Date: Fri, 23 Jul 2004 08:52:36 -0300
Reply-To: Hector Maletta <email@example.com>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Hector Maletta <firstname.lastname@example.org>
Subject: Re: descriptive statistics and FREQUENCIES, difference
Content-Type: text/plain; charset="us-ascii"
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]
> On Behalf Of Russ Sanders
> Sent: Friday, July 23, 2004 2:06 AM
> To: SPSSX-L@LISTSERV.UGA.EDU
> Subject: Re: descriptive statistics and FREQUENCIES, difference
> On Thu, 22 Jul 2004 06:00:07 -0700, Cady Wan <email@example.com> wrote:
> >Dear list,
> >I have quite a simple question, I think.
> >I have a variable: var which is an integer, e.g.
> >number of population. I used descriptive statistics
> >and frequencies to calculate the sum of var, after I
> >copied the both outputs in Excel, I noticed that the
> >output of descriptiv in Excel is a decimal number
> >while fre. shows the sum as an integer, does anyone
> >know the reason? Thanks!
> frequencies is a count of each unique value in a variable.
> If "A" occurs 50 times in your variable then frequencies will
> show A = 50.
Not quite so. Frequencies are actually a count of cases for each unique
value in a variable, multiplied by the hidden system variable $WEIGHT, which
equals 1 by default but can be assigned the value of any variable in the
file through the WEIGHT BY command. If the weights are fractional, the raw
weighted frequency will also be fractional. SPSS rounds it to the nearest
integer when producing frequency tables. The fractional values, however,
crop up in other ways.