WITHIN SUBJECTS ANOVA - HOW TO CHECK JUST MAIN EFFECTS IN SPSS

[blue]

Dear all! I have a problem with a within-subjects anova - language: english/spanish and word type: negative/neutral as within subjects factors.
The interaction is not significant, but word type is at the level of significance p=0.14 аnd language p=0.11 - so they show a tendency to be significant.

I got an advice to just check the effects of language and word type, without or omitting the interaction (since its 0 and it might be confounding),
but I do not seem to manage to figure it out how should I do this in SPSS?

(Not putting language*word type into the options-->display means for gives the same results, same F-tests and levels of significance).

 Thanks in advance!

[Bruce Weaver]

I assume you are estimating your model via GLM (Analyze > General Linear Model > Repeated Measures via the GUI).  That would explain why you are unable to omit the interaction term:  GLM includes it automatically.

To have more flexibility, I suggest you restructure your data from WIDE to LONG (look up VARSTOCASES, and see the examples).  Then use MIXED to estimate your model.  The Command Syntax Reference manual (aka the FM) includes an example of how to perform repeated measures ANOVA via MIXED.  

HTH.

blue wrote

Dear all! I have a problem with a within-subjects anova - language: english/spanish and word type: negative/neutral as within subjects factors.
The interaction is not significant, but word type is at the level of significance p=0.14 аnd language p=0.11 - so they show a tendency to be significant.

I got an advice to just check the effects of language and word type, without or omitting the interaction (since its 0 and it might be confounding),
but I do not seem to manage to figure it out how should I do this in SPSS?

(Not putting language*word type into the options-->display means for gives the same results, same F-tests and levels of significance).

 Thanks in advance!

[blue]

Dear Bruce,
thanks for the help.

If I understand it right,
your suggestion is (I will quote the commands from the book):

1. to copy this (but I do not know where):
CASESTOVARS
[/ID = varlist]
[/FIXED = varlist]
[/AUTOFIX = {YES**}]
{NO }
[/VIND [ROOT = rootname]]
[/COUNT = new variable ["label"]]
[/RENAME varname=rootname varname=rootname ...]
[/SEPARATOR = {"." }]
{“string”}]
[/INDEX = varlist]
[/GROUPBY = {VARIABLE**}]
{INDEX }]
[/DROP = varlist]

and then to

2. do this?

GENLINMIXED
[/DATA_STRUCTURE]
SUBJECTS = fieldName[*fieldName[*...]]
[REPEATED_MEASURES = fieldName[*fieldName[*...]]]
[GROUPING = fieldName[*fieldName[*...]]]
[COVARIANCE_TYPE = DIAGONAL** | AR1 | ARMA11 | COMPOUND_SYMMETRY | IDENTITY
TOEPLITZ | UNSTRUCTURED | VARIANCE_COMPONENTS]
/FIELDS
TARGET = fieldName
[TRIALS = {NONE** }]
{VALUE(number) }
{FIELD(fieldName)}
[ANALYSIS_WEIGHT = fieldName]
[OFFSET = {NONE** }]
{VALUE(number) }
{FIELD(fieldName)}
[/TARGET_OPTIONS]
[REFERENCE = value]
[DISTRIBUTION = NORMAL | BINOMIAL | MULTINOMIAL | GAMMA |
INVERSE_GAUSSIAN | NEGATIVE_BINOMIAL | POISSON]
[LINK = IDENTITY | CAUCHIT | CLOGLOG | LOG | LOGC | LOGIT | NLOGLOG | POWER | PROBIT ]
[LINK_PARAMETER = number]
[/FIXED]
[EFFECTS = effect [effect ...]]
[USE_INTERCEPT = TRUE** | FALSE]
[/RANDOM]
[EFFECTS = effect [effect ...]]
[USE_INTERCEPT = TRUE | FALSE**]
[SUBJECTS = fieldName[*fieldName[*...]]]
[GROUPING = fieldName[*fieldName[*...]]]
[COVARIANCE_TYPE = DIAGONAL | AR1 | ARMA11 | COMPOUND_SYMMETRY | IDENTITY
TOEPLITZ | UNSTRUCTURED | VARIANCE_COMPONENTS**]
[/RANDOM ...]
[/BUILD_OPTIONS]
[TARGET_CATEGORY_ORDER = {ASCENDING**}]
{DESCENDING }
{DATA }
[INPUTS_CATEGORY_ORDER = {ASCENDING**}]
{DESCENDING }
{DATA }
[MAX_ITERATIONS = {100** }]
{number}
[CONFIDENCE_LEVEL = {95** }]
{number}
[DF_METHOD = {RESIDUAL** }]
{SATTERTHWAITE}
[COVB = {MODEL**}]
{ROBUST }
[/EMMEANS
[TABLES = factor[*factor...]]
[COMPARE = factor]
[CONTRAST = {NONE** }]
{PAIRWISE }
{DEVIATION}
{SIMPLE }
[/EMMEANS...]
[/EMMEANS_OPTIONS]
[CONTROL = fieldName (number) [fieldName (number) ...]]
[SCALE = {ORIGINAL** }]
{TRANSFORMED}
[PADJUST = {LSD** }]
{SEQBONFERRONI}
{SEQSIDAK }
[/OUTFILE MODEL = 'file']
[/SAVE [PREDICTED_VALUES(fieldName)]]
[PREDICTED_PROBABILITY(rootname)]
[MAX_CATEGORIES({25** })]
{integer}
[CONFIDENCE(fieldName)]
[CONFIDENCE_METHOD({PREDICTEDPROBABILITY**})]
{PROBABILITYIMPROVEMENT}
[CONFIDENCE_INTERVALS(rootname)]
[PEARSON_RESIDUALS(fieldName)].

Or did I get it wrong?
But I do not know where I should paste these and whether I should make some changes in them?

Thanks again!

[David Marso]

Have you read up on VARSTOCASES and MIXED?
Your CASESTOVARS statement goes from long to wide.
Bruce's advice was to transform to LONG and use MIXED, not GENLINMIXED.

blue wrote

Dear Bruce,
thanks for the help.

If I understand it right,
your suggestion is (I will quote the commands from the book):

1. to copy this (but I do not know where):
CASESTOVARS
[/ID = varlist]
[/FIXED = varlist]
[/AUTOFIX = {YES**}]
{NO }
[/VIND [ROOT = rootname]]
[/COUNT = new variable ["label"]]
[/RENAME varname=rootname varname=rootname ...]
[/SEPARATOR = {"." }]
{“string”}]
[/INDEX = varlist]
[/GROUPBY = {VARIABLE**}]
{INDEX }]
[/DROP = varlist]

and then to

2. do this?

GENLINMIXED
[/DATA_STRUCTURE]
SUBJECTS = fieldName[*fieldName[*...]]
[REPEATED_MEASURES = fieldName[*fieldName[*...]]]
[GROUPING = fieldName[*fieldName[*...]]]
[COVARIANCE_TYPE = DIAGONAL** | AR1 | ARMA11 | COMPOUND_SYMMETRY | IDENTITY
TOEPLITZ | UNSTRUCTURED | VARIANCE_COMPONENTS]
/FIELDS
TARGET = fieldName
[TRIALS = {NONE** }]
{VALUE(number) }
{FIELD(fieldName)}
[ANALYSIS_WEIGHT = fieldName]
[OFFSET = {NONE** }]
{VALUE(number) }
{FIELD(fieldName)}
[/TARGET_OPTIONS]
[REFERENCE = value]
[DISTRIBUTION = NORMAL | BINOMIAL | MULTINOMIAL | GAMMA |
INVERSE_GAUSSIAN | NEGATIVE_BINOMIAL | POISSON]
[LINK = IDENTITY | CAUCHIT | CLOGLOG | LOG | LOGC | LOGIT | NLOGLOG | POWER | PROBIT ]
[LINK_PARAMETER = number]
[/FIXED]
[EFFECTS = effect [effect ...]]
[USE_INTERCEPT = TRUE** | FALSE]
[/RANDOM]
[EFFECTS = effect [effect ...]]
[USE_INTERCEPT = TRUE | FALSE**]
[SUBJECTS = fieldName[*fieldName[*...]]]
[GROUPING = fieldName[*fieldName[*...]]]
[COVARIANCE_TYPE = DIAGONAL | AR1 | ARMA11 | COMPOUND_SYMMETRY | IDENTITY
TOEPLITZ | UNSTRUCTURED | VARIANCE_COMPONENTS**]
[/RANDOM ...]
[/BUILD_OPTIONS]
[TARGET_CATEGORY_ORDER = {ASCENDING**}]
{DESCENDING }
{DATA }
[INPUTS_CATEGORY_ORDER = {ASCENDING**}]
{DESCENDING }
{DATA }
[MAX_ITERATIONS = {100** }]
{number}
[CONFIDENCE_LEVEL = {95** }]
{number}
[DF_METHOD = {RESIDUAL** }]
{SATTERTHWAITE}
[COVB = {MODEL**}]
{ROBUST }
[/EMMEANS
[TABLES = factor[*factor...]]
[COMPARE = factor]
[CONTRAST = {NONE** }]
{PAIRWISE }
{DEVIATION}
{SIMPLE }
[/EMMEANS...]
[/EMMEANS_OPTIONS]
[CONTROL = fieldName (number) [fieldName (number) ...]]
