Interaction

[Billy Thompson-2]

Hopefully some of you stats ‘gurus’ can help me solve my problem.

I have a project in which the PI is interested in the interaction effects
among certain variables and not the main effects.    The problem results
that when I run  the ‘full’ factorial model with all effects the
interaction effects are non significant and the main effects are
significant.  If I then remove the significant main effects the
interaction effects then become significant.

Is it appropriate to run the model with interaction effects only, thus
ignoring the main effects?

Thanks for your help,

Billy T

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

[Spousta Jan]

Hi Billy,

In general you cannot work in this way, I think. The interactions-only model has significant interactions not because the interactions are really "significant" in itself in the common meaning of the word, but because they contain a part of the information from the main effects.

Instead of the full model, try models with all main effects and one interaction, where you believe that the interaction may exist.

Best regards,

Jan


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Billy Thompson
Sent: Wednesday, July 29, 2009 1:59 PM
To: [hidden email]
Subject: Interaction

Hopefully some of you stats ‘gurus’ can help me solve my problem.

I have a project in which the PI is interested in the interaction effects
among certain variables and not the main effects.    The problem results
that when I run  the ‘full’ factorial model with all effects the interaction effects are non significant and the main effects are significant.  If I then remove the significant main effects the interaction effects then become significant.

Is it appropriate to run the model with interaction effects only, thus ignoring the main effects?

Thanks for your help,

Billy T

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



_____________
Tato zpráva a všechny připojené soubory jsou důvěrné a určené výlučně adresátovi(-ům). Jestliže nejste oprávněným adresátem, je zakázáno jakékoliv zveřejňování, zprostředkování nebo jiné použití těchto informací. Jestliže jste tento mail dostali neoprávněně, prosím, uvědomte odesilatele a smažte zprávu i přiložené soubory. Odesilatel nezodpovídá za jakékoliv chyby nebo opomenutí způsobené tímto přenosem.
�
Jste si jisti, že opravdu potřebujete vytisknout tuto zprávu a/nebo její přílohy? Myslete na přírodu.
�
�
This message and any attached files are confidential and intended solely for the addressee(s). Any publication, transmission or other use of the information by a person or entity other than the intended addressee is prohibited. If you receive this in error please contact the sender and delete the message as well as all attached documents. The sender does not accept liability for any errors or omissions as a result of the transmission.
�
Are you sure that you really need a print version of this message and/or its attachments? Think about nature.

-.- --

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

[SR Millis-3]

If you include interactions, you must include the main effects as well.

SR Millis


--- On Wed, 7/29/09, Spousta Jan <[hidden email]> wrote:

> From: Spousta Jan <[hidden email]>
> Subject: Re: Interaction
> To: [hidden email]
> Date: Wednesday, July 29, 2009, 8:12 AM
> Hi Billy,
>
> In general you cannot work in this way, I think. The
> interactions-only model has significant interactions not
> because the interactions are really "significant" in itself
> in the common meaning of the word, but because they contain
> a part of the information from the main effects.
>
> Instead of the full model, try models with all main effects
> and one interaction, where you believe that the interaction
> may exist.
>
> Best regards,
>
> Jan
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]]
> On Behalf Of Billy Thompson
> Sent: Wednesday, July 29, 2009 1:59 PM
> To: [hidden email]
> Subject: Interaction
>
> Hopefully some of you stats
> ‘gurus’ can help me solve my
> problem.
>
> I have a project in which the PI is interested in the
> interaction effects
> among certain variables and not the main effects.�
> �  The problem results
> that when I run�  the
> ‘full’ factorial model with
> all effects the interaction effects are non significant and
> the main effects are significant.�  If I then remove the
> significant main effects the interaction effects then become
> significant.
>
> Is it appropriate to run the model with interaction effects
> only, thus ignoring the main effects?
>
> Thanks for your help,
>
> Billy T
>
> =====================
> 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
>
>
>
> _____________
> Tato zpráva a všechny připojené soubory jsou
> důvěrné a ur�ené výlu�ně
> adresátovi(-ům). Jestliže nejste
> oprávněným adresátem, je zakázáno
> jakékoliv zveřejňování,
> zprostředkování nebo jiné použití
> těchto informací. Jestliže jste tento mail dostali
> neoprávněně, prosím, uvědomte odesilatele
> a smažte zprávu i přiložené soubory.
> Odesilatel nezodpovídá za jakékoliv chyby nebo
> opomenutí způsobené tímto přenosem.
> Â
> Jste si jisti, že opravdu potřebujete vytisknout
> tuto zprávu a/nebo její přílohy? Myslete na
> přírodu.
> Â
> Â
> This message and any attached files are confidential and
> intended solely for the addressee(s). Any publication,
> transmission or other use of the information by a person or
> entity other than the intended addressee is prohibited. If
> you receive this in error please contact the sender and
> delete the message as well as all attached documents. The
> sender does not accept liability for any errors or omissions
> as a result of the transmission.
> Â
> Are you sure that you really need a print version of this
> message and/or its attachments? Think about nature.
>
> -.- --
>
> =====================
> 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