SPSSX Discussion

documentation on choosing forms of scaling.

Classic

List

Threaded

10 messages Options

Art Kendall-2

documentation on choosing forms of scaling.

I recall seeing somewhere in SPSS documentation a large table the
crossed kinds of data by SPSS multidimensional scaling procedures.

Does anyone recall what that might be?

Art

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

Reutter, Alex

Re: documentation on choosing forms of scaling.

Art,

Are you thinking of the "Models for types of matrix input" table in the ALSCAL chapter of the syntax reference? It's in the section called "Specification of Analyses" with several other related tables.

Alex

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Art Kendall
Sent: Monday, February 04, 2008 3:24 PM
To: [hidden email]
Subject: documentation on choosing forms of scaling.

I recall seeing somewhere in SPSS documentation a large table the
crossed kinds of data by SPSS multidimensional scaling procedures.

Does anyone recall what that might be?

Art

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

Manmit Shrimali-2

data change

Hi All:

I understand that spss does not faciliate using two weight variables however I am in situation where I need to use two weight variables. Below is an example:

Q1: How many cold drink you drink in a year? (answer in range of 0-500).
Q2. Of those (q1) cold drinks how many were the following? (product a to d summing to q1).

Now I have to use q1 as weight as well # given to product a of q2. Any idea how should I do it.

Thanks,
MS

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

ViAnn Beadle

Re: data change

Can you give us an example of what the weight value would be for a given
case. Why do you want to weight your file in the 1st place?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Manmit Shrimali
Sent: Tuesday, February 05, 2008 9:40 AM
To: [hidden email]
Subject: data change

Hi All:

I understand that spss does not faciliate using two weight variables however
I am in situation where I need to use two weight variables. Below is an
example:

Q1: How many cold drink you drink in a year? (answer in range of 0-500).
Q2. Of those (q1) cold drinks how many were the following? (product a to d
summing to q1).

Now I have to use q1 as weight as well # given to product a of q2. Any idea
how should I do it.

Thanks,
MS

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

Manmit Shrimali-2

Re: data change

I apologise for not giving full information. I have to generate mean of attributes and several other questions but the data should be weighted by q1 and q2(product a). I am not sure what you mean by weight value?

-----Original Message-----
From: SPSSX(r) Discussion on behalf of ViAnn Beadle
Sent: Tue 2/5/2008 10:06 PM
To: [hidden email]
Cc:
Subject: Re: data change

Can you give us an example of what the weight value would be for a given
case. Why do you want to weight your file in the 1st place?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Manmit Shrimali
Sent: Tuesday, February 05, 2008 9:40 AM
To: [hidden email]
Subject: data change

Hi All:

I understand that spss does not faciliate using two weight variables however
I am in situation where I need to use two weight variables. Below is an
example:

Q1: How many cold drink you drink in a year? (answer in range of 0-500).
Q2. Of those (q1) cold drinks how many were the following? (product a to d
summing to q1).

Now I have to use q1 as weight as well # given to product a of q2. Any idea
how should I do it.

Thanks,
MS

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

I

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

Art Kendall

Re: documentation on choosing forms of scaling.

In reply to this post by Reutter, Alex

Exactly.

Thank you.

Art

Reutter, Alex wrote:

> Art,
>
> Are you thinking of the "Models for types of matrix input" table in the ALSCAL chapter of the syntax reference? It's in the section called "Specification of Analyses" with several other related tables.
>
> Alex
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Art Kendall
> Sent: Monday, February 04, 2008 3:24 PM
> To: [hidden email]
> Subject: documentation on choosing forms of scaling.
>
> I recall seeing somewhere in SPSS documentation a large table the
> crossed kinds of data by SPSS multidimensional scaling procedures.
>
>
> Does anyone recall what that might be?
>
> Art
>
> =====================
> 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
>
>
>

Art Kendall
Social Research Consultants

ViAnn Beadle

Re: data change

In reply to this post by Manmit Shrimali-2

You can only have a single weight at any one time so what would that weight
be given values of q1 and q2? Give us an example.

-----Original Message-----
From: Manmit Shrimali [mailto:[hidden email]]
Sent: Tuesday, February 05, 2008 9:55 AM
To: ViAnn Beadle; [hidden email]
Subject: RE: Re: data change

I apologise for not giving full information. I have to generate mean of
attributes and several other questions but the data should be weighted by q1
and q2(product a). I am not sure what you mean by weight value?

-----Original Message-----
From: SPSSX(r) Discussion on behalf of ViAnn Beadle
Sent: Tue 2/5/2008 10:06 PM
To: [hidden email]
Cc:
Subject: Re: data change

Can you give us an example of what the weight value would be for a given
case. Why do you want to weight your file in the 1st place?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Manmit Shrimali
Sent: Tuesday, February 05, 2008 9:40 AM
To: [hidden email]
Subject: data change

Hi All:

I understand that spss does not faciliate using two weight variables however
I am in situation where I need to use two weight variables. Below is an
example:

Q1: How many cold drink you drink in a year? (answer in range of 0-500).
Q2. Of those (q1) cold drinks how many were the following? (product a to d
summing to q1).

Now I have to use q1 as weight as well # given to product a of q2. Any idea
how should I do it.

Thanks,
MS

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

I

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

Manmit Shrimali-2

Re: data change

In reply to this post by Manmit Shrimali-2

I am not sure sir how the weight value be. But whatever the value it
should incorporate q1 and q2(a). I was thinking to divide q2(a)/q1 and
use the result as weight variable however I am not sure if I am really
using q1 as weight.

There is q3 question that asks out of q2(a) how many were diet and
caffeine drinks. When I take mean of q3 I want to apply weight of q1 and
q2(a) i.e. total drinks consumed and drinks consumed of product a.

I hope I am able to provide the required info.