[SCALE = {ORIGINAL** }]
{TRANSFORMED}
[PADJUST = {LSD** }]
{SEQBONFERRONI}
{SEQSIDAK }
[/OUTFILE MODEL = 'file']
[/SAVE [PREDICTED_VALUES(fieldName)]]
[PREDICTED_PROBABILITY(rootname)]
[MAX_CATEGORIES({25** })]
{integer}
[CONFIDENCE(fieldName)]
[CONFIDENCE_METHOD({PREDICTEDPROBABILITY**})]
{PROBABILITYIMPROVEMENT}
[CONFIDENCE_INTERVALS(rootname)]
[PEARSON_RESIDUALS(fieldName)].

Or did I get it wrong?
But I do not know where I should paste these and whether I should make some changes in them?

Thanks again!

[blue]

Dear David!
I found VARSTOCASES on the discussion site,

but I do not seem to get it right how should I do it.

The thing is that I have to do an analysis by participants and another one by stimuli (so in one case rows are people, in the other - words).

I have found the MIXED command and I hope that it is the right one now:
MIXED dependent varname [BY factor list] [WITH covariate list]
[/CRITERIA = [CIN({95** })] [HCONVERGE({0** } {ABSOLUTE**})
{value} {value} {RELATIVE }
[LCONVERGE({0** } {ABSOLUTE**})] [MXITER({100**})]
{value} {RELATIVE } {n }
[MXSTEP({5**})] [PCONVERGE({1E-6**},{ABSOLUTE**})] [SCORING({1**})]
{n } {value } {RELATIVE } {n }
[SINGULAR({1E-12**})] ]
{value }
[/EMMEANS = TABLES ({OVERALL })]
{factor }
{factor*factor ...}
[WITH (covariate=value [covariate = value ...])
[COMPARE [({factor})] [REFCAT({value})] [ADJ({LSD** })] ]
{FIRST} {BONFERRONI}
{LAST } {SIDAK }
[/FIXED = [effect [effect ...]] [| [NOINT] [SSTYPE({1 })] ] ]
{3**}
[/METHOD = {ML }]
{REML**}
[/MISSING = {EXCLUDE**}]
{INCLUDE }
[/PRINT = [CORB] [COVB] [CPS] [DESCRIPTIVES] [G] [HISTORY(1**)] [LMATRIX] [R]
(n )
[SOLUTION] [TESTCOV]]
[/RANDOM = effect [effect ...]
[| [SUBJECT(varname[*varname[*...]])] [COVTYPE({VC** })]]]
{covstruct+}
[/REGWGT = varname]
[/REPEATED = varname[*varname[*...]] | SUBJECT(varname[*varname[*...]])
[COVTYPE({DIAG** })]]
{covstruct†}
[/SAVE = [tempvar [(name)] [tempvar [(name)]] ...]
[/TEST[(valuelist)] =
['label'] effect valuelist ... [| effect valuelist ...] [divisor=value]]
[; effect valuelist ... [| effect valuelist ...] [divisor=value]]
[/TEST[(valuelist)] = ['label'] ALL list [| list] [divisor=value]]
[; ALL list [| list] [divisor=value]]


This is the first time that I am doing something like this, so I am lost a bit and I am a little anxoius that I will make a mistake in the steps.

