collapsing groups

[Genevieve Thompson]

 

Hi,

I have a list of job classes in my data and would like to break it down
into groups. For example, I have about 200 jobs in my list called nurse,
seamstress, driver etc. I would like to create a total of 5 groups which
collapse these classifications. How do I do this so that when I build a
chart, it doesn't list the jobs but lists the various groups.

 

Thanks.

 

Genevieve Thompson

Policy and Program Analyst

 

OANHSS

Suite 700 - 7050 Weston Rd.

Woodbridge, ON  L4L 8G7

Tel:  [phone] x 241 Fax:  [phone]

[hidden email] <mailto:[hidden email]>

www.oanhss.org <http://www.oanhss.org/>

 

OANHSS Upcoming Events

 

Diversity in Action - 3 Regional Sessions


Bullying in the Workplace - 3 Regional Sessions


HR Management Series - Meeting the Challenges of Managing Your Workforce
Four one-day sessions focused on the core competencies of human resource
management

 

 

For dates and registration information go to www.oanhss.org

 

------------------------------------------------------------------------
------------------------------------------------------------------------

This electronic communication is from the Ontario Association of
Non-Profit Homes and Services for Seniors. It is for the intended
recipient only and may contain confidential and/or privileged
information. Any review, retransmission, dissemination or other use of,
or taking of any action in reliance upon this information, by persons or
entities other than the intended recipient, is prohibited. If you
received this in error, please contact the sender and delete the
material from your computer.

 

 

====================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]

Check out RECODE and recode the values into a new variable.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Genevieve Thompson
Sent: Monday, September 15, 2008 2:29 PM
To: [hidden email]
Subject: collapsing groups



Hi,

I have a list of job classes in my data and would like to break it down
into groups. For example, I have about 200 jobs in my list called nurse,
seamstress, driver etc. I would like to create a total of 5 groups which
collapse these classifications. How do I do this so that when I build a
chart, it doesn't list the jobs but lists the various groups.



Thanks.



Genevieve Thompson

Policy and Program Analyst



OANHSS

Suite 700 - 7050 Weston Rd.

Woodbridge, ON  L4L 8G7

Tel:  [phone] x 241 Fax:  [phone]

[hidden email] <mailto:[hidden email]>

www.oanhss.org <http://www.oanhss.org/>



OANHSS Upcoming Events



Diversity in Action - 3 Regional Sessions


Bullying in the Workplace - 3 Regional Sessions


HR Management Series - Meeting the Challenges of Managing Your Workforce
Four one-day sessions focused on the core competencies of human resource
management





For dates and registration information go to www.oanhss.org



------------------------------------------------------------------------
------------------------------------------------------------------------

This electronic communication is from the Ontario Association of
Non-Profit Homes and Services for Seniors. It is for the intended
recipient only and may contain confidential and/or privileged
information. Any review, retransmission, dissemination or other use of,
or taking of any action in reliance upon this information, by persons or
entities other than the intended recipient, is prohibited. If you
received this in error, please contact the sender and delete the
material from your computer.





=======
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

[Drake, Lorin]

Does anyone know how to create a dependent variable out of >1 question
on a survey?

 

1.  Overall satisfaction with product

2.  Likelihood to recommend product

3.  Likelihood to re-purchase product

 

All three questions are on a 5 pt. scale.

 

I have previously only used (1) as a DV but want to use all three as a
loyalty metric - calling it "Loyalty."
I'd like to use this DV in my regression model to find out what
attributes on the survey predict customer loyalty.

 

What's the most efficient way to do it in SPSS?

FYI: This is for a business application and not an academic one.

 

Thanks in advance,

Lorin.

 

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

[Jignesh Sutar]

Hi Lorin,

There are a number of ways achieving this.

Simplest form would be to take an average score across the 3 measurements.

Other alternatives could be to take an weighted average score. You may
attribute a higher weight to one of the three attributes than another if you
believe it to be more influential in your loyalty metric.)

One final alternative I can suggest is it to create an average of all the
variables and then divide each respondent by the mean score of your loyalty
metric. By doing this loyalty scores of greater than one represent those
performing above average on the loyalty metric and those below one
performing below average. Please note this is just a simple transformation
in your dependent, dividing by a constant, so will yield same results in
regression analysis as taking a simple average.

