Date: Sun, 29 Jul 2001 15:55:43 -0300
Reply-To: hmaletta@fibertel.com.ar
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Hector Maletta <hmaletta@FIBERTEL.COM.AR>
Subject: Re: Survey analysis
Content-Type: text/plain; charset=us-ascii
Christian:
Please clarify exactly what is the structure of your data file.
1. What does each record in your file (i.e. each row) represent: one
house in a particular year, one occurrence of the disease in a
particular house and year, or what?
2. Do you have only one file, or one file per year?
3. In case you have one record per house, and each indicates how many
occurrences there were in that house, what is your problem exactly? It
might be, for instance, that you want to know a way of obtaining the
total number of occurrences in all the houses, year by year, or the
total of the four years.
4. Are you interested in something else, besides knowing the total
number of occurrences of the disease? For instance, you might be
interested in analyzing the time trend of the occurrences from 1996 to
2000, or you may want to cross the frequency of disease with other
variables in the house (building materials, level of living, sanitation,
etc.).
5. You are interested in cases of malaria, but you say your file refers
to tuberculosis (TB). Clarify.
Please send a sample of rows and columns from your data file. Each row
is a "case" (may be one house, one person, one occurrence, whatever is
your unit of analysis), and each column is a "variable" (an item of
information about each unit).
Hope I'd be able to help when I know all this.
Hector Maletta
Universidad del Salvador
Buenos Aires, Argentina
Christian Bautista wrote:
>
> Hi everybody!!
>
> I would like to know what kind of analysis I must to use for analyzing this
> information.
>
> Period: 1996 to 2000
> Variable1: Houses
> Variable2: Nro de cases of malaria
>
> I have information of the number of cases (in this case: TB) per house and
> per month from 1996 to 2000.
>
> Thanks
>
> Christian Bautista,
> NAMRCD
| 