Thanks again!

[Mike]

Just a clarification:

Below you say:

> The thing is that I have to do an analysis by participants and another
> one
> by stimuli (so in one case rows are people, in the other - words).

II assume that you want to do this because of the arguments made by
Herbert Clark that both subjects and stimuli (words) should be
considered
random effects.  In traditional analyses, such as repeated measures
ANOVA,
subjects are a random effects factor and words are considered fixed
effects.
Because of limitation of the software of the time, to get words to be
random effect, one had to "flip" the dataset so that the words became
the
unit of analysis.  I believe that the relevant publication for this is
Clark 1973
which can be accessed here:
http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=2&cad=rja&uact=8&ved=0CDEQFjAB&url=http%3A%2F%2Fcseweb.ucsd.edu%2F~gary%2FPAPER-SUGGESTIONS%2Fclark-jvlvb-1973.pdf&ei=UVxOU-H3BvOnsATPpYGIBQ&usg=AFQjCNFYlTLJX85pIjakWlwJbvN5QMaZSQ&sig2=IPqYrzb_Mqa9PdopjZwngw
(If Url get broken search scholar.google.com for "Clark", "1973" and
"language as fixed-effect-fallacy".

However, this was a controversial assertion which not everyone in the
psycholinguistics and memory research area agreed to.  You may
want to see who cite this article and whether they are pro or con.

With newer software, factors in ANOVA can be defined as fixed
(default) or random.  You may want to take a look at the following
reference (Note: I got it from scholar.google.com and it is supposed
to be in APA format but scholar doesn't get it right):

Carson, R. J., & Beeson, C. M. (2013). Crossing language barriers:
Using crossed random effects modelling in psycholinguistics research.
Tutorials Quant Meth Psych, 9(1), 25-41.

The article is available here:
www.tqmp.org/Content/vol09-1/p025/p025.pdf

This paper by Carson & Beeson (2013) provides background, rationale
for doing an analysis where both subjects and words/stimuli are
considered
random effects, and provide SPSS examples using the MIXED procedure.

I never cared for Clark's argument but other have.  There are people
on SPSS who are unfamiliar with Clark's argument but are SPSS guru's
and can provide advice on to do the analysis presented by Carson &
Beeson.

-Mike Palij
New York University
[hidden email]




----- Original Message -----
From: "blue" <[hidden email]>
To: <[hidden email]>
Sent: Wednesday, April 16, 2014 3:45 AM
Subject: Re: WITHIN SUBJECTS ANOVA - HOW TO CHECK JUST MAIN EFFECTS IN
SPSS