Thanks very much for inputs so far.

Manmit Shrimali | Engagement Manager
marketRx, a Cognizant Company
t: +91.124.4160800 ext:235 | m: +91.9911205354
e: [hidden email]
www.marketrx.com | www.cognizant.com
-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
ViAnn Beadle
Sent: Tuesday, February 05, 2008 10:06 PM
To: [hidden email]
Subject: Re: data change

Can you give us an example of what the weight value would be for a given
case. Why do you want to weight your file in the 1st place?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Manmit Shrimali
Sent: Tuesday, February 05, 2008 9:40 AM
To: [hidden email]
Subject: data change

Hi All:

I understand that spss does not faciliate using two weight variables
however
I am in situation where I need to use two weight variables. Below is an
example:

Q1: How many cold drink you drink in a year? (answer in range of 0-500).
Q2. Of those (q1) cold drinks how many were the following? (product a to
d
summing to q1).

Now I have to use q1 as weight as well # given to product a of q2. Any
idea
how should I do it.

Thanks,
MS

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

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

Art Kendall-2

Re: data change

I am not sure whether or not you mean "weight" in the sense of weighting
CASES to adjust summary statistics or not.
IF NOT:
Perhaps you mean that you want to obtain summary stats by AGGREGATE.
COMPUTE CONSTANT=1.
AGGREGATE OUTFILE= */BREAK=CONSTANT
/SUM_ALL_DRINKS = SUM(Q1)
/SUM_PRODUCT_A = SUM(Q2_A)
/ = SUM(Q3)
/KOUNT=N.
list.
* find proportions.
compute p_dc_all = SUM_A_DIET_CAFF / SUM_ALL_DRINKS.
compute p_dc_ProdA = SUM_A_DIET_CAFF / SUM_PRODUCT_A.
list.

The above is example syntax

Save all your current work, then open a new instance of SPSS. Make sure
that you put warnings, etc. into the output file. <edit> <options>
<viewer>. Open your input file. Cut-and-paste then run the syntax.
Does this do what you want? If not please restate your question in more
detail.
Perhaps post a small data set with variables Q1 Q2_a Q3 and "want" for a
few cases.

Manmit Shrimali wrote:

> I am not sure sir how the weight value be. But whatever the value it
> should incorporate q1 and q2(a). I was thinking to divide q2(a)/q1 and
> use the result as weight variable however I am not sure if I am really
> using q1 as weight.
>
> There is q3 question that asks out of q2(a) how many were diet and
> caffeine drinks. When I take mean of q3 I want to apply weight of q1 and
> q2(a) i.e. total drinks consumed and drinks consumed of product a.
>
> I hope I am able to provide the required info.
>
> Thanks very much for inputs so far.
>
> Manmit Shrimali | Engagement Manager
> marketRx, a Cognizant Company
> t: +91.124.4160800 ext:235 | m: +91.9911205354
> e: [hidden email]
> www.marketrx.com | www.cognizant.com
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
> ViAnn Beadle
> Sent: Tuesday, February 05, 2008 10:06 PM
> To: [hidden email]
> Subject: Re: data change
>
> Can you give us an example of what the weight value would be for a given
> case. Why do you want to weight your file in the 1st place?
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
> Manmit Shrimali
> Sent: Tuesday, February 05, 2008 9:40 AM
> To: [hidden email]
> Subject: data change
>
> Hi All:
>
> I understand that spss does not faciliate using two weight variables
> however
> I am in situation where I need to use two weight variables. Below is an
> example:
>
> Q1: How many cold drink you drink in a year? (answer in range of 0-500).
> Q2. Of those (q1) cold drinks how many were the following? (product a to
> d
> summing to q1).
>
> Now I have to use q1 as weight as well # given to product a of q2. Any
> idea
> how should I do it.
>
> Thanks,
> MS
>
> =====================
> 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
>
> =====================
> 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
>
>
>

Manmit Shrimali-2

Re: data change

Yes, I mean weighting cases for summary statistics. Below is the sample dataset. Sum(q2a,q2b,q2c)=q1. Sum(q3a,q3b)=q2a. For summary statistics I want to take mean of q3a and q3b but use case weight of q1 and q2a.

ID,Q1,Q2A,Q2B,Q2C,Q3A,Q3B
1,100,50,30,20,30,20,
2,250,100,100,50,50,50
3,50,5,45,0,2,3
4,10,5,2,3,2,3,2
5,300,200,50,50,100,50,50

Hope this helps.

-----Original Message-----
From: SPSSX(r) Discussion on behalf of Art Kendall
Sent: Wed 2/6/2008 7:01 PM
To: [hidden email]
Cc:
Subject: Re: data change

I am not sure whether or not you mean "weight" in the sense of weighting
CASES to adjust summary statistics or not.
IF NOT:
Perhaps you mean that you want to obtain summary stats by AGGREGATE.
COMPUTE CONSTANT=1.
AGGREGATE OUTFILE= */BREAK=CONSTANT
/SUM_ALL_DRINKS = SUM(Q1)
/SUM_PRODUCT_A = SUM(Q2_A)
/ = SUM(Q3)
/KOUNT=N.
list.
* find proportions.
compute p_dc_all = SUM_A_DIET_CAFF / SUM_ALL_DRINKS.
compute p_dc_ProdA = SUM_A_DIET_CAFF / SUM_PRODUCT_A.
list.

The above is example syntax

Save all your current work, then open a new instance of SPSS. Make sure
that you put warnings, etc. into the output file. <edit> <options>
<viewer>. Open your input file. Cut-and-paste then run the syntax.
Does this do what you want? If not please restate your question in more
detail.
Perhaps post a small data set with variables Q1 Q2_a Q3 and "want" for a
few cases.

Manmit Shrimali wrote:

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