Hope that helps

Jignesh
2008/9/15 Drake, Lorin <[hidden email]>

> Does anyone know how to create a dependent variable out of >1 question
> on a survey?
>
>
>
> 1.  Overall satisfaction with product
>
> 2.  Likelihood to recommend product
>
> 3.  Likelihood to re-purchase product
>
>
>
> All three questions are on a 5 pt. scale.
>
>
>
> I have previously only used (1) as a DV but want to use all three as a
> loyalty metric - calling it "Loyalty."
> I'd like to use this DV in my regression model to find out what
> attributes on the survey predict customer loyalty.
>
>
>
> What's the most efficient way to do it in SPSS?
>
> FYI: This is for a business application and not an academic one.
>
>
>
> Thanks in advance,
>
> Lorin.
>
>
>
> 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

[Hesham Abdel-Meguid Abdalla]

Dear All
I think there is one more alternative, you can use Factor
analysis to create one factor from the three variables. So, you can use
the resulted score of this factor as DV in your regression model.

Hi Lorin,

There are a number of ways achieving this.

Simplest form would be to take an average score across the 3
measurements.

Other alternatives could be to take an weighted
average score. You may
attribute a higher weight to one of the three
attributes than another if
you
believe it to be more
influential in your loyalty metric.)

One final alternative I
can suggest is it to create an average of all the
variables and then
divide each respondent by the mean score of your
loyalty
metric. By doing this loyalty scores of greater than one represent those

performing above average on the loyalty metric and those below one

performing below average. Please note this is just a simple
transformation
in your dependent, dividing by a constant, so will
yield same results in
regression analysis as taking a simple
average.

Hope that helps

Jignesh
2008/9/15
Drake, Lorin <[hidden email]>

> Does
anyone know how to create a dependent variable out of >1 question
> on a survey?
>
>
>
> 1. Overall
satisfaction with product
>
> 2. Likelihood to recommend
product
>
> 3. Likelihood to re-purchase product
>
>
>
> All three questions are on a 5 pt.
scale.
>
>
>
> I have previously only
used (1) as a DV but want to use all three as a
> loyalty metric
- calling it "Loyalty."
> I'd like to use this DV in my
regression model to find out what
> attributes on the survey
predict customer loyalty.
>
>
>
>
What's the most efficient way to do it in SPSS?
>
> FYI:
This is for a business application and not an academic one.
>
>
>
> Thanks in advance,
>
>
Lorin.
>
>
>
> 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
_ _ _ _ _ _ _ _ _
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
_
This
message has been scanned by AUN Spam E-mail Filter and Virus
detection software.




--
Hesham
Abdel-Meguid
Statistics Dept.
Faculty of Commerce
Assiut
University

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

[Drake, Lorin]

Thanks, everyone - great suggestions.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Hesham Abdel-Meguid Abdalla
Sent: Tuesday, September 16, 2008 5:24 AM
To: [hidden email]
Subject: Re: dependent variable question

Dear All
I think there is one more alternative, you can use Factor
analysis to create one factor from the three variables. So, you can use
the resulted score of this factor as DV in your regression model.

Hi Lorin,

There are a number of ways achieving this.

Simplest form would be to take an average score across the 3
measurements.

Other alternatives could be to take an weighted
average score. You may
attribute a higher weight to one of the three
attributes than another if
you
believe it to be more
influential in your loyalty metric.)

One final alternative I
can suggest is it to create an average of all the
variables and then
divide each respondent by the mean score of your
loyalty
metric. By doing this loyalty scores of greater than one represent those

performing above average on the loyalty metric and those below one

performing below average. Please note this is just a simple
transformation
in your dependent, dividing by a constant, so will
yield same results in
regression analysis as taking a simple
average.

Hope that helps

Jignesh
2008/9/15
Drake, Lorin <[hidden email]>

> Does
anyone know how to create a dependent variable out of >1 question
> on a survey?
>
>
>
> 1. Overall
satisfaction with product
>
> 2. Likelihood to recommend
product
>
> 3. Likelihood to re-purchase product
>
>
>
> All three questions are on a 5 pt.
scale.
>
>
>
> I have previously only
used (1) as a DV but want to use all three as a
> loyalty metric
- calling it "Loyalty."
> I'd like to use this DV in my
regression model to find out what
> attributes on the survey
predict customer loyalty.
>
>
>
>
What's the most efficient way to do it in SPSS?
>
> FYI:
This is for a business application and not an academic one.
>
>
>
> Thanks in advance,
>
>
Lorin.
>
>
>
> 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
_ _ _ _ _ _ _ _ _
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
_
This
message has been scanned by AUN Spam E-mail Filter and Virus
detection software.




--
Hesham
Abdel-Meguid
Statistics Dept.
Faculty of Commerce
Assiut
University

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