SPSSX Discussion

data replication

Classic

List

Threaded

4 messages Options

David Lindsay-4

data replication

I am creating some dummy data so that I can run some examples
of multivariate analyses for a teach-in that I am running. I
have a small amount of data (100 cases) that I need to expand
into a bigger database (500 cases). The 100 case data set shows
some interesting patterns that I want to replicate in the
bigger dataset.
In other words I can see that the data follows a certain
distribution. Is it possible to fit a distribtion to the data
and then use that relationship to generate some more data?

Regards
--
David Lindsay
+44 118 940 3086
+44 78 9996 3336(mobile - new from 7 July)

=====================
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

Oliver, Richard

Re: data replication

You could just weight the data:

compute weightvar=5.
weight by weightvar.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of David Lindsay
Sent: Monday, January 26, 2009 10:20 AM
To: [hidden email]
Subject: data replication

I am creating some dummy data so that I can run some examples
of multivariate analyses for a teach-in that I am running. I
have a small amount of data (100 cases) that I need to expand
into a bigger database (500 cases). The 100 case data set shows
some interesting patterns that I want to replicate in the
bigger dataset.
In other words I can see that the data follows a certain
distribution. Is it possible to fit a distribtion to the data
and then use that relationship to generate some more data?

Regards
--
David Lindsay
+44 118 940 3086
+44 78 9996 3336(mobile - new from 7 July)

=====================
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

=====================
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

David Lindsay-4

Re: data replication

Yes, I could do that and that would answer my query. Is it
possible to do what I was aiming to do?

Regards

>
> You could just weight the data:
>
> compute weightvar=5.
> weight by weightvar.
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On
> Behalf Of David Lindsay
> Sent: Monday, January 26, 2009 10:20 AM
> To: [hidden email]
> Subject: data replication
>
> I am creating some dummy data so that I can run some examples
> of multivariate analyses for a teach-in that I am running. I
> have a small amount of data (100 cases) that I need to expand
> into a bigger database (500 cases). The 100 case data set shows
> some interesting patterns that I want to replicate in the
> bigger dataset.
> In other words I can see that the data follows a certain
> distribution. Is it possible to fit a distribtion to the data
> and then use that relationship to generate some more data?
>
> Regards
> --
> David Lindsay
> +44 118 940 3086
> +44 78 9996 3336(mobile - new from 7 July)
>
> =====================
> 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
>

Albert-Jan Roskam

Re: data replication

Or copy the file onto itself, as in:
add files
/ file = 'c:/program files/spss/employee data.sav'
/ file = 'c:/program files/spss/employee data.sav'
/ file = 'c:/program files/spss/employee data.sav'
/ file = 'c:/program files/spss/employee data.sav'
/ file = 'c:/program files/spss/employee data.sav' .
save outfile = 'd:\fivefold.sav'.

Cheers!!
ALbert-Jan

----- Original Message ----
From: David Lindsay <[hidden email]>
To: [hidden email]
Sent: Tuesday, January 27, 2009 9:38:03 AM
Subject: Re: data replication

Yes, I could do that and that would answer my query. Is it
possible to do what I was aiming to do?

Regards

--
David Lindsay
Significantly Different Research
+44 118 940 3086
+44 78 9996 3336(mobile - new from 7 July)

=====================
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

=====================
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