about creating a database

[Rodrigo Briceño]

Dear SPSS friends.

 

Problem: I’m trying to calculate the percentage of people who declared (on a
survey) to have paid for health services. The problem is that not all the
people reported payments, so when I calculate the frequencies (weighted) I
do not get the total amount of people for that country. This is caused
because members who did not pay at all are excluded from the DB. I know how
much households are and how many members are in each household. The idea to
solve this problem will be to have a full database with all households have
all their members as lines of the file, no matter if they paid or not for
health services.

 

 

Solution that I’m thinking how to do it in SPSS:

 

I want to create a new database which have on each line each member of the
household as new line.

For ex if HH1= 4 members, then the new DB will have four lines for this HH.

 

Does anybody could help me? I can send the file with the Households and
number of people. Thanks.

__________________________________________________________________

Rodrigo Briceño
Project Manager
Sanigest Internacional

[phone] ext. 113   Oficina Costa Rica
[phone]                   Fax
[phone]                   Celular
 <mailto:[hidden email]> [hidden email]
 <http://www.sanigest.com/> www.sanigest.com

MSN:  <mailto:[hidden email]> [hidden email]
SKYPE: rbriceno1087

_____________________

This communication contains legal information which is privileged and
confidential. It is for the exclusive use of the address and distribution,
dissemination, copying or use by others is strictly prohibited. If you have
received this communication by error, please delete the original message and
e-mail us.


Esta comunicación contiene información legal privilegiada y confidencial
para el uso exclusivo del destinatario. La distribución, diseminación, copia
u otro uso por terceras personas es estrictamente prohibida. Si usted ha
recibido esta comunicación por error, le rogamos borrar el mensaje original
y comunicárnoslo a esta misma dirección.

 

====================To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Richard Ristow]

At 05:26 PM 10/19/2007, Rodrigo Briceno wrote:

>Problem: I'm trying to calculate the percentage of people who declared
>(on a survey) to have paid for health services. The problem is that
>not all the people reported payments, so when I calculate the
>frequencies (weighted) I do not get the total amount of people for
>that country. This is caused because members who did not pay at all
>are excluded from the DB.

That means, or seems to mean, that you need somehow to *not* exclude
them from the database.

I don't know how your database was built. Some data collection
protocols never 'see' the people who haven't done, or paid, or
whatever, the activity being studied.

There's nothing to be done unless you have a master database of all the
people. If you do have such a database, and you merge it with the data
collected on the activity, people who didn't participate in the
activity will have missing data. This is an instance where 'missing' is
a 0 value, rather than an unknown value, and it's proper to use RECODE
those missing values to 0.

Does that start to help?

>I know how much households are and how many members are in each
>household. The idea to solve this problem will be to have a full
>database with all households have all their members as lines of the
>file, no matter if they paid or not for health services.

Right. That's often useful. It's called 'unrolling'. The original form,
with all household members on the same record, is called 'wide'
organization; having "all households members as lines of the file" is
called 'long' organization, and is very often a good idea.

In SPSS,

>I want to create a new database which have on each line each member of
>the household as new line. For ex if HH1= 4 members, then the new DB
>will have four lines for this HH.

To point you the right direction: the SPSS command VARSTOCASES does
precisely this.

It may be easiest to run VARSTOCASES from the menus. To do so,

a.) Load your data (BUT MAKE SURE YOU HAVE A COPY THAT'S SAVED
PERMANENTLY)

b.) From the menus, choose Data > Restructure...   On the first panel,
choose "Restructure selected variables into cases", and go on from
there, following the directions.

See how this goes, and post again if you have difficulties.

-Best wishes,
  Richard

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD