So like I said, a One-way FIXED effects Between Subject ANOVA in SPSS.

I want to run this ANOVA to see how study participants answered a 20-item questionnaire, based on 4 different conditions.

So, I have everyone's score on the 20 item questionnaire (and its mean), and it split between 4 different groups (Group 1, Group 2, Group 3, Group 4).

It is to test how people response to this questionnaire, under these 4 different conditions.

Any help? ]]>

I have a weird problem that I've never encountered before. I'm hoping someone else might provide their insight.

I am conducted a study where the same individuals are received 5 consecutive trials under two different conditions, let's call them easy and hard.

For both the easy and hard conditions, individuals rarely ever get the first trial correct. So let's say their accuracy is at approximately 0% on trial 1.

After trial 1, however, individuals experiencing easy condition are more likely to get trials 2-5 correct when compared to when they experience the hard condition. Accuracy improves with each trial number, just to a considerably greater extent in the easy condition (so imagine a steeper slope for easy relative to hard when plotting accuracy by trial number).

I performed a Repeated Measures ANOVA looking at difficulty condition and trial number. I included Trial 1 in the analysis because it acts as an anchor point where the two conditions are equated. When I include Trial 1, I get a significant interaction.

I have received some criticism for including Trial 1 in the analysis because there's virtually no way for participants to get it correct, and thus, is inappropriate to include. My rationale for including it is because I am interested in how individuals learn more rapidly in easy conditions relative to hard.

Am I violating some statistical assumption by including Trial 1? Or do you see any issues with my original analysis?

Thank you, and any feedback is greatly appreciated! ]]>

Thank you in advance for reading, and for trying to help!

To put it briefly.. I am working with Structural Equiation Modeling (for the first time :S). In this study, we have 1000+ participants and we are studying the relationship between alcohol use and a personality construct.

Personality is measured with different validated questionnaires, but alcohol use is measured using a Likert-type scale on the number of times the participant has used alcohol in the last month (this is the usual way to measure alcohol use), so that: 0 (never), 1 (1-3 times), 2 (4-7 times), 3 (8-12 times), etc... up to 7 (40+ times)

My question is..

Other models with other alcohol use outcomes (validated questionnaires for example) show a pretty decent fit. However, models with this Likert-type variable usually show good CFI (>.95)... but low TLI (0.70-0.85) and sufficiently high RMSEA (0.10 - 0-13) as to reject the models..

Is it possible that this Likert-type format is hindering our chances to find a good fit? Is there any way (e.g. recoding the variable? reducing levels of the variable?) that could help improving the fit? i.e. reducing RMSEA...

Otherwise I'm guessing I'll just have to reject the models... what else :D

Thank you very much in advance!!

Best

S ]]>