> Dear David!
> I found VARSTOCASES on the discussion site,
>
> but I do not seem to get it right how should I do it.
>
> The thing is that I have to do an analysis by participants and another
> one
> by stimuli (so in one case rows are people, in the other - words).
>
> I have found the MIXED command and I hope that it is the right one
> now:
> MIXED dependent varname [BY factor list] [WITH covariate list]
> [/CRITERIA = [CIN({95** })] [HCONVERGE({0** } {ABSOLUTE**})
> {value} {value} {RELATIVE }
> [LCONVERGE({0** } {ABSOLUTE**})] [MXITER({100**})]
> {value} {RELATIVE } {n }
> [MXSTEP({5**})] [PCONVERGE({1E-6**},{ABSOLUTE**})] [SCORING({1**})]
> {n } {value } {RELATIVE } {n }
> [SINGULAR({1E-12**})] ]
> {value }
> [/EMMEANS = TABLES ({OVERALL })]
> {factor }
> {factor*factor ...}
> [WITH (covariate=value [covariate = value ...])
> [COMPARE [({factor})] [REFCAT({value})] [ADJ({LSD** })] ]
> {FIRST} {BONFERRONI}
> {LAST } {SIDAK }
> [/FIXED = [effect [effect ...]] [| [NOINT] [SSTYPE({1 })] ] ]
> {3**}
> [/METHOD = {ML }]
> {REML**}
> [/MISSING = {EXCLUDE**}]
> {INCLUDE }
> [/PRINT = [CORB] [COVB] [CPS] [DESCRIPTIVES] [G] [HISTORY(1**)]
> [LMATRIX]
> [R]
> (n )
> [SOLUTION] [TESTCOV]]
> [/RANDOM = effect [effect ...]
> [| [SUBJECT(varname[*varname[*...]])] [COVTYPE({VC** })]]]
> {covstruct+}
> [/REGWGT = varname]
> [/REPEATED = varname[*varname[*...]] |
> SUBJECT(varname[*varname[*...]])
> [COVTYPE({DIAG** })]]
> {covstruct }
> [/SAVE = [tempvar [(name)] [tempvar [(name)]] ...]
> [/TEST[(valuelist)] =
> ['label'] effect valuelist ... [| effect valuelist ...]
> [divisor=value]]
> [; effect valuelist ... [| effect valuelist ...] [divisor=value]]
> [/TEST[(valuelist)] = ['label'] ALL list [| list] [divisor=value]]
> [; ALL list [| list] [divisor=value]]
>
>
> This is the first time that I am doing something like this, so I am
> lost a
> bit and I am a little anxoius that I will make a mistake in the steps.
>
> Thanks again!
>
>
>
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/WITHIN-SUBJECTS-ANOVA-HOW-TO-CHECK-JUST-MAIN-EFFECTS-IN-SPSS-tp5725451p5725472.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

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

[blue]

Dear Mike,
yes, you are right, I would like to do an analysis by participants and stimuli,

but the main problem is

that I can not find a way to switch off the interaction-calculating procedure in repeated measures Anova.
This would be important, because the analysis by participant show a tendency to be significant (p levels at 0.11 and 0.14) and the interaction is zero,

so it was suggested to me to do the analysis without the interaction.

Thanks for the articles, I believe that I would not be confident in doing the crossed-random effects model analysis....

[blue]

P.S.
you were right, the double analysis is based on Clarks view.

[Bruce Weaver]

Here's another article on using multilevel models as an alternative to the old "Clarkian" methods.

   http://link.springer.com/article/10.3758/BF03192962

The Appendix includes both SAS and SPSS examples.

While looking for that link, I also found this "technical report", which anyone can download (no university library access required).  I've not read it, but have heard of the author*, and would guess it is probably fairly sound.

http://crr.ugent.be/papers/The%20language%20as%20fixed%20effect%20fallacy%20Version%202%200.pdf


* Years ago, I used a very nice Turbo Pascal timer routine Brysbaert published in Behavior Research Methods, Instruments & Computers.  Those who are interested in a little history can view it here:  http://link.springer.com/article/10.3758/BF03209826.


HTH.

blue wrote

Dear Mike,
yes, you are right, I would like to do an analysis by participants and stimuli,

but the main problem is

that I can not find a way to switch off the interaction-calculating procedure in repeated measures Anova.
This would be important, because the analysis by participant show a tendency to be significant (p levels at 0.11 and 0.14) and the interaction is zero,

so it was suggested to me to do the analysis without the interaction.

Thanks for the articles, I believe that I would not be confident in doing the crossed-random effects model analysis....

[blue]

Thanks Bruce,
the second one seems very interesting
.

[Mike]

I'd like to thank Bruce as well, especially for the second paper.
I have some old unpublished data that could be re-analyzed
by multilevel methods.  Looks like I know what I'm going to do
this summer (but I may have to draw the line at learning R ;-)

-Mike Palij
New York University
[hidden email]



----- Original Message -----
From: "Bruce Weaver" <[hidden email]>
To: <[hidden email]>
Sent: Wednesday, April 16, 2014 9:15 AM
Subject: Re: WITHIN SUBJECTS ANOVA - HOW TO CHECK JUST MAIN EFFECTS IN
SPSS

