Hierarchical (moderated) regression and interaction term

Hello all, 

I need to use hierarchical multiple regression, and to do so, I was suggested creating interaction terms.  I looked up Pallant (2010), but Pallant doesn't mention how to create interaction terms. Could anybody advise? I don't use syntax, so appreciate it if you let me know what to do without using syntax. I assume I go to Transform --> Compute Variables. 

Thanks, 

Tamaki 

[Bruce Weaver]

You need to provide more information about the model.  Specifically, how many steps do you have in your hierarchy?  Which variables are included in the first step, and which are added on subsequent steps?

*If* the interaction terms you mention involve two scaled variables, you need to compute the products of those two variables.  If the interactions involve indicator-coded categorical variables, you'll need multiple products (the number being the product of the two df).

Re syntax, I suggest you start learning how to use it.  A good first step is exiting the GUI menus via PASTE rather than OKAY.  You can search the archives of this list for one some of Art Kendall's good "soapbox" posts on the benefits of using syntax.

HTH.

Onishi, Tamaki wrote

Hello all,

I need to use hierarchical multiple regression, and to do so, I was suggested creating interaction terms.  I looked up Pallant (2010), but Pallant doesn't mention how to create interaction terms. Could anybody advise? I don't use syntax, so appreciate it if you let me know what to do without using syntax. I assume I go to Transform --> Compute Variables.

Thanks,
Tamaki

[Jon K Peck]

You might be interested in the SPSSINC CREATE DUMMIES extension command.  It is installed as part of the Python Essentials available from the SPSS Community website (www.ibm.com/developerworks/spssdevcentral).  However, there is a newer version available in the Extension Commands collection on that site that handles up to three-way interactions.

CREATE DUMMIES uses the variables' measurement levels to figure out what dummies to create.

BTW, "I don't use syntax" isn't really true.  Every dialog box in Statistics generates syntax in order to carry out the request.  The Paste button shows this to you.

HTH,

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: [phone]




From:        Bruce Weaver <[hidden email]>
To:        [hidden email]
Date:        07/01/2012 06:50 AM
Subject:        Re: [SPSSX-L] Hierarchical (moderated) regression and interaction              term
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

You need to provide more information about the model.  Specifically, how many
steps do you have in your hierarchy?  Which variables are included in the
first step, and which are added on subsequent steps?

*If* the interaction terms you mention involve two scaled variables, you
need to compute the products of those two variables.  If the interactions
involve indicator-coded categorical variables, you'll need multiple products
(the number being the product of the two df).

Re syntax, I suggest you start learning how to use it.  A good first step is
exiting the GUI menus via PASTE rather than OKAY.  You can search the
archives of this list for one some of Art Kendall's good "soapbox" posts on
the benefits of using syntax.

HTH.


Onishi, Tamaki wrote
>
> Hello all,
>
> I need to use hierarchical multiple regression, and to do so, I was
> suggested creating interaction terms.  I looked up Pallant (2010), but
> Pallant doesn't mention how to create interaction terms. Could anybody
> advise? I don't use syntax, so appreciate it if you let me know what to do
> without using syntax. I assume I go to Transform --> Compute Variables.
>
> Thanks,
> Tamaki
>


-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Hierarchical-moderated-regression-and-interaction-term-tp5713928p5713931.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

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