every line, they don't really teach the reader very much, and they
make it more difficult to cut-and-paste from the manual.
You could well be right. Maybe it only needs the prompt for the first
few examples.
J'
--
PGP Public key ID: 1024D/2DE827B3
fingerprint = 8797 A26D 0854 2EAB 0285 A290 8A67 719C 2DE8 27B3
See http://pgp.mit.edu or any PGP keyserver for public key.
signature.asc
Description: Digital signature
_______________________________________________ pspp-dev mailing list [email protected] http://lists.gnu.org/mailman/listinfo/pspp-dev
