Is there a EUR/USD exchange rate before the euro existed?

I am dealing with unbalanced designs - comparing groups with different sample sizes,

however I'm not sure I cancompare groups with different sample sizes while performing 2-way PERMANOVA.

Hi everybody,

I am trying to run a flexible factorial analysis with one factor (with 12 factors levels) and 14 subjects using the SPM GUI.

My design matrix looks fine but estimation fails with this error message:

Failed 'Model estimation'

Index exceeds the number of array elements (0).

- But as soon as I enter only 12 subjects, the analysis works fine.

Attached see my batch.

Does anyone have experienced similar problems? I would appreciate any kind of suggestion how to solve this error.

Thank you!

I am trying to build first level GLMs in SPM for a memory task which has 3 stimuli types (X, Y, and Z) and two possible response types for each condition (“A” and “B”). I want to have regressors for each response type and stimuli (so six total conditions to model), however there are some conditions that never occur in some subjects (e.g. some subjects never response “A” to Z, others never respond “B” to X).

Is it okay if some subjects’ first level models just don’t include regressors for conditions that never happened for them? If not, how could I include that regressor if SPM does not allow empty values for onset and duration of conditions?

Any insights would be appreciated! Thank you!

I am trying to programming fMRI (BOLD) data processing via SPM12 using MATLAB. I have four stimuli that each participant should note and respond according to each stimulus. When I want to set conditions for 1st-Level, in data some runs lack some stimuli (some of the stimuli have not been used). for example, there is no second-stimulus in run-2, but in others have been used.

Now, should I define an empty vector/zero value for "Onsets of the Condition" or in general I should not set a second-stimulus condition for run-2?

Dear SPM-Experts,

I have set up a full factorial model on the second level in which I compare two groups (factor 1: experimental group vs. control) and two time points: pre vs post (factor 2).

I was wondering whether the contrast images for factor 2 can stem from the same first-level GLM? Specifically, there, I modelled the pre- and post-session within one GLM and defined various contrasts already on the first level, for instance, differential contrast pre vs. post (1 -1 and other regressors 0), mean activity pre (1 0), mean activity post (0 1). For the second-level full factorial model , I guess I would use then the mean activity pre (1 0) and mean activity post (0 1) contrast images from the first level as inputs (for the two levels of factor 2).

Alternatively, one could run two first-level GLMs - one for only the pre session, and one for only the post-session, and then use those mean activity contrast images for the second-level model.

However, I would prefer the first option, because then one could already compare the pre vs. post activity on the first-level. This way one could also use this difference contrast on the second level and run for instance a simple two-sample t-test, comparing the two groups.

I hope that my prefered variant (modeling both pre- and post-session in one first-level model) is also fine for the second-level full factorial model. Or is the alternative variant (separate first-level models for pre and post) preferable? And if so, why? I am not completely sure if these two variants should produce the same or similar results anyway. My intuition is yes, at least similar. On the other hand, I think that when modeling both pre- and post-session in one model the mean baseline activity to which, for instance, pre-activity-only is compared, is quite different (because it also includes post-activity) then when keeping them separate.

Maybe someone can help. Thanks a lot!

Stefan

I have completed a study with the following design:

3 visits/conditions (intervention A, intervention B, control)

3 timepoints/stages per visit (pre-intervention, immediately post-intervention, 1hr post-intervention)

Numerous outcome measures of skin blood flow (each analysed independently)

All participants completed all 3 visits and stages.

I am using SPSS to analyse the results using linear mixed modelling.

The covariance structures with lowest information criteria are auto-regressive first order heterogenous (ARH1) and unstructured. Half of my outcome measures prefer ARH1, the other half unstructured.

A) is there an inherent reason to use either structure for ALL measures? Or,

B) as each measure is analysed independently, can I use a different structure for each measure as determined by information criteria?

Thanks!

I have functional connectivity .mat matrices and need to convert to fishers z score.

Thank you

Dear all,

I run an ECM model and these are my post-estimation results:

Durbin-Watson (autocorrelation): 2.1638

Breusch-Godfrey (autocorrelation): 0.4418

RAMSEY (omitted variables): 0.3565

Jarque-Bera (normality): 0.1119

How can heteroscedasticity be corrected for ? Again, if any of these tests are significant, does that invalidate the regression results?

Thanks!