> Here's another article on using multilevel models as an alternative to
> the
> old "Clarkian" methods.
>
>   http://link.springer.com/article/10.3758/BF03192962
>
> The Appendix includes both SAS and SPSS examples.
>
> While looking for that link, I also found this "technical report",
> which
> anyone can download (no university library access required).  I've not
> read
> it, but have heard of the author*, and would guess it is probably
> fairly
> sound.
>
> http://crr.ugent.be/papers/The%20language%20as%20fixed%20effect%20fallacy%20Version%202%200.pdf
>
>
> * Years ago, I used a very nice Turbo Pascal timer routine Brysbaert
> published in Behavior Research Methods, Instruments & Computers.
> Those who
> are interested in a little history can view it here:
> http://link.springer.com/article/10.3758/BF03209826.
>
>
> HTH.
>
>
>
> blue wrote
>> Dear Mike,
>> yes, you are right, I would like to do an analysis by participants
>> and
>> stimuli,
>>
>> but the main problem is
>>
>> that I can not find a way to switch off the interaction-calculating
>> procedure in repeated measures Anova.
>> This would be important, because the analysis by participant show a
>> tendency to be significant (p levels at 0.11 and 0.14) and the
>> interaction
>> is zero,
>>
>> so it was suggested to me to do the analysis without the interaction.
>>
>> Thanks for the articles, I believe that I would not be confident in
>> doing
>> the crossed-random effects model analysis....
>
>
>
>
>
> -----
> --
> 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/WITHIN-SUBJECTS-ANOVA-HOW-TO-CHECK-JUST-MAIN-EFFECTS-IN-SPSS-tp5725451p5725481.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

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

[Ryan]

Hey Bruce,

I just read the article below. I learned a great deal about this area of research by reading the article. Quite informative! Also, I like how the author demonstrates that LMMs will yield the same results as GLMs under certain conditions, and then discusses how LMMs can go beyond that of GLMs in ways germane to the content area. IMHO, we need more articles/books that bridge the gap between GLMs and LMMs in a similar way.

I would have liked to have seen:

1. Avoidance of specifying an UNstructured covariance matrix when there is a single random intercept term on a RANDOM statement

2. Likelihood Ratio Tests for the covariance parameters in SPSS rather than relying on the default Wald Tests, particularly since they seemed to be critical of the default Wald tests

3. The actual multilevel equation(s)--I think including the multilevel equations could help explain how the RANDOM components are connected to the FIXED component

These are relatively minor issues given the overall objective of the article, which was clearly achieved. It's a great read and certainly something I will share with others. 

Thanks for sharing this article.

Ryan

On Wed, Apr 16, 2014 at 9:15 AM, Bruce Weaver <[hidden email]> wrote:

Here's another article on using multilevel models as an alternative to the
old "Clarkian" methods.

   http://link.springer.com/article/10.3758/BF03192962

The Appendix includes both SAS and SPSS examples.

While looking for that link, I also found this "technical report", which
anyone can download (no university library access required).  I've not read
it, but have heard of the author*, and would guess it is probably fairly
sound.

http://crr.ugent.be/papers/The%20language%20as%20fixed%20effect%20fallacy%20Version%202%200.pdf


* Years ago, I used a very nice Turbo Pascal timer routine Brysbaert
published in Behavior Research Methods, Instruments & Computers.  Those who
are interested in a little history can view it here:
http://link.springer.com/article/10.3758/BF03209826.


HTH.



blue wrote

> Dear Mike,
> yes, you are right, I would like to do an analysis by participants and
> stimuli,
>
> but the main problem is
>
> that I can not find a way to switch off the interaction-calculating
> procedure in repeated measures Anova.
> This would be important, because the analysis by participant show a
> tendency to be significant (p levels at 0.11 and 0.14) and the interaction
> is zero,
>
> so it was suggested to me to do the analysis without the interaction.
>
> Thanks for the articles, I believe that I would not be confident in doing
> the crossed-random effects model analysis....

-----
--
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/WITHIN-SUBJECTS-ANOVA-HOW-TO-CHECK-JUST-MAIN-EFFECTS-IN-SPSS-tp5725451p5725